[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M78BMMK0GYFDP540MCZZHGHD":3,"skill-same:01M78BMMK0GYFDP540MCZZHGHD":57},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":16,"categories":17,"keywords":18,"publishedAt":19,"linkOnly":20,"markdownContent":21,"markdownBody":22,"frontMatter":23,"refName":37,"commitSha":38,"skillDirectory":39,"forksCount":14,"repositoryHtmlUrl":40,"repositoryHomepageUrl":41,"ownerHtmlUrl":42,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":43,"install":44,"resources":56},"01M78BMMK0GYFDP540MCZZHGHD","cv-generator",null,"Generate professional, ATS-optimized CVs for FlowCV, Canva, Google Docs, or Word. Handles multi-source merging, JD targeting, seniority adaptation, and humanized rewriting. Outputs paste-ready text with an ATS flaw report and improvement suggestions.","princepatel04477-web\u002Ftrivoxa-group","princepatel04477-web","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F227740714?v=4","01M788ZAJ2KECD5KXVP55PZXKS","Prince Patel","01M788ZAJTCN8YSD737MRSKC5Q",0,"MIT","https:\u002F\u002Fgithub.com\u002Fprincepatel04477-web\u002Ftrivoxa-group\u002Fblob\u002Fmaster\u002F.github\u002Fskills\u002Fcv-generator\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: cv-generator\ndescription: \"Generate professional, ATS-optimized CVs for FlowCV, Canva, Google Docs, or Word. Handles multi-source merging, JD targeting, seniority adaptation, and humanized rewriting. Outputs paste-ready text with an ATS flaw report and improvement suggestions.\"\ncategory: content\nrisk: safe\nsource: community\ndate_added: \"2026-06-06\"\nauthor: \"WHOISABHISHEKADHIKARI\"\nuser-invokable: true\ntags:\n  - cv\n  - resume\n  - ats\n  - career\n  - job-application\n  - career-change\n---\n\n# CV Generator Skill — FlowCV \u002F Canva Edition\n\n## When to Use\n\nUse this skill when you need to:\n- Generate a professional, ATS-optimized CV from multiple sources (LinkedIn, GitHub, Portfolio).\n- Tailor an existing CV for a specific Job Description (JD).\n- Improve the language, metrics, and structure of a draft resume.\n- Prepare a paste-ready version of your CV for tools like FlowCV or Canva.\n\nTurns raw profile data into a polished, ATS-ready CV. Outputs a paste-ready plain-text\nversion formatted for FlowCV, Canva, Google Docs, or Word — with a flaw report and\nmissing-info checklist.\n\n---\n\n## FLAW REGISTER — KNOWN ISSUES FIXED IN THIS VERSION\n\nThe following issues were identified across the two prior skill drafts and are corrected here:\n\n| # | Flaw | Fix applied |\n|---|------|-------------|\n| F-01 | Output was Markdown-first, not paste-ready plain text | Final output is plain text; Markdown is internal staging only |\n| F-02 | FlowCV\u002FCanva field structure was never addressed | Section mapping to tool fields added (section 11c) |\n| F-03 | Questionnaire dumped all 20 questions at once in practice | Hard rule: one question at a time, wait for answer |\n| F-04 | Anti-hallucination rules listed but never enforced structurally | Enforcement gate added before every output (section 10) |\n| F-05 | Cover letter was offered but never scoped for these tools | Cover letter now outputs to a separate plain-text block, not inline |\n| F-06 | ATS check listed but had no scored output | Flaw report now scores 0–100 with per-item pass\u002Ffail |\n| F-07 | Seniority detection was \"detect or ask\" with no fallback | Default is mid-level if undetectable; user is told the assumption |\n| F-08 | No guidance on what FlowCV\u002FCanva cannot render | Added explicit field-by-field paste map (section 11c) |\n| F-09 | Tense rules stated but never verified in quality gate | Tense check is now a hard gate — output blocked until corrected |\n| F-10 | \"Passionate about\" and similar banned phrases still appeared in examples | Phrase blocklist now machine-checkable (section 7c) |\n| F-11 | Nepal\u002FSouth Asia market conventions were present but incomplete | Confirmed and expanded (section 14) |\n| F-12 | No explicit rule on what to do when LinkedIn scraping is blocked | Hard fallback rule: ask for PDF export immediately, do not proceed empty |\n| F-13 | File naming convention mentioned once, never enforced | File name rule is part of the final output block (section 11) |\n| F-14 | Skill had no version history or upgrade path | Version field added to frontmatter |\n| F-15 | GitHub was listed as a source but extraction rules were missing | GitHub extraction rules added (section 4f) |\n\n---\n\n## 1. Invocation\n\n```\nUse @cv-generator to build my CV from my LinkedIn PDF.\nUse @cv-generator to tailor my CV for this job description.\nUse @cv-generator to improve my existing draft.\nUse @cv-generator to create a fresh CV via questionnaire.\nUse @cv-generator — I want a FlowCV-ready output.\n```\n\nAny combination of sources is valid. Multiple sources are merged and deduplicated\nbefore writing begins.\n\n---\n\n## Source Selection\n\nAsk the user which source(s) to use. At least one is required.\nIf no source is provided, default immediately to the questionnaire (section 4d).\n\n| # | Source | Instruction |\n|---|--------|-------------|\n| 1 | LinkedIn profile URL | Fetch page; extract all visible sections. **If blocked or empty: immediately ask for a LinkedIn PDF — do not proceed on an empty extraction.** |\n| 2 | LinkedIn PDF export | Parse uploaded file. If scanned image: apply OCR and warn the user to verify accuracy. |\n| 3 | Portfolio \u002F personal website | Fetch URL; extract About, Projects, Skills, Services, Testimonials, Case Studies, Contact. |\n| 4 | Questionnaire | Step-by-step (section 4d). One question at a time. |\n| 5 | Existing CV or draft | Upload or paste; improve only — never alter facts. |\n| 6 | GitHub profile | Extract pinned repos, bio, tech stack, contribution summary (section 4f). |\n| 7 | Resume file (DOCX \u002F PDF \u002F TXT) | Parse and rewrite. Flag scanned PDFs; apply OCR. |\n\n---\n\n## Purpose, seniority, and format\n\n### Purpose\n\nAsk after source selection:\n\n> \"What is the main purpose of this CV?\"\n\n| Purpose | Key adaptation |\n|---------|----------------|\n| Applying for a specific job | Full JD analysis + keyword targeting (section 9) |\n| General professional CV | Balanced, role-agnostic, reverse-chronological |\n| Internship \u002F entry-level | Education and projects lead; transferable skills foregrounded |\n| Academic \u002F research | Publications, grants, teaching, research interests |\n| Freelance \u002F client proposal | Deliverables, outcomes, services |\n| Career change | Functional or hybrid; transferable skills reframed |\n| Executive \u002F board-level | Executive summary, board positions, P&L scope |\n| Military-to-civilian | Translate ranks and jargon to civilian equivalents |\n| Return to work \u002F career break | Frame gap positively; emphasise upskilling |\n| Other | Ask the user to describe the goal in one sentence |\n\n### Seniority\n\nDetect from data. If undetectable, **default to mid-level and tell the user:**\n> \"I've assumed mid-level (3–8 years). Let me know if this should be different.\"\n\n| Level | Years | CV emphasis |\n|-------|-------|-------------|\n| Student \u002F fresh graduate | 0–1 | Education first; projects; extracurriculars; 1 page |\n| Junior \u002F entry | 1–3 | Skills + education prominent; 1 page |\n| Mid-level | 3–8 | Experience leads; achievements over duties; 1–2 pages |\n| Senior | 8–15 | Leadership, scope, impact, mentoring; 2 pages |\n| Executive \u002F C-suite | 15+ | Strategic narrative; board roles; P&L; 2–3 pages |\n| Academic | Any | No page limit; publications; grants; teaching |\n\n### Format\n\n| Format | Use when |\n|--------|----------|\n| Chronological (default) | Clear career progression; most job applications |\n| Functional \u002F skills-first | Career changers; large gaps; military-to-civilian |\n| Hybrid \u002F combination | Senior professionals rebranding; career changers with strong experience |\n| Academic CV | University, research, PhDs, postdocs |\n| Executive \u002F Board bio | C-suite, NED, advisory |\n| Portfolio-led | Designers, architects, creatives |\n\n---\n\n## Data extraction rules\n\n### LinkedIn URL\n\nIf the page is blocked or returns no content, **stop immediately** and ask:\n> \"LinkedIn blocked the fetch. Please export your LinkedIn profile as a PDF\n> (LinkedIn → Me → Settings → Data Privacy → Get a copy of your data) and upload it.\"\n\nIf accessible, extract in order:\n1. Full name and headline\n2. Contact information (email, phone, location — public only)\n3. About \u002F Professional Summary\n4. Work experience: title, company, location, dates, bullets\n5. Education: degree, institution, dates, grade\u002Fhonours\n6. Skills (flag top endorsed skills)\n7. Certifications and licences\n8. Projects\n9. Achievements, honours, awards\n10. Volunteer experience\n11. Languages and proficiency\n12. Publications, patents, courses\n\n### LinkedIn PDF\n\nHard rules:\n- Extract only what is physically present in the document.\n- Preserve all dates exactly as written.\n- If a section is absent, mark it **[Not provided]** — do not skip silently.\n- Do not merge bullets across different roles.\n- If scanned: apply OCR and display this warning before continuing:\n  > \"OCR was used to read this document. Please review the extracted text below\n  > for accuracy before we continue.\"\n\n### Portfolio \u002F personal website\n\nExtract:\n- About \u002F bio → Professional Summary\n- Projects: name, description, technologies, outcomes, live\u002Frepo URLs\n- Skills and services\n- Testimonials or client logos → Achievements\n- Case studies → 2–4 bullets each\n- Blog posts or articles → Publications \u002F Thought Leadership\n- Contact details\n\n### Questionnaire\n\n**One question at a time. Wait for the answer before continuing.**\nDo not display the full list unless the user explicitly asks for a form.\n\n```\nQ1.  Full legal name (as it should appear on the CV)\nQ2.  Target job title or role\nQ3.  Email address\nQ4.  Phone number including country code (optional but recommended)\nQ5.  City and country of residence\nQ6.  LinkedIn URL (optional)\nQ7.  Portfolio, GitHub, or personal website URL (optional)\nQ8.  Professional summary — describe yourself in 2–3 sentences (will be rewritten)\nQ9.  Work experience — for EACH role:\n       - Job title\n       - Company name and industry\n       - Employment type (full-time \u002F part-time \u002F contract \u002F freelance \u002F internship)\n       - Location or Remote\n       - Start and end date (or \"Present\")\n       - 3–6 key responsibilities and achievements\n       - Any measurable results (numbers, %, revenue, team size, budget)\nQ10. Education — for EACH qualification:\n       - Degree or certificate name\n       - Institution name and country\n       - Start and graduation year\n       - Grade, GPA, or classification if notable\n       - Thesis or relevant modules (optional; for academic\u002Fentry-level only)\nQ11. Technical and professional skills\n       (ask to separate: Expert \u002F Proficient \u002F Familiar)\nQ12. Projects — for each:\n       - Name\n       - Purpose\n       - Your specific role\n       - Technologies or methods used\n       - Outcome or impact\nQ13. Certifications (name, issuing body, date, expiry if applicable)\nQ14. Achievements, awards, or recognitions\nQ15. Languages and proficiency: Native \u002F Fluent \u002F Professional \u002F Conversational \u002F Basic\nQ16. Volunteer or open-source work (optional)\nQ17. Publications, speaking engagements, press mentions (optional)\nQ18. Preferred CV format: chronological \u002F functional \u002F hybrid \u002F academic \u002F executive\nQ19. Target country or job market\nQ20. Any employment gaps? Dates and brief reason — will be framed constructively.\n```\n\n### Existing CV or draft\n\nRules:\n- Preserve every fact: titles, companies, dates, institutions, grades.\n- Rewrite weak or passive bullets with strong action verbs.\n- Remove repetition across roles.\n- Correct grammar, punctuation, spelling.\n- Fix tense: past for completed roles, present for current role.\n- Replace all banned phrases (section 7c).\n- Improve ATS keyword density where natural — do not keyword-stuff.\n- Restructure section order if it does not match target market or seniority.\n- **Do not add experience, qualifications, metrics, or skills not present in the original.**\n\n### GitHub profile\n\nExtract:\n- Bio \u002F tagline → supplement Professional Summary\n- Pinned repositories: name, description, tech stack, stars\u002Fforks\n- Contribution activity (years active, languages used)\n- README content for context on major projects\n- Do not infer seniority from commit count alone\n\n### Employment gaps and special situations\n\n**Gap under 3 months:** no special treatment.\n\n**Gap 3–12 months:** one-line entry:\n> \"Career break — [brief honest reason: personal development \u002F caregiving \u002F travel \u002F health]\"\n\n**Gap over 12 months:** add a neutral framing entry in the experience section;\nhighlight any upskilling, freelance, volunteering, or relevant activity during the gap.\nNever fabricate activity.\n\n**Contract \u002F freelance \u002F part-time:** label employment type clearly. Group multiple\nshort contracts under one umbrella entry (e.g. \"Freelance Consultant\") if they share\na skill area.\n\n**Concurrent roles:** list both with accurate overlapping dates; add \"(concurrent with\n[other role])\" if helpful.\n\n**Early or irrelevant roles (> 10 years):** condense to one line for senior professionals\nunless directly relevant to the target role.\n\n**Fresh graduate:** lead with Education → Projects → Skills → Internships.\nUse academic projects as proof of practical skills.\n\n**Military-to-civilian:** translate all ranks and jargon to civilian equivalents;\nquantify command scope (e.g. \"Managed 35 personnel and $2M in equipment\").\n\n**Non-English source:** translate accurately; preserve institution and company names\nin the original language with an English translation in parentheses on first use;\nadvise the user to have the translation reviewed by a native speaker.\n\n---\n\n## Multi-source merging\n\n1. Build a master profile combining all extracted data.\n2. Deduplicate: keep the most detailed version of each entry.\n3. If two sources conflict on a date or title, flag it and ask the user to confirm.\n4. Identify gaps; ask follow-up questions only for critical missing data.\n5. Never fabricate a detail — mark it **[Not provided]** until the user confirms.\n\n---\n\n## CV section order\n\n### Chronological (default — mid \u002F senior)\n```\n1.  Full Name\n2.  Contact Information (email | phone | LinkedIn | portfolio | city, country)\n3.  Professional Summary\n4.  Core Skills\n5.  Work Experience (reverse chronological)\n6.  Education (reverse chronological)\n7.  Certifications and Licences\n8.  Projects\n9.  Technical Skills (grouped: Languages | Frameworks | Tools | Platforms)\n10. Achievements and Awards\n11. Volunteer Experience\n12. Publications \u002F Speaking\n13. Languages\n14. Additional Information\n```\n\n### Fresh graduate \u002F student\n```\n1.  Full Name + Contact Information\n2.  Professional Summary \u002F Objective\n3.  Education\n4.  Projects and Coursework\n5.  Skills\n6.  Work Experience \u002F Internships\n7.  Certifications\n8.  Extracurricular \u002F Volunteer\n9.  Languages\n```\n\n### Functional \u002F skills-first (career changers, large gaps)\n```\n1.  Full Name + Contact Information\n2.  Professional Summary\n3.  Core Competencies \u002F Skills\n4.  Key Achievements\n5.  Work History (company, title, dates — minimal bullets)\n6.  Education\n7.  Certifications\n8.  Languages\n```\n\n### Academic CV\n```\n1.  Full Name + Contact + ORCID \u002F ResearchGate\n2.  Research Interests\n3.  Education\n4.  Academic Positions\n5.  Publications\n6.  Grants and Funding\n7.  Teaching Experience\n8.  Supervision\n9.  Awards and Honours\n10. Conference Presentations\n11. Professional Memberships\n12. Skills\n13. References\n```\n\n### Executive \u002F Board\n```\n1.  Full Name + Contact Information\n2.  Executive Summary\n3.  Core Competencies\n4.  Board and Advisory Roles\n5.  Executive Experience\n6.  Education and Qualifications\n7.  Publications \u002F Media \u002F Speaking\n8.  Professional Memberships\n```\n\n---\n\n## Writing rules\n\n### Professional Summary\n\nWrite 3–5 sentences (executive: 5–7) covering:\n1. Who the person is: job title + years of experience\n2. Primary domain of expertise\n3. One concrete differentiator or standout achievement\n4. Value proposition aligned to the target role\n\n- Do not open with \"I am\".\n- Do not open with any banned phrase (section 7c).\n- Base strictly on data collected — no padding.\n\nGood example:\n> \"Software engineer with seven years building distributed systems at scale.\n> Deep expertise in Go and Kubernetes, with a track record of cutting infrastructure\n> costs 30–40% through cloud-native redesigns. Seeking a staff-level role where\n> systems reliability and platform engineering intersect.\"\n\n### Experience bullets — STAR-lite\n\nPattern: `[Strong verb] + [what you did] + [scale\u002Fscope] + [outcome if available]`\n\nRules:\n- 3–6 bullets per role (2–3 for short-tenure or early roles)\n- Past tense for completed roles; present tense for current role\n- 15–30 words per bullet\n- Different verb to open each bullet — never repeat within one role\n- If no metric was provided: write a result-focused statement without inventing numbers\n- Never fabricate metrics — if the user says \"we grew a lot\", ask for specifics\n\nAction verb bank:\n\n```\nLeadership:    Led, Directed, Managed, Supervised, Mentored, Coached, Championed\nBuilding:      Built, Developed, Engineered, Architected, Designed, Implemented, Launched, Shipped\nImprovement:   Reduced, Improved, Optimised, Streamlined, Accelerated, Automated, Consolidated\nAnalysis:      Analysed, Researched, Evaluated, Identified, Diagnosed, Assessed, Mapped\nCommunication: Presented, Authored, Documented, Trained, Negotiated, Advised, Collaborated\nGrowth:        Grew, Expanded, Scaled, Generated, Increased, Secured, Delivered\nStrategy:      Defined, Established, Prioritised, Planned, Coordinated, Oversaw, Aligned\n```\n\nRewrites:\n```\nBEFORE: \"Responsible for managing the team\"\nAFTER:  \"Managed a cross-functional team of 8 engineers, delivering the product roadmap\n         on schedule for three consecutive quarters\"\n\nBEFORE: \"Helped with developing new features\"\nAFTER:  \"Developed four customer-facing features in React, reducing support tickets by 25%\"\n\nBEFORE: \"Was involved in the migration project\"\nAFTER:  \"Led migration from monolith to microservices, cutting deployment time from\n         45 minutes to under 4 minutes\"\n```\n\n### Banned phrases — machine-checkable blocklist\n\nBefore output, scan the full CV text and **reject any bullet or sentence containing**\nany of the following strings (case-insensitive):\n\n```\nresults-driven\ndynamic individual\nhighly motivated\nteam player\nproven track record\npassionate about\npassionate professional\ndetail-oriented\nself-starter\nhard worker\nstrong communication skills\nexcellent communication\nsynergy\nleverage (when used as a verb meaning \"use\")\nparadigm shift\nthought leader\ngo-getter\ninnovative thinker\noutside the box\npeople person\nvisionary\nchange agent\n```\n\nIf found: rewrite the sentence to show the specific evidence instead.\n\n### Tense enforcement\n\nThis is a hard gate — output is blocked until tense is correct:\n\n- **Completed role** → all bullets in past tense (Led, Built, Reduced...)\n- **Current role** → all bullets in present tense (Lead, Build, Reduce...)\n- **Mixed tense within one role** → always fail; fix before output\n\n### Acronym and terminology\n\n- Spell out on first use: \"Machine Learning (ML)\"; use abbreviation thereafter.\n- Consistent capitalisation throughout: \"JavaScript\" not \"Javascript\".\n- Mirror exact JD phrasing where applicable.\n- Include both full form and abbreviation for searchability.\n\n---\n\n## ATS optimisation\n\n### Structural rules\n\n| Rule | Why it matters |\n|------|----------------|\n| Name must be the very first line of the body | Parsers read top-to-bottom; name in header\u002Ffooter is often missed |\n| Contact info in body, not in header or footer | Header\u002Ffooter text is invisible to Taleo, Workday, iCIMS |\n| Single-column layout only | Two-column layouts break ATS text extraction order |\n| No tables for layout | Table cells are read in unpredictable order |\n| No text boxes, shapes, or SmartArt | Text inside shapes is invisible to ATS |\n| No images or photos (unless market requires it) | Images are ignored; photos risk bias filtering |\n| No icons in bullets or headings | Symbols like ➤ ✓ ★ corrupt parsed text |\n| Bullet characters: hyphen (-) or plain dot (•) only | Safe across all ATS platforms |\n| Standard section headings only | Non-standard headings cause misclassification |\n| No \"Objective\" heading | Flags CV as outdated; use \"Professional Summary\" |\n| Font: minimum 10pt body, 12–14pt headings | Smaller text garbles in PDF-to-text conversion |\n| Margins: minimum 0.5 in \u002F 1.27 cm all sides | Narrow margins cause line-wrapping errors |\n| Spell out all URLs fully | Anchor text loses URL when ATS strips formatting |\n| File format: .docx preferred for ATS; PDF for email | DOCX parses more accurately in most ATS |\n| File name: FirstName_LastName_CV.docx | Generic names (\"resume.pdf\") get buried in recruiter files |\n\n### Keyword strategy\n\n1. Extract top 10–20 keywords from the JD (if provided).\n2. Categorise: hard skills | soft skills | qualifications | industry terms.\n3. For each keyword, record:\n   - Present and prominent\n   - Present but weak or buried → strengthen placement\n   - Absent but user has the skill → weave in naturally\n   - Absent and user lacks the skill → do not add\n4. Target keyword density: 2–4 natural occurrences per hard skill across the full CV.\n5. Include both spelled-out form and abbreviation for key terms.\n6. Mirror exact JD phrasing for shared responsibilities.\n\n### ATS platform quick notes\n\n| Platform | Key quirk |\n|----------|-----------|\n| Workday | DOCX preferred; complex PDF tables fail |\n| Taleo | Strictest; no special characters; plain text preferred |\n| Greenhouse | Lenient; weights keyword frequency |\n| Lever | Modern parser; handles most formats |\n| iCIMS | DOCX preferred; strips header\u002Ffooter text |\n| SmartRecruiters | Handles DOCX and PDF; relatively lenient |\n\nDefault when platform is unknown: apply Taleo-level strictness.\n\n---\n\n## Job description integration\n\nWhen a JD is provided, run four steps:\n\n**Step 1 — Parse:**\n- Job title and seniority signals\n- Required vs preferred qualifications\n- Hard skills: tools, languages, platforms, methodologies\n- Soft skills and collaboration patterns\n- Industry terminology\n- Responsibility verb phrases (mirror these in bullets)\n\n**Step 2 — Score:**\nFor each of the top 15 keywords, mark: present and prominent \u002F present but weak \u002F\nabsent.\n\n**Step 3 — Integrate:**\n- Strengthen weak keyword placements.\n- Weave in missing keywords the user genuinely has experience with.\n- Never add a keyword the user cannot truthfully claim.\n\n**Step 4 — Report (include at end of output):**\n```\nJD KEYWORD MATCH REPORT\nTotal JD keywords identified: 18\nMatched in CV: 14 (78%)\nAdded naturally during generation: 3\nNot added (user lacks skill): 1 — Salesforce\nRecommendation: even limited Salesforce exposure is worth noting if any exists\n```\n\n---\n\n## Anti-hallucination enforcement gate\n\nBefore any output is produced, confirm every item in the CV passes this check.\n**Output is blocked until all items pass.**\n\n| Item | Rule |\n|------|------|\n| Job titles | Sourced directly from user data — not inferred or upgraded |\n| Company names | Sourced directly — not corrected, normalised, or embellished |\n| Dates | Reproduced exactly as provided — no normalisation without noting it |\n| Degrees and institutions | Reproduced exactly as provided |\n| Certifications | Only those explicitly named by the user |\n| Metrics and numbers | Only those provided by the user — never approximated or invented |\n| Awards and achievements | Only those named by the user |\n| Skills and tools | Only those provided or clearly evidenced in source data |\n| Projects | Only those named by the user |\n\nIf any item cannot be verified: mark it **[Not provided]** and include it in the\nmissing information checklist (section 11d). Never fill gaps silently.\n\n---\n\n## Final output — deliver in this exact order\n\n### Formatted CV (staging draft)\n\nClean plain-text draft with clear section labels. Used as the working version\nbefore generating the tool-specific paste copies below.\n\n### FlowCV paste-ready version\n\nFlowCV uses structured text fields, not free-form documents. Format accordingly:\n\n```\nFULL NAME\n[First name] [Last name]\n\nPROFESSIONAL TITLE\n[Target job title]\n\nCONTACT\nEmail: [email]\nPhone: [+country code number]\nLocation: [City, Country]\nLinkedIn: [full URL]\nPortfolio: [full URL if applicable]\n\nPROFESSIONAL SUMMARY\n[3–5 sentence plain paragraph — no bullets, no Markdown]\n\nCORE SKILLS\n[skill], [skill], [skill], [skill]\n[skill], [skill], [skill], [skill]\n\nWORK EXPERIENCE\n\n[Job Title]\n[Company Name] | [City, Country] | [Mon YYYY] – [Mon YYYY or Present]\n[Employment type if not full-time: Contract \u002F Freelance \u002F Part-time]\n- [Bullet one: action verb + context + outcome]\n- [Bullet two]\n- [Bullet three]\n\n[Repeat for each role]\n\nEDUCATION\n\n[Degree Name]\n[Institution Name], [Country] | [YYYY] – [YYYY]\n[Grade or classification if notable]\n\n[Repeat for each qualification]\n\nCERTIFICATIONS\n[Certificate Name] — [Issuing Body] — [Month YYYY]\n\nPROJECTS\n\n[Project Name]\n[Technologies: tool, tool, tool]\n- [What it does \u002F your role \u002F outcome]\n\nACHIEVEMENTS\n- [Achievement one]\n- [Achievement two]\n\nVOLUNTEER EXPERIENCE\n[Role] — [Organisation] — [YYYY–YYYY]\n- [One-line description]\n\nLANGUAGES\n[Language]: [Native \u002F Fluent \u002F Professional \u002F Conversational \u002F Basic]\n\nADDITIONAL INFORMATION\n[Anything else: open-source, interests relevant to role]\n```\n\n### Canva paste-ready version\n\nCanva CV templates use individual text boxes per section. Provide each section as\na separate clearly labelled block, with no Markdown symbols.\n\n```\n--- PASTE INTO: Name field ---\n[Full name]\n\n--- PASTE INTO: Job title \u002F headline field ---\n[Target job title]\n\n--- PASTE INTO: Contact block ---\n[email] | [phone] | [city, country] | [LinkedIn URL]\n\n--- PASTE INTO: Summary \u002F About field ---\n[3–5 sentence paragraph, plain text, no hyphens or bullets]\n\n--- PASTE INTO: Skills field ---\n[skill] | [skill] | [skill] | [skill] | [skill]\n\n--- PASTE INTO: Experience entry 1 ---\n[Job Title]\n[Company] | [Location] | [Mon YYYY – Mon YYYY]\n- [Bullet]\n- [Bullet]\n- [Bullet]\n\n[Continue for each role as a separate block]\n\n--- PASTE INTO: Education entry 1 ---\n[Degree]\n[Institution], [Country] | [YYYY – YYYY]\n[Grade if notable]\n\n--- PASTE INTO: Certifications ---\n[Certificate] | [Issuer] | [YYYY]\n\n--- PASTE INTO: Languages ---\n[Language] ([Proficiency])\n```\n\n### Missing information checklist\n\n```\nMISSING INFORMATION\n[ ] Phone number\n[ ] LinkedIn URL\n[ ] Portfolio or GitHub URL\n[ ] Measurable results for [Role] at [Company]\n[ ] Certifications — do you hold any?\n[ ] Languages — list any beyond English\n[ ] Employment gap [Mon YYYY – Mon YYYY] — add a brief framing note\n[ ] [Any other flagged item]\n```\n\n### CV flaw report (scored 0–100)\n\nRun all checks. Display a scored report:\n\n```\nCV FLAW REPORT\n──────────────────────────────────────\nScore: [X]\u002F100\n\nPASS  Truthfulness — all facts sourced from user data\nPASS  No hallucination — no fabricated details\nPASS  Tense correctness — past for completed, present for current\nPASS  ATS structure — single column, no tables or images\nPASS  Standard headings — all recognisable by parsers\nPASS  No forbidden characters — no ➤ ✓ ★\nPASS  Humanized — no banned phrases found\nPASS  Contact info in body (not header\u002Ffooter)\nFAIL  [Check name] — [specific issue and location in CV]\n──────────────────────────────────────\nDeductions: -[N] per FAIL item\nFinal score: [X]\u002F100\n\nISSUES TO FIX:\n1. [Exact location] — [Exact problem] — [Suggested fix]\n2. [Exact location] — [Exact problem] — [Suggested fix]\n```\n\nScore deductions: -10 per FAIL on truthfulness or hallucination;\n-5 per FAIL on tense, ATS structure, or banned phrases;\n-3 per FAIL on formatting issues.\n\n### Improvement suggestions (3–7, specific and actionable)\n\n- \"Your summary does not state the target role. Open with your job title explicitly.\"\n- \"The [Company] role has no metrics. Even approximate scope (team size, users, budget range) strengthens credibility.\"\n- \"Skills section mixes expert and basic tools without distinction. Group into Proficient \u002F Familiar.\"\n- \"Add a GitHub or portfolio URL — technical recruiters check it before the interview.\"\n- \"Three bullets begin with 'Responsible for' — replace with direct action verbs.\"\n- \"CV is [N] pages for [N] years of experience. Target is [N] pages; trim older roles to one line.\"\n\n### Suggested file name\n\n```\nSuggested filename: [FirstName]_[LastName]_CV.docx\n```\n\n---\n\n## Cover letter companion (optional)\n\nAfter the CV output, offer:\n\n> \"Would you like a tailored cover letter for this application?\"\n\nIf yes, output as a **separate clearly labelled plain-text block** — not inline with the CV.\n\nRules:\n- Opens with a specific hook — not \"I am writing to apply for…\"\n- References company and role by name\n- Bridges 2–3 strongest CV points to the JD's key requirements\n- Closes with a clear call to action\n- Matches tone of the target industry\n- 3 paragraphs maximum, 250–350 words\n- Does not repeat the CV verbatim\n\n---\n\n## Limitations\n\n- **No hallucination.** Never invent a title, company, date, degree, cert, skill, metric, or award.\n- **No fake metrics.** If the user says \"we grew a lot\", ask for specifics — never insert a percentage.\n- **Respect source truth.** \"Junior Developer\" stays \"Junior Developer\" — suggest a reframe if needed; never silently change it.\n- **No silent changes.** If something is materially reworded, note the change.\n- **One version at a time.** Complete the CV before offering variants.\n- **Privacy.** Do not expose full home address, national ID, DOB, marital status, or religion unless the user's target market requires it.\n- **No keyword stuffing.** Adding skills the user does not have is fraud. Flag gaps; never fabricate.\n- **OCR warning.** Always display before continuing: \"OCR was used — please verify the extracted text for accuracy.\"\n\n---\n\n## Country and market conventions\n\n| Market | Length | Photo | DOB | Marital status | References |\n|--------|--------|-------|-----|----------------|------------|\n| USA | 1–2 pages | No | No | No | \"Available on request\" |\n| Canada | 1–2 pages | No | No | No | \"Available on request\" |\n| UK | 2 pages | No | No | No | \"Available on request\" |\n| Ireland | 2 pages | No | No | No | \"Available on request\" |\n| Australia \u002F NZ | 2–3 pages | No | No | No | \"Available on request\" |\n| Germany \u002F Austria \u002F Switzerland | 2–3 pages | Yes (expected) | Yes | Sometimes | Listed or on request |\n| France | 1–2 pages | Optional | No (illegal to require) | No | On request |\n| Netherlands \u002F Scandinavia | 1–2 pages | Optional | No | No | On request |\n| Japan | 1–2 pages (rirekisho) | Yes | Yes | Yes | Listed |\n| South Korea | 1–2 pages | Yes | Yes | Yes | Listed |\n| China | 1–2 pages | Yes | Yes | Yes | Listed |\n| India | 2–3 pages | Optional | Yes (common) | Sometimes | Listed |\n| Nepal | 2–3 pages | Yes (common) | Yes | Sometimes | Listed |\n| Bangladesh \u002F Sri Lanka | 2–3 pages | Yes (common) | Yes | Sometimes | Listed |\n| UAE \u002F Gulf (GCC) | 2–3 pages | Yes (common) | Yes | Yes (sometimes) | Listed |\n| Nigeria \u002F East Africa | 2–3 pages | Yes (common) | Yes | Sometimes | Listed |\n| South Africa | 3–5 pages | Optional | Yes (common) | No | Listed |\n| Brazil | 1–2 pages | Optional | Yes (common) | No | On request |\n| Academic (global) | No limit | Varies | Varies | No | Full list required |\n| Executive \u002F board (global) | 2–3 pages | No | No | No | On request |\n\nDefault when market is unknown: UK \u002F international conventions (no photo, no DOB, 2 pages,\n\"Available on request\").\n\n---\n\n## Decision tree\n\n```\nUser invokes @cv-generator\n        |\n        v\nSource provided? --No--> Run questionnaire (Q1–Q20, one at a time)\n        |Yes\n        v\nLinkedIn URL blocked? --Yes--> Ask for PDF export immediately; do not proceed empty\n        |No\n        v\nCollect all sources --> merge and deduplicate (section 5)\n        |\n        v\nAsk: Purpose? --> Detect or assume seniority (default: mid-level; tell the user)\n        |\n        v\nSelect format (section 3c)\n        |\n        v\nSelect section order (section 6)\n        |\n        v\nJD provided? --Yes--> Parse JD --> extract and score keywords (section 9)\n        |No                  |\n        v                    v\nWrite CV content       Integrate keywords naturally\n(sections 7–8)               |\n        |\u003C-------------------+\n        v\nRun anti-hallucination gate (section 10) --> block output until all pass\n        |\n        v\nRun tense enforcement (section 7d) --> block output until all pass\n        |\n        v\nRun banned phrase scan (section 7c) --> fix any found\n        |\n        v\nOutput in order:\n  Formatted CV (staging draft)\n  FlowCV paste-ready version\n  Canva paste-ready version\n  Missing information checklist\n  CV flaw report (scored)\n  Improve suggestions\n  Suggested file name\n        |\n        v\nOffer cover letter (section 12)\n```\n","# CV Generator Skill — FlowCV \u002F Canva Edition\n\n## When to Use\n\nUse this skill when you need to:\n- Generate a professional, ATS-optimized CV from multiple sources (LinkedIn, GitHub, Portfolio).\n- Tailor an existing CV for a specific Job Description (JD).\n- Improve the language, metrics, and structure of a draft resume.\n- Prepare a paste-ready version of your CV for tools like FlowCV or Canva.\n\nTurns raw profile data into a polished, ATS-ready CV. Outputs a paste-ready plain-text\nversion formatted for FlowCV, Canva, Google Docs, or Word — with a flaw report and\nmissing-info checklist.\n\n---\n\n## FLAW REGISTER — KNOWN ISSUES FIXED IN THIS VERSION\n\nThe following issues were identified across the two prior skill drafts and are corrected here:\n\n| # | Flaw | Fix applied |\n|---|------|-------------|\n| F-01 | Output was Markdown-first, not paste-ready plain text | Final output is plain text; Markdown is internal staging only |\n| F-02 | FlowCV\u002FCanva field structure was never addressed | Section mapping to tool fields added (section 11c) |\n| F-03 | Questionnaire dumped all 20 questions at once in practice | Hard rule: one question at a time, wait for answer |\n| F-04 | Anti-hallucination rules listed but never enforced structurally | Enforcement gate added before every output (section 10) |\n| F-05 | Cover letter was offered but never scoped for these tools | Cover letter now outputs to a separate plain-text block, not inline |\n| F-06 | ATS check listed but had no scored output | Flaw report now scores 0–100 with per-item pass\u002Ffail |\n| F-07 | Seniority detection was \"detect or ask\" with no fallback | Default is mid-level if undetectable; user is told the assumption |\n| F-08 | No guidance on what FlowCV\u002FCanva cannot render | Added explicit field-by-field paste map (section 11c) |\n| F-09 | Tense rules stated but never verified in quality gate | Tense check is now a hard gate — output blocked until corrected |\n| F-10 | \"Passionate about\" and similar banned phrases still appeared in examples | Phrase blocklist now machine-checkable (section 7c) |\n| F-11 | Nepal\u002FSouth Asia market conventions were present but incomplete | Confirmed and expanded (section 14) |\n| F-12 | No explicit rule on what to do when LinkedIn scraping is blocked | Hard fallback rule: ask for PDF export immediately, do not proceed empty |\n| F-13 | File naming convention mentioned once, never enforced | File name rule is part of the final output block (section 11) |\n| F-14 | Skill had no version history or upgrade path | Version field added to frontmatter |\n| F-15 | GitHub was listed as a source but extraction rules were missing | GitHub extraction rules added (section 4f) |\n\n---\n\n## 1. Invocation\n\n```\nUse @cv-generator to build my CV from my LinkedIn PDF.\nUse @cv-generator to tailor my CV for this job description.\nUse @cv-generator to improve my existing draft.\nUse @cv-generator to create a fresh CV via questionnaire.\nUse @cv-generator — I want a FlowCV-ready output.\n```\n\nAny combination of sources is valid. Multiple sources are merged and deduplicated\nbefore writing begins.\n\n---\n\n## Source Selection\n\nAsk the user which source(s) to use. At least one is required.\nIf no source is provided, default immediately to the questionnaire (section 4d).\n\n| # | Source | Instruction |\n|---|--------|-------------|\n| 1 | LinkedIn profile URL | Fetch page; extract all visible sections. **If blocked or empty: immediately ask for a LinkedIn PDF — do not proceed on an empty extraction.** |\n| 2 | LinkedIn PDF export | Parse uploaded file. If scanned image: apply OCR and warn the user to verify accuracy. |\n| 3 | Portfolio \u002F personal website | Fetch URL; extract About, Projects, Skills, Services, Testimonials, Case Studies, Contact. |\n| 4 | Questionnaire | Step-by-step (section 4d). One question at a time. |\n| 5 | Existing CV or draft | Upload or paste; improve only — never alter facts. |\n| 6 | GitHub profile | Extract pinned repos, bio, tech stack, contribution summary (section 4f). |\n| 7 | Resume file (DOCX \u002F PDF \u002F TXT) | Parse and rewrite. Flag scanned PDFs; apply OCR. |\n\n---\n\n## Purpose, seniority, and format\n\n### Purpose\n\nAsk after source selection:\n\n> \"What is the main purpose of this CV?\"\n\n| Purpose | Key adaptation |\n|---------|----------------|\n| Applying for a specific job | Full JD analysis + keyword targeting (section 9) |\n| General professional CV | Balanced, role-agnostic, reverse-chronological |\n| Internship \u002F entry-level | Education and projects lead; transferable skills foregrounded |\n| Academic \u002F research | Publications, grants, teaching, research interests |\n| Freelance \u002F client proposal | Deliverables, outcomes, services |\n| Career change | Functional or hybrid; transferable skills reframed |\n| Executive \u002F board-level | Executive summary, board positions, P&L scope |\n| Military-to-civilian | Translate ranks and jargon to civilian equivalents |\n| Return to work \u002F career break | Frame gap positively; emphasise upskilling |\n| Other | Ask the user to describe the goal in one sentence |\n\n### Seniority\n\nDetect from data. If undetectable, **default to mid-level and tell the user:**\n> \"I've assumed mid-level (3–8 years). Let me know if this should be different.\"\n\n| Level | Years | CV emphasis |\n|-------|-------|-------------|\n| Student \u002F fresh graduate | 0–1 | Education first; projects; extracurriculars; 1 page |\n| Junior \u002F entry | 1–3 | Skills + education prominent; 1 page |\n| Mid-level | 3–8 | Experience leads; achievements over duties; 1–2 pages |\n| Senior | 8–15 | Leadership, scope, impact, mentoring; 2 pages |\n| Executive \u002F C-suite | 15+ | Strategic narrative; board roles; P&L; 2–3 pages |\n| Academic | Any | No page limit; publications; grants; teaching |\n\n### Format\n\n| Format | Use when |\n|--------|----------|\n| Chronological (default) | Clear career progression; most job applications |\n| Functional \u002F skills-first | Career changers; large gaps; military-to-civilian |\n| Hybrid \u002F combination | Senior professionals rebranding; career changers with strong experience |\n| Academic CV | University, research, PhDs, postdocs |\n| Executive \u002F Board bio | C-suite, NED, advisory |\n| Portfolio-led | Designers, architects, creatives |\n\n---\n\n## Data extraction rules\n\n### LinkedIn URL\n\nIf the page is blocked or returns no content, **stop immediately** and ask:\n> \"LinkedIn blocked the fetch. Please export your LinkedIn profile as a PDF\n> (LinkedIn → Me → Settings → Data Privacy → Get a copy of your data) and upload it.\"\n\nIf accessible, extract in order:\n1. Full name and headline\n2. Contact information (email, phone, location — public only)\n3. About \u002F Professional Summary\n4. Work experience: title, company, location, dates, bullets\n5. Education: degree, institution, dates, grade\u002Fhonours\n6. Skills (flag top endorsed skills)\n7. Certifications and licences\n8. Projects\n9. Achievements, honours, awards\n10. Volunteer experience\n11. Languages and proficiency\n12. Publications, patents, courses\n\n### LinkedIn PDF\n\nHard rules:\n- Extract only what is physically present in the document.\n- Preserve all dates exactly as written.\n- If a section is absent, mark it **[Not provided]** — do not skip silently.\n- Do not merge bullets across different roles.\n- If scanned: apply OCR and display this warning before continuing:\n  > \"OCR was used to read this document. Please review the extracted text below\n  > for accuracy before we continue.\"\n\n### Portfolio \u002F personal website\n\nExtract:\n- About \u002F bio → Professional Summary\n- Projects: name, description, technologies, outcomes, live\u002Frepo URLs\n- Skills and services\n- Testimonials or client logos → Achievements\n- Case studies → 2–4 bullets each\n- Blog posts or articles → Publications \u002F Thought Leadership\n- Contact details\n\n### Questionnaire\n\n**One question at a time. Wait for the answer before continuing.**\nDo not display the full list unless the user explicitly asks for a form.\n\n```\nQ1.  Full legal name (as it should appear on the CV)\nQ2.  Target job title or role\nQ3.  Email address\nQ4.  Phone number including country code (optional but recommended)\nQ5.  City and country of residence\nQ6.  LinkedIn URL (optional)\nQ7.  Portfolio, GitHub, or personal website URL (optional)\nQ8.  Professional summary — describe yourself in 2–3 sentences (will be rewritten)\nQ9.  Work experience — for EACH role:\n       - Job title\n       - Company name and industry\n       - Employment type (full-time \u002F part-time \u002F contract \u002F freelance \u002F internship)\n       - Location or Remote\n       - Start and end date (or \"Present\")\n       - 3–6 key responsibilities and achievements\n       - Any measurable results (numbers, %, revenue, team size, budget)\nQ10. Education — for EACH qualification:\n       - Degree or certificate name\n       - Institution name and country\n       - Start and graduation year\n       - Grade, GPA, or classification if notable\n       - Thesis or relevant modules (optional; for academic\u002Fentry-level only)\nQ11. Technical and professional skills\n       (ask to separate: Expert \u002F Proficient \u002F Familiar)\nQ12. Projects — for each:\n       - Name\n       - Purpose\n       - Your specific role\n       - Technologies or methods used\n       - Outcome or impact\nQ13. Certifications (name, issuing body, date, expiry if applicable)\nQ14. Achievements, awards, or recognitions\nQ15. Languages and proficiency: Native \u002F Fluent \u002F Professional \u002F Conversational \u002F Basic\nQ16. Volunteer or open-source work (optional)\nQ17. Publications, speaking engagements, press mentions (optional)\nQ18. Preferred CV format: chronological \u002F functional \u002F hybrid \u002F academic \u002F executive\nQ19. Target country or job market\nQ20. Any employment gaps? Dates and brief reason — will be framed constructively.\n```\n\n### Existing CV or draft\n\nRules:\n- Preserve every fact: titles, companies, dates, institutions, grades.\n- Rewrite weak or passive bullets with strong action verbs.\n- Remove repetition across roles.\n- Correct grammar, punctuation, spelling.\n- Fix tense: past for completed roles, present for current role.\n- Replace all banned phrases (section 7c).\n- Improve ATS keyword density where natural — do not keyword-stuff.\n- Restructure section order if it does not match target market or seniority.\n- **Do not add experience, qualifications, metrics, or skills not present in the original.**\n\n### GitHub profile\n\nExtract:\n- Bio \u002F tagline → supplement Professional Summary\n- Pinned repositories: name, description, tech stack, stars\u002Fforks\n- Contribution activity (years active, languages used)\n- README content for context on major projects\n- Do not infer seniority from commit count alone\n\n### Employment gaps and special situations\n\n**Gap under 3 months:** no special treatment.\n\n**Gap 3–12 months:** one-line entry:\n> \"Career break — [brief honest reason: personal development \u002F caregiving \u002F travel \u002F health]\"\n\n**Gap over 12 months:** add a neutral framing entry in the experience section;\nhighlight any upskilling, freelance, volunteering, or relevant activity during the gap.\nNever fabricate activity.\n\n**Contract \u002F freelance \u002F part-time:** label employment type clearly. Group multiple\nshort contracts under one umbrella entry (e.g. \"Freelance Consultant\") if they share\na skill area.\n\n**Concurrent roles:** list both with accurate overlapping dates; add \"(concurrent with\n[other role])\" if helpful.\n\n**Early or irrelevant roles (> 10 years):** condense to one line for senior professionals\nunless directly relevant to the target role.\n\n**Fresh graduate:** lead with Education → Projects → Skills → Internships.\nUse academic projects as proof of practical skills.\n\n**Military-to-civilian:** translate all ranks and jargon to civilian equivalents;\nquantify command scope (e.g. \"Managed 35 personnel and $2M in equipment\").\n\n**Non-English source:** translate accurately; preserve institution and company names\nin the original language with an English translation in parentheses on first use;\nadvise the user to have the translation reviewed by a native speaker.\n\n---\n\n## Multi-source merging\n\n1. Build a master profile combining all extracted data.\n2. Deduplicate: keep the most detailed version of each entry.\n3. If two sources conflict on a date or title, flag it and ask the user to confirm.\n4. Identify gaps; ask follow-up questions only for critical missing data.\n5. Never fabricate a detail — mark it **[Not provided]** until the user confirms.\n\n---\n\n## CV section order\n\n### Chronological (default — mid \u002F senior)\n```\n1.  Full Name\n2.  Contact Information (email | phone | LinkedIn | portfolio | city, country)\n3.  Professional Summary\n4.  Core Skills\n5.  Work Experience (reverse chronological)\n6.  Education (reverse chronological)\n7.  Certifications and Licences\n8.  Projects\n9.  Technical Skills (grouped: Languages | Frameworks | Tools | Platforms)\n10. Achievements and Awards\n11. Volunteer Experience\n12. Publications \u002F Speaking\n13. Languages\n14. Additional Information\n```\n\n### Fresh graduate \u002F student\n```\n1.  Full Name + Contact Information\n2.  Professional Summary \u002F Objective\n3.  Education\n4.  Projects and Coursework\n5.  Skills\n6.  Work Experience \u002F Internships\n7.  Certifications\n8.  Extracurricular \u002F Volunteer\n9.  Languages\n```\n\n### Functional \u002F skills-first (career changers, large gaps)\n```\n1.  Full Name + Contact Information\n2.  Professional Summary\n3.  Core Competencies \u002F Skills\n4.  Key Achievements\n5.  Work History (company, title, dates — minimal bullets)\n6.  Education\n7.  Certifications\n8.  Languages\n```\n\n### Academic CV\n```\n1.  Full Name + Contact + ORCID \u002F ResearchGate\n2.  Research Interests\n3.  Education\n4.  Academic Positions\n5.  Publications\n6.  Grants and Funding\n7.  Teaching Experience\n8.  Supervision\n9.  Awards and Honours\n10. Conference Presentations\n11. Professional Memberships\n12. Skills\n13. References\n```\n\n### Executive \u002F Board\n```\n1.  Full Name + Contact Information\n2.  Executive Summary\n3.  Core Competencies\n4.  Board and Advisory Roles\n5.  Executive Experience\n6.  Education and Qualifications\n7.  Publications \u002F Media \u002F Speaking\n8.  Professional Memberships\n```\n\n---\n\n## Writing rules\n\n### Professional Summary\n\nWrite 3–5 sentences (executive: 5–7) covering:\n1. Who the person is: job title + years of experience\n2. Primary domain of expertise\n3. One concrete differentiator or standout achievement\n4. Value proposition aligned to the target role\n\n- Do not open with \"I am\".\n- Do not open with any banned phrase (section 7c).\n- Base strictly on data collected — no padding.\n\nGood example:\n> \"Software engineer with seven years building distributed systems at scale.\n> Deep expertise in Go and Kubernetes, with a track record of cutting infrastructure\n> costs 30–40% through cloud-native redesigns. Seeking a staff-level role where\n> systems reliability and platform engineering intersect.\"\n\n### Experience bullets — STAR-lite\n\nPattern: `[Strong verb] + [what you did] + [scale\u002Fscope] + [outcome if available]`\n\nRules:\n- 3–6 bullets per role (2–3 for short-tenure or early roles)\n- Past tense for completed roles; present tense for current role\n- 15–30 words per bullet\n- Different verb to open each bullet — never repeat within one role\n- If no metric was provided: write a result-focused statement without inventing numbers\n- Never fabricate metrics — if the user says \"we grew a lot\", ask for specifics\n\nAction verb bank:\n\n```\nLeadership:    Led, Directed, Managed, Supervised, Mentored, Coached, Championed\nBuilding:      Built, Developed, Engineered, Architected, Designed, Implemented, Launched, Shipped\nImprovement:   Reduced, Improved, Optimised, Streamlined, Accelerated, Automated, Consolidated\nAnalysis:      Analysed, Researched, Evaluated, Identified, Diagnosed, Assessed, Mapped\nCommunication: Presented, Authored, Documented, Trained, Negotiated, Advised, Collaborated\nGrowth:        Grew, Expanded, Scaled, Generated, Increased, Secured, Delivered\nStrategy:      Defined, Established, Prioritised, Planned, Coordinated, Oversaw, Aligned\n```\n\nRewrites:\n```\nBEFORE: \"Responsible for managing the team\"\nAFTER:  \"Managed a cross-functional team of 8 engineers, delivering the product roadmap\n         on schedule for three consecutive quarters\"\n\nBEFORE: \"Helped with developing new features\"\nAFTER:  \"Developed four customer-facing features in React, reducing support tickets by 25%\"\n\nBEFORE: \"Was involved in the migration project\"\nAFTER:  \"Led migration from monolith to microservices, cutting deployment time from\n         45 minutes to under 4 minutes\"\n```\n\n### Banned phrases — machine-checkable blocklist\n\nBefore output, scan the full CV text and **reject any bullet or sentence containing**\nany of the following strings (case-insensitive):\n\n```\nresults-driven\ndynamic individual\nhighly motivated\nteam player\nproven track record\npassionate about\npassionate professional\ndetail-oriented\nself-starter\nhard worker\nstrong communication skills\nexcellent communication\nsynergy\nleverage (when used as a verb meaning \"use\")\nparadigm shift\nthought leader\ngo-getter\ninnovative thinker\noutside the box\npeople person\nvisionary\nchange agent\n```\n\nIf found: rewrite the sentence to show the specific evidence instead.\n\n### Tense enforcement\n\nThis is a hard gate — output is blocked until tense is correct:\n\n- **Completed role** → all bullets in past tense (Led, Built, Reduced...)\n- **Current role** → all bullets in present tense (Lead, Build, Reduce...)\n- **Mixed tense within one role** → always fail; fix before output\n\n### Acronym and terminology\n\n- Spell out on first use: \"Machine Learning (ML)\"; use abbreviation thereafter.\n- Consistent capitalisation throughout: \"JavaScript\" not \"Javascript\".\n- Mirror exact JD phrasing where applicable.\n- Include both full form and abbreviation for searchability.\n\n---\n\n## ATS optimisation\n\n### Structural rules\n\n| Rule | Why it matters |\n|------|----------------|\n| Name must be the very first line of the body | Parsers read top-to-bottom; name in header\u002Ffooter is often missed |\n| Contact info in body, not in header or footer | Header\u002Ffooter text is invisible to Taleo, Workday, iCIMS |\n| Single-column layout only | Two-column layouts break ATS text extraction order |\n| No tables for layout | Table cells are read in unpredictable order |\n| No text boxes, shapes, or SmartArt | Text inside shapes is invisible to ATS |\n| No images or photos (unless market requires it) | Images are ignored; photos risk bias filtering |\n| No icons in bullets or headings | Symbols like ➤ ✓ ★ corrupt parsed text |\n| Bullet characters: hyphen (-) or plain dot (•) only | Safe across all ATS platforms |\n| Standard section headings only | Non-standard headings cause misclassification |\n| No \"Objective\" heading | Flags CV as outdated; use \"Professional Summary\" |\n| Font: minimum 10pt body, 12–14pt headings | Smaller text garbles in PDF-to-text conversion |\n| Margins: minimum 0.5 in \u002F 1.27 cm all sides | Narrow margins cause line-wrapping errors |\n| Spell out all URLs fully | Anchor text loses URL when ATS strips formatting |\n| File format: .docx preferred for ATS; PDF for email | DOCX parses more accurately in most ATS |\n| File name: FirstName_LastName_CV.docx | Generic names (\"resume.pdf\") get buried in recruiter files |\n\n### Keyword strategy\n\n1. Extract top 10–20 keywords from the JD (if provided).\n2. Categorise: hard skills | soft skills | qualifications | industry terms.\n3. For each keyword, record:\n   - Present and prominent\n   - Present but weak or buried → strengthen placement\n   - Absent but user has the skill → weave in naturally\n   - Absent and user lacks the skill → do not add\n4. Target keyword density: 2–4 natural occurrences per hard skill across the full CV.\n5. Include both spelled-out form and abbreviation for key terms.\n6. Mirror exact JD phrasing for shared responsibilities.\n\n### ATS platform quick notes\n\n| Platform | Key quirk |\n|----------|-----------|\n| Workday | DOCX preferred; complex PDF tables fail |\n| Taleo | Strictest; no special characters; plain text preferred |\n| Greenhouse | Lenient; weights keyword frequency |\n| Lever | Modern parser; handles most formats |\n| iCIMS | DOCX preferred; strips header\u002Ffooter text |\n| SmartRecruiters | Handles DOCX and PDF; relatively lenient |\n\nDefault when platform is unknown: apply Taleo-level strictness.\n\n---\n\n## Job description integration\n\nWhen a JD is provided, run four steps:\n\n**Step 1 — Parse:**\n- Job title and seniority signals\n- Required vs preferred qualifications\n- Hard skills: tools, languages, platforms, methodologies\n- Soft skills and collaboration patterns\n- Industry terminology\n- Responsibility verb phrases (mirror these in bullets)\n\n**Step 2 — Score:**\nFor each of the top 15 keywords, mark: present and prominent \u002F present but weak \u002F\nabsent.\n\n**Step 3 — Integrate:**\n- Strengthen weak keyword placements.\n- Weave in missing keywords the user genuinely has experience with.\n- Never add a keyword the user cannot truthfully claim.\n\n**Step 4 — Report (include at end of output):**\n```\nJD KEYWORD MATCH REPORT\nTotal JD keywords identified: 18\nMatched in CV: 14 (78%)\nAdded naturally during generation: 3\nNot added (user lacks skill): 1 — Salesforce\nRecommendation: even limited Salesforce exposure is worth noting if any exists\n```\n\n---\n\n## Anti-hallucination enforcement gate\n\nBefore any output is produced, confirm every item in the CV passes this check.\n**Output is blocked until all items pass.**\n\n| Item | Rule |\n|------|------|\n| Job titles | Sourced directly from user data — not inferred or upgraded |\n| Company names | Sourced directly — not corrected, normalised, or embellished |\n| Dates | Reproduced exactly as provided — no normalisation without noting it |\n| Degrees and institutions | Reproduced exactly as provided |\n| Certifications | Only those explicitly named by the user |\n| Metrics and numbers | Only those provided by the user — never approximated or invented |\n| Awards and achievements | Only those named by the user |\n| Skills and tools | Only those provided or clearly evidenced in source data |\n| Projects | Only those named by the user |\n\nIf any item cannot be verified: mark it **[Not provided]** and include it in the\nmissing information checklist (section 11d). Never fill gaps silently.\n\n---\n\n## Final output — deliver in this exact order\n\n### Formatted CV (staging draft)\n\nClean plain-text draft with clear section labels. Used as the working version\nbefore generating the tool-specific paste copies below.\n\n### FlowCV paste-ready version\n\nFlowCV uses structured text fields, not free-form documents. Format accordingly:\n\n```\nFULL NAME\n[First name] [Last name]\n\nPROFESSIONAL TITLE\n[Target job title]\n\nCONTACT\nEmail: [email]\nPhone: [+country code number]\nLocation: [City, Country]\nLinkedIn: [full URL]\nPortfolio: [full URL if applicable]\n\nPROFESSIONAL SUMMARY\n[3–5 sentence plain paragraph — no bullets, no Markdown]\n\nCORE SKILLS\n[skill], [skill], [skill], [skill]\n[skill], [skill], [skill], [skill]\n\nWORK EXPERIENCE\n\n[Job Title]\n[Company Name] | [City, Country] | [Mon YYYY] – [Mon YYYY or Present]\n[Employment type if not full-time: Contract \u002F Freelance \u002F Part-time]\n- [Bullet one: action verb + context + outcome]\n- [Bullet two]\n- [Bullet three]\n\n[Repeat for each role]\n\nEDUCATION\n\n[Degree Name]\n[Institution Name], [Country] | [YYYY] – [YYYY]\n[Grade or classification if notable]\n\n[Repeat for each qualification]\n\nCERTIFICATIONS\n[Certificate Name] — [Issuing Body] — [Month YYYY]\n\nPROJECTS\n\n[Project Name]\n[Technologies: tool, tool, tool]\n- [What it does \u002F your role \u002F outcome]\n\nACHIEVEMENTS\n- [Achievement one]\n- [Achievement two]\n\nVOLUNTEER EXPERIENCE\n[Role] — [Organisation] — [YYYY–YYYY]\n- [One-line description]\n\nLANGUAGES\n[Language]: [Native \u002F Fluent \u002F Professional \u002F Conversational \u002F Basic]\n\nADDITIONAL INFORMATION\n[Anything else: open-source, interests relevant to role]\n```\n\n### Canva paste-ready version\n\nCanva CV templates use individual text boxes per section. Provide each section as\na separate clearly labelled block, with no Markdown symbols.\n\n```\n--- PASTE INTO: Name field ---\n[Full name]\n\n--- PASTE INTO: Job title \u002F headline field ---\n[Target job title]\n\n--- PASTE INTO: Contact block ---\n[email] | [phone] | [city, country] | [LinkedIn URL]\n\n--- PASTE INTO: Summary \u002F About field ---\n[3–5 sentence paragraph, plain text, no hyphens or bullets]\n\n--- PASTE INTO: Skills field ---\n[skill] | [skill] | [skill] | [skill] | [skill]\n\n--- PASTE INTO: Experience entry 1 ---\n[Job Title]\n[Company] | [Location] | [Mon YYYY – Mon YYYY]\n- [Bullet]\n- [Bullet]\n- [Bullet]\n\n[Continue for each role as a separate block]\n\n--- PASTE INTO: Education entry 1 ---\n[Degree]\n[Institution], [Country] | [YYYY – YYYY]\n[Grade if notable]\n\n--- PASTE INTO: Certifications ---\n[Certificate] | [Issuer] | [YYYY]\n\n--- PASTE INTO: Languages ---\n[Language] ([Proficiency])\n```\n\n### Missing information checklist\n\n```\nMISSING INFORMATION\n[ ] Phone number\n[ ] LinkedIn URL\n[ ] Portfolio or GitHub URL\n[ ] Measurable results for [Role] at [Company]\n[ ] Certifications — do you hold any?\n[ ] Languages — list any beyond English\n[ ] Employment gap [Mon YYYY – Mon YYYY] — add a brief framing note\n[ ] [Any other flagged item]\n```\n\n### CV flaw report (scored 0–100)\n\nRun all checks. Display a scored report:\n\n```\nCV FLAW REPORT\n──────────────────────────────────────\nScore: [X]\u002F100\n\nPASS  Truthfulness — all facts sourced from user data\nPASS  No hallucination — no fabricated details\nPASS  Tense correctness — past for completed, present for current\nPASS  ATS structure — single column, no tables or images\nPASS  Standard headings — all recognisable by parsers\nPASS  No forbidden characters — no ➤ ✓ ★\nPASS  Humanized — no banned phrases found\nPASS  Contact info in body (not header\u002Ffooter)\nFAIL  [Check name] — [specific issue and location in CV]\n──────────────────────────────────────\nDeductions: -[N] per FAIL item\nFinal score: [X]\u002F100\n\nISSUES TO FIX:\n1. [Exact location] — [Exact problem] — [Suggested fix]\n2. [Exact location] — [Exact problem] — [Suggested fix]\n```\n\nScore deductions: -10 per FAIL on truthfulness or hallucination;\n-5 per FAIL on tense, ATS structure, or banned phrases;\n-3 per FAIL on formatting issues.\n\n### Improvement suggestions (3–7, specific and actionable)\n\n- \"Your summary does not state the target role. Open with your job title explicitly.\"\n- \"The [Company] role has no metrics. Even approximate scope (team size, users, budget range) strengthens credibility.\"\n- \"Skills section mixes expert and basic tools without distinction. Group into Proficient \u002F Familiar.\"\n- \"Add a GitHub or portfolio URL — technical recruiters check it before the interview.\"\n- \"Three bullets begin with 'Responsible for' — replace with direct action verbs.\"\n- \"CV is [N] pages for [N] years of experience. Target is [N] pages; trim older roles to one line.\"\n\n### Suggested file name\n\n```\nSuggested filename: [FirstName]_[LastName]_CV.docx\n```\n\n---\n\n## Cover letter companion (optional)\n\nAfter the CV output, offer:\n\n> \"Would you like a tailored cover letter for this application?\"\n\nIf yes, output as a **separate clearly labelled plain-text block** — not inline with the CV.\n\nRules:\n- Opens with a specific hook — not \"I am writing to apply for…\"\n- References company and role by name\n- Bridges 2–3 strongest CV points to the JD's key requirements\n- Closes with a clear call to action\n- Matches tone of the target industry\n- 3 paragraphs maximum, 250–350 words\n- Does not repeat the CV verbatim\n\n---\n\n## Limitations\n\n- **No hallucination.** Never invent a title, company, date, degree, cert, skill, metric, or award.\n- **No fake metrics.** If the user says \"we grew a lot\", ask for specifics — never insert a percentage.\n- **Respect source truth.** \"Junior Developer\" stays \"Junior Developer\" — suggest a reframe if needed; never silently change it.\n- **No silent changes.** If something is materially reworded, note the change.\n- **One version at a time.** Complete the CV before offering variants.\n- **Privacy.** Do not expose full home address, national ID, DOB, marital status, or religion unless the user's target market requires it.\n- **No keyword stuffing.** Adding skills the user does not have is fraud. Flag gaps; never fabricate.\n- **OCR warning.** Always display before continuing: \"OCR was used — please verify the extracted text for accuracy.\"\n\n---\n\n## Country and market conventions\n\n| Market | Length | Photo | DOB | Marital status | References |\n|--------|--------|-------|-----|----------------|------------|\n| USA | 1–2 pages | No | No | No | \"Available on request\" |\n| Canada | 1–2 pages | No | No | No | \"Available on request\" |\n| UK | 2 pages | No | No | No | \"Available on request\" |\n| Ireland | 2 pages | No | No | No | \"Available on request\" |\n| Australia \u002F NZ | 2–3 pages | No | No | No | \"Available on request\" |\n| Germany \u002F Austria \u002F Switzerland | 2–3 pages | Yes (expected) | Yes | Sometimes | Listed or on request |\n| France | 1–2 pages | Optional | No (illegal to require) | No | On request |\n| Netherlands \u002F Scandinavia | 1–2 pages | Optional | No | No | On request |\n| Japan | 1–2 pages (rirekisho) | Yes | Yes | Yes | Listed |\n| South Korea | 1–2 pages | Yes | Yes | Yes | Listed |\n| China | 1–2 pages | Yes | Yes | Yes | Listed |\n| India | 2–3 pages | Optional | Yes (common) | Sometimes | Listed |\n| Nepal | 2–3 pages | Yes (common) | Yes | Sometimes | Listed |\n| Bangladesh \u002F Sri Lanka | 2–3 pages | Yes (common) | Yes | Sometimes | Listed |\n| UAE \u002F Gulf (GCC) | 2–3 pages | Yes (common) | Yes | Yes (sometimes) | Listed |\n| Nigeria \u002F East Africa | 2–3 pages | Yes (common) | Yes | Sometimes | Listed |\n| South Africa | 3–5 pages | Optional | Yes (common) | No | Listed |\n| Brazil | 1–2 pages | Optional | Yes (common) | No | On request |\n| Academic (global) | No limit | Varies | Varies | No | Full list required |\n| Executive \u002F board (global) | 2–3 pages | No | No | No | On request |\n\nDefault when market is unknown: UK \u002F international conventions (no photo, no DOB, 2 pages,\n\"Available on request\").\n\n---\n\n## Decision tree\n\n```\nUser invokes @cv-generator\n        |\n        v\nSource provided? --No--> Run questionnaire (Q1–Q20, one at a time)\n        |Yes\n        v\nLinkedIn URL blocked? --Yes--> Ask for PDF export immediately; do not proceed empty\n        |No\n        v\nCollect all sources --> merge and deduplicate (section 5)\n        |\n        v\nAsk: Purpose? --> Detect or assume seniority (default: mid-level; tell the user)\n        |\n        v\nSelect format (section 3c)\n        |\n        v\nSelect section order (section 6)\n        |\n        v\nJD provided? --Yes--> Parse JD --> extract and score keywords (section 9)\n        |No                  |\n        v                    v\nWrite CV content       Integrate keywords naturally\n(sections 7–8)               |\n        |\u003C-------------------+\n        v\nRun anti-hallucination gate (section 10) --> block output until all pass\n        |\n        v\nRun tense enforcement (section 7d) --> block output until all pass\n        |\n        v\nRun banned phrase scan (section 7c) --> fix any found\n        |\n        v\nOutput in order:\n  Formatted CV (staging draft)\n  FlowCV paste-ready version\n  Canva paste-ready version\n  Missing information checklist\n  CV flaw report (scored)\n  Improve suggestions\n  Suggested file name\n        |\n        v\nOffer cover letter (section 12)\n```\n",{"name":5,"risk":24,"tags":25,"author":32,"source":33,"category":34,"date_added":35,"description":7,"user-invokable":36},"safe",[26,27,28,29,30,31],"cv","resume","ats","career","job-application","career-change","WHOISABHISHEKADHIKARI","community","content","2026-06-06",true,"master","877653a671c51fae6476bd9f0d34ee6c408d68b9",".github\u002Fskills\u002Fcv-generator","https:\u002F\u002Fgithub.com\u002Fprincepatel04477-web\u002Ftrivoxa-group","https:\u002F\u002Ftrivoxa-group.vercel.app","https:\u002F\u002Fgithub.com\u002Fprincepatel04477-web","2026-08-01 17:29:31",{"source":8,"skillName":5,"commands":45,"prompt":55,"zipAvailable":36},[46,49,52],{"tool":47,"command":48},"npx","npx skills add princepatel04477-web\u002Ftrivoxa-group --skill cv-generator",{"tool":50,"command":51},"bunx","bunx skills add princepatel04477-web\u002Ftrivoxa-group --skill cv-generator",{"tool":53,"command":54},"pnpm","pnpm dlx skills add princepatel04477-web\u002Ftrivoxa-group --skill cv-generator","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fprincepatel04477-web\u002Ftrivoxa-group\u002Fblob\u002Fmaster\u002F.github\u002Fskills\u002Fcv-generator\u002FSKILL.md",[],[58,65,72,79,86,93],{"skillNo":59,"name":60,"nameZh":6,"description":61,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":62,"categories":63,"keywords":64,"publishedAt":19},"01M78G4Z5RFJ72G536XYPC77PG","zustand-store-ts","Create Zustand stores following established patterns with proper TypeScript types and middleware.","https:\u002F\u002Fgithub.com\u002Fprincepatel04477-web\u002Ftrivoxa-group\u002Fblob\u002Fmaster\u002F.github\u002Fskills\u002Fzustand-store-ts\u002FSKILL.md",[],[],{"skillNo":66,"name":67,"nameZh":6,"description":68,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":69,"categories":70,"keywords":71,"publishedAt":19},"01M78G4WQMHRST36KDP7AV3NR3","zoom-automation","Automate Zoom meeting creation, management, recordings, webinars, and participant tracking via Rube MCP (Composio). Always search tools first for current schemas.","https:\u002F\u002Fgithub.com\u002Fprincepatel04477-web\u002Ftrivoxa-group\u002Fblob\u002Fmaster\u002F.github\u002Fskills\u002Fzoom-automation\u002FSKILL.md",[],[],{"skillNo":73,"name":74,"nameZh":6,"description":75,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":76,"categories":77,"keywords":78,"publishedAt":19},"01M78G4T37F4SPS7M4KT0A8JJB","zoho-crm-automation","Automate Zoho CRM tasks via Rube MCP (Composio): create\u002Fupdate records, search contacts, manage leads, and convert leads. Always search tools first for current schemas.","https:\u002F\u002Fgithub.com\u002Fprincepatel04477-web\u002Ftrivoxa-group\u002Fblob\u002Fmaster\u002F.github\u002Fskills\u002Fzoho-crm-automation\u002FSKILL.md",[],[],{"skillNo":80,"name":81,"nameZh":6,"description":82,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":83,"categories":84,"keywords":85,"publishedAt":19},"01M78G4QAJMF71KD1G38MNDQYK","zod-validation-expert","Expert in Zod — TypeScript-first schema validation. Covers parsing, custom errors, refinements, type inference, and integration with React Hook Form, Next.js, and tRPC.","https:\u002F\u002Fgithub.com\u002Fprincepatel04477-web\u002Ftrivoxa-group\u002Fblob\u002Fmaster\u002F.github\u002Fskills\u002Fzod-validation-expert\u002FSKILL.md",[],[],{"skillNo":87,"name":88,"nameZh":6,"description":89,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":90,"categories":91,"keywords":92,"publishedAt":19},"01M78G4MS3WE96MH5P561KFY95","zipai-optimizer","Adaptive token optimizer: intelligent filtering, surgical output, ambiguity-first, context-window-aware, VCS-aware, MCP-aware.","https:\u002F\u002Fgithub.com\u002Fprincepatel04477-web\u002Ftrivoxa-group\u002Fblob\u002Fmaster\u002F.github\u002Fskills\u002Fzipai-optimizer\u002FSKILL.md",[],[],{"skillNo":94,"name":95,"nameZh":6,"description":96,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":97,"categories":98,"keywords":99,"publishedAt":19},"01M78G4GZ0T47C6929V9CVH1AK","zeroize-audit","Detects missing zeroization of sensitive data in source code and identifies zeroization removed by compiler optimizations, with assembly-level analysis, and control-flow verification. Use for auditing C\u002FC++\u002FRust code handling secrets, keys, passwords, or other sensitive data.","https:\u002F\u002Fgithub.com\u002Fprincepatel04477-web\u002Ftrivoxa-group\u002Fblob\u002Fmaster\u002F.github\u002Fskills\u002Fzeroize-audit\u002FSKILL.md",[],[]]