[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7AYE699MXNGF4GS587AC5KM":3,"skill-same:01M7AYE699MXNGF4GS587AC5KM":80},{"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":31,"commitSha":32,"skillDirectory":33,"forksCount":34,"repositoryHtmlUrl":35,"repositoryHomepageUrl":6,"ownerHtmlUrl":36,"ownerBlogUrl":37,"ownerDescription":38,"updatedAt":39,"install":40,"resources":53},"01M7AYE699MXNGF4GS587AC5KM","career-coaching",null,"Review resumes, LinkedIn profiles, and job applications.","oat431\u002Fhermes_config_backup","oat431","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F54722120?v=4","01M7AYD07EH8SYPMYY8CGZKS22","Oralita","01M7AYD0816QDF77E3TWCRSQC9",1,"Unlicense","https:\u002F\u002Fgithub.com\u002Foat431\u002Fhermes_config_backup\u002Fblob\u002Fmain\u002Fworkflow\u002Fcareer-coach\u002Fcareer-coaching\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: career-coaching\ndescription: Review resumes, LinkedIn profiles, and job applications.\ntags: [career, resume, linkedin, interview, star, job-search]\n---\n\n# Career Coaching Workflow\n\nComprehensive workflow for job seekers: resume review → LinkedIn audit → master profile → STAR stories → tailored applications.\n\n## When to Use\n\n- User asks for resume\u002FCV review or rewrite\n- User asks for LinkedIn profile audit or optimization\n- User wants to build a \"master profile\" for job applications\n- User needs STAR stories extracted for behavioral interviews\n- User is preparing cover letters or job applications\n\n## The Master Profile Pattern\n\nBuild ONE master profile (Obsidian note) that serves as the single source of truth for all job artifacts. Structure:\n\n### 8-Block Master Profile Framework\n\n1. **Core Identity** — Name, contact, location, languages, LinkedIn URL\n2. **Professional Narrative** — 50-word story: who you are, where you've been, where you're going\n3. **Experience Database** — Each job with: company, dates, role, metrics, tech stack, achievements\n4. **Education & Credentials** — Degree, GPA, honors, certifications, test scores, TA experience\n5. **Skills Inventory** — Categorized by proficiency (Expert\u002FProficient\u002FFamiliar)\n6. **Projects Portfolio** — Curated list with descriptions, tech, impact, links\n7. **STAR Stories** — 8-12 reusable stories covering leadership, conflict, failure, ambiguity, influence, judgment\n8. **Job Search Parameters** — Target roles, industries, salary range, location preferences, deal-breakers\n\n### Artifact Generation Order\n\n1. Master profile (source of truth)\n2. Resume (ATS-optimized, quantified)\n3. LinkedIn (keyword-rich, discoverable)\n4. Cover letter template (tailored per application)\n5. STAR story portfolio (extracted via `\u002Fgrill-me`)\n\n## Resume Review Checklist\n\nSee `references\u002Fresume-review-checklist.md` for the full scoring rubric.\n\n**Critical checks:**\n- ATS compatibility (single-column, standard headings, no tables\u002Fgraphics in headers)\n- Quantification (every bullet has metrics: %, time, users, revenue)\n- Action verbs (Led, Built, Migrated, Reduced — not \"Responsible for\")\n- Professional summary (50 words, keyword-rich, achievement-focused)\n- Skills section (categorized, specific technologies, not vague categories)\n- Contact info (includes LinkedIn URL, language proficiency for Thai market)\n\n## LinkedIn Audit Checklist\n\nSee `references\u002Flinkedin-audit-checklist.md` for the full audit framework.\n\n**Critical checks:**\n- Headline (keyword-rich, 220 chars max, includes role + top 4 tech + architecture keywords)\n- About section (first 3 lines are critical — show before \"see more\" click)\n- Experience detail (same quantification as resume, but expanded)\n- Language levels (Thai = Native\u002Fbilingual, English = Professional working for B2+)\n- Open to Work (enabled — ASK the user which visibility they use: public green frame vs Recruiters-only. The headline must match: with a public frame, drop redundant \"Open to New Opportunities\" phrasing and spend those characters on keywords; with Recruiters-only, keep availability text in the headline but never the green frame)\n- Projects (curate to 2-4 strong projects, remove trivial learning exercises)\n- Certifications (relevant to target roles)\n\n## STAR Story Extraction\n\nUse `\u002Fgrill-me` skill to extract stories. Run 3 sessions minimum:\n\n**Session 1: Technical Leadership**\n- Biggest technical project or migration\n- Focus: problem-solving, technical judgment, impact\n\n**Session 2: People\u002FInfluence**\n- Mentoring, teaching, or leading without authority\n- Focus: communication, influence, team dynamics\n\n**Session 3: Initiative\u002FOwnership**\n- Stepping up in ambiguity, taking ownership\n- Focus: decision-making, accountability, learning from failure\n\nEach session produces one polished STAR story. Add to Block 7 of master profile.\n\n## Personality & Values Assessment Coaching\n\nWhen the user takes, brings, or asks about personality\u002Fvalues tests — their own or employer-mandated:\n\n- **Recommendation tier list:** IPIP Big Five (OCEAN) = the only tier worth trusting for self-insight; Moral Foundations = values layer, recommend as the follow-up after OCEAN; MBTI \u002F DISC \u002F political-compass family = entertainment tier — vocabulary, never verdicts.\n- **Hard privacy rule:** assessment results never enter resume, LinkedIn, cover letters, or interview answers. Values data stays private entirely (Thai market conservatism makes signaling costly).\n- **Interpret from behavioral evidence, not percentiles:** cross-check each trait against the master profile; when behavior contradicts a score, state which reading to trust and why. Full protocol + vault layout: `references\u002Fassessment-interpretation.md`.\n- **High-stability narrators need injected stakes:** very high emotional stability produces failure\u002Fpressure STAR stories with zero emotional texture, which interviewers read as evasive; coach one honest stakes sentence (what was at risk, what was felt) before the Action section.\n- **Every spike trait gets a shadow row:** shadow + countermeasure in the analysis AND in the improvement tracker (e.g., stability spike → silent overload → weekly external load gauge).\n- **Verify test-site URLs live before recommending** (`curl -s -o \u002Fdev\u002Fnull -w \"%{http_code}\" \u003Curl>`): assessment hosts and mirror paths rot without notice; never hand the user an unverified link.\n- **Company-mandated tests:** coach answer-honestly-but-consistently (these instruments carry lie scales; faking badly scores worse than ordinary), treat the hiring *process* as the culture signal rather than the test result, and give the flip question to ask in interviews: \"how does the team actually use these results?\"\n\n## Improvement TODO Tracker\n\nMaintain one living tracker at the career-folder root (`00-Improvement-TODO.md`) — career-level facts about the user, per the vault rule in `career-artifact-prep`:\n\n- Horizon bands: 🔴 Now (dated window) \u002F 🟡 current-role window (probation, first months) \u002F 🟢 long-horizon \u002F ✅ Done.\n- **Done = artifact or evidence link, never intention.** Every open item wikilinks to the real vault artifact it will modify (STAR file, study base, relocation plan, assessment summary); no dangling TODOs.\n- Standing **hygiene item**: diff the master profile against reality each review (story counts, stale \"to be developed\" markers, last-updated dates) — the profile drifts after every prep session.\n- Cadence: weekly review (doubles as the load gauge) + monthly deep review; scheduled retests go in 🟢 with a target month.\n\n## Thai Market Specifics\n\nSee `references\u002Fthai-market.md` for salary ranges, job platforms, and conventions.\n\n**Quick reference:**\n- Mid-level SWE Bangkok: 40,000–70,000 THB\u002Fmonth\n- Remote\u002Finternational: 60,000–100,000+ THB\u002Fmonth\n- Key platforms: JobsDB Thailand, LinkedIn, Blognone\n- Always include language proficiency (Thai + English)\n- Indicate relocation willingness if applying to Bangkok from provinces\n\n## Fact Verification Pass (mandatory on EVERY review)\n\nAgent drafts accumulate fabrication over time — details carried from earlier drafts, wrong guesses, and plausible-sounding specifics survive rewrites. Run this pass before approving any artifact:\n\n1. **Primary-source check** — re-read the user's own resume PDF \u002F official documents; never trust details carried from earlier drafts. (Real cases that had to be removed: an NSTDA job entry, a KMUTNB degree\u002Faward for a CMU graduate, a Node upgrade attributed to an intern instead of the user.)\n2. **Official-name check** — web-search official names of tests, certifications, institutions before writing them. (Real case: CMU's English exit test is officially **CMU-eGrad** per reg.cmu.ac.th — guessed acronyms like \"CMU TEP\u002FTEGS\" were wrong twice in a row.)\n3. **URL check** — HTTP-check every GitHub\u002Fportfolio URL in the artifact (`curl -s -o \u002Fdev\u002Fnull -w \"%{http_code}\" \u003Curl>`); 404 = remove the link or mark \"none yet\". A 404 under a personal account does NOT prove the repo doesn't exist — university\u002Fteam projects often live under a GitHub **organization** account. Before deleting a link, probe `https:\u002F\u002Fapi.github.com\u002Forgs\u002F\u003COrg>\u002Frepos` or ask the user where the repo lives. (Real case: Transmatter lived under github.com\u002FTransmatter org; it was nearly cut because probes only hit personal accounts.)\n4. **Cross-file contradiction scan** — after ANY fact correction, grep ALL artifact files (resume, LinkedIn, master profile, STAR stories) for the old value and fix every occurrence, including memory. Verify clean with a final grep.\n5. **Same-file consistency scan** — look for numeric contradictions within one file (e.g., \"50-person team\" in About vs \"20+ developers\" in Experience).\n6. **Attribution check** — for every achievement claim, confirm who actually did the work (user vs intern vs team). Misattributed work collapses under interview probing. When two claims LOOK contradictory (e.g., \"user upgraded Node 12→24\" AND \"intern upgraded Node 12→24\"), do NOT assume one is wrong and flip the attribution — ask about project structure first. Real case: one legacy project had 4 modules (3 API + 1 web); user did the 3 API modules (0→90%+ tests), the intern independently did the web module (Babel→Vite, 100%). Both claims were true and both belong on the resume — module-level ownership questions resolve these. Split-ownership stories are STRONGER: one bullet shows technical execution, the parallel intern result shows mentoring.\n7. **Planned-but-never-used tech** — users often list tech they plan to learn. Confirm \"did you use this in production?\" — learning plans never go on resume\u002FLinkedIn.\n8. **Log corrections** — append a numbered \"Review Notes (date)\" section to the vault note documenting every correction and why, so future sessions don't reintroduce errors. Save durable corrections to memory too.\n\nWhen unsure about a fact, ask the user in ONE batched question (2–4 items) before rewriting — don't guess.\n\n### English Certification → Fluency Level (honest mapping)\n\n| Certification | LinkedIn\u002Fresume fluency |\n|---|---|\n| TOEIC \u003C 600 \u002F A2–B1 | Limited Working Proficiency |\n| TOEIC 600–780 \u002F B2 (e.g., CMU-eGrad B2) | Professional Working Proficiency |\n| TOEIC 785–900 \u002F C1 | Full Professional Proficiency |\n| TOEIC 900+ \u002F C2 | Native or Bilingual Proficiency |\n\nNever claim \"Full Professional\" on a B2 cert — interviewers probe English live and the mismatch reads as dishonesty. Keep resume and LinkedIn fluency identical.\n\n## Pitfalls\n\n- **Never invent metrics** — estimate and mark `[CONFIRM]`, let user verify\n- **Company names must be consistent across artifacts** — use full legal names everywhere (e.g., \"Agoda Services Co., Ltd.\", not \"Agoda\" in one artifact and the full name in another). Ask the user for the registered name if unknown.\n- **Headline vs discretion conflict** — \"Open to New Opportunities\" in a public headline contradicts a Recruiters-only Open to Work strategy (which hides the search from the current employer). Flag it; let the user choose.\n- **Every skills keyword must be evidenced** — only list skills backed by an experience bullet or project; cut the rest (they invite interview questions the user can't answer).\n- **Always show before\u002Fafter rewrites** — suggestions alone are not actionable\n- **Test ATS compatibility by extracting PDF** — if text is jumbled, ATS will reject it\n- **LinkedIn language levels are often wrong** — native speakers underrate themselves\n- **Curate LinkedIn projects** — 10 projects dilutes the strong ones; keep 2-4\n- **Don't skip market research** — Thai conventions differ from US\u002FEU conventions\n\n## Related Skills\n\n- `grill-me` — Use for STAR story extraction sessions\n- `grill-with-docs` — Use when grilling also needs domain modeling\n","# Career Coaching Workflow\n\nComprehensive workflow for job seekers: resume review → LinkedIn audit → master profile → STAR stories → tailored applications.\n\n## When to Use\n\n- User asks for resume\u002FCV review or rewrite\n- User asks for LinkedIn profile audit or optimization\n- User wants to build a \"master profile\" for job applications\n- User needs STAR stories extracted for behavioral interviews\n- User is preparing cover letters or job applications\n\n## The Master Profile Pattern\n\nBuild ONE master profile (Obsidian note) that serves as the single source of truth for all job artifacts. Structure:\n\n### 8-Block Master Profile Framework\n\n1. **Core Identity** — Name, contact, location, languages, LinkedIn URL\n2. **Professional Narrative** — 50-word story: who you are, where you've been, where you're going\n3. **Experience Database** — Each job with: company, dates, role, metrics, tech stack, achievements\n4. **Education & Credentials** — Degree, GPA, honors, certifications, test scores, TA experience\n5. **Skills Inventory** — Categorized by proficiency (Expert\u002FProficient\u002FFamiliar)\n6. **Projects Portfolio** — Curated list with descriptions, tech, impact, links\n7. **STAR Stories** — 8-12 reusable stories covering leadership, conflict, failure, ambiguity, influence, judgment\n8. **Job Search Parameters** — Target roles, industries, salary range, location preferences, deal-breakers\n\n### Artifact Generation Order\n\n1. Master profile (source of truth)\n2. Resume (ATS-optimized, quantified)\n3. LinkedIn (keyword-rich, discoverable)\n4. Cover letter template (tailored per application)\n5. STAR story portfolio (extracted via `\u002Fgrill-me`)\n\n## Resume Review Checklist\n\nSee `references\u002Fresume-review-checklist.md` for the full scoring rubric.\n\n**Critical checks:**\n- ATS compatibility (single-column, standard headings, no tables\u002Fgraphics in headers)\n- Quantification (every bullet has metrics: %, time, users, revenue)\n- Action verbs (Led, Built, Migrated, Reduced — not \"Responsible for\")\n- Professional summary (50 words, keyword-rich, achievement-focused)\n- Skills section (categorized, specific technologies, not vague categories)\n- Contact info (includes LinkedIn URL, language proficiency for Thai market)\n\n## LinkedIn Audit Checklist\n\nSee `references\u002Flinkedin-audit-checklist.md` for the full audit framework.\n\n**Critical checks:**\n- Headline (keyword-rich, 220 chars max, includes role + top 4 tech + architecture keywords)\n- About section (first 3 lines are critical — show before \"see more\" click)\n- Experience detail (same quantification as resume, but expanded)\n- Language levels (Thai = Native\u002Fbilingual, English = Professional working for B2+)\n- Open to Work (enabled — ASK the user which visibility they use: public green frame vs Recruiters-only. The headline must match: with a public frame, drop redundant \"Open to New Opportunities\" phrasing and spend those characters on keywords; with Recruiters-only, keep availability text in the headline but never the green frame)\n- Projects (curate to 2-4 strong projects, remove trivial learning exercises)\n- Certifications (relevant to target roles)\n\n## STAR Story Extraction\n\nUse `\u002Fgrill-me` skill to extract stories. Run 3 sessions minimum:\n\n**Session 1: Technical Leadership**\n- Biggest technical project or migration\n- Focus: problem-solving, technical judgment, impact\n\n**Session 2: People\u002FInfluence**\n- Mentoring, teaching, or leading without authority\n- Focus: communication, influence, team dynamics\n\n**Session 3: Initiative\u002FOwnership**\n- Stepping up in ambiguity, taking ownership\n- Focus: decision-making, accountability, learning from failure\n\nEach session produces one polished STAR story. Add to Block 7 of master profile.\n\n## Personality & Values Assessment Coaching\n\nWhen the user takes, brings, or asks about personality\u002Fvalues tests — their own or employer-mandated:\n\n- **Recommendation tier list:** IPIP Big Five (OCEAN) = the only tier worth trusting for self-insight; Moral Foundations = values layer, recommend as the follow-up after OCEAN; MBTI \u002F DISC \u002F political-compass family = entertainment tier — vocabulary, never verdicts.\n- **Hard privacy rule:** assessment results never enter resume, LinkedIn, cover letters, or interview answers. Values data stays private entirely (Thai market conservatism makes signaling costly).\n- **Interpret from behavioral evidence, not percentiles:** cross-check each trait against the master profile; when behavior contradicts a score, state which reading to trust and why. Full protocol + vault layout: `references\u002Fassessment-interpretation.md`.\n- **High-stability narrators need injected stakes:** very high emotional stability produces failure\u002Fpressure STAR stories with zero emotional texture, which interviewers read as evasive; coach one honest stakes sentence (what was at risk, what was felt) before the Action section.\n- **Every spike trait gets a shadow row:** shadow + countermeasure in the analysis AND in the improvement tracker (e.g., stability spike → silent overload → weekly external load gauge).\n- **Verify test-site URLs live before recommending** (`curl -s -o \u002Fdev\u002Fnull -w \"%{http_code}\" \u003Curl>`): assessment hosts and mirror paths rot without notice; never hand the user an unverified link.\n- **Company-mandated tests:** coach answer-honestly-but-consistently (these instruments carry lie scales; faking badly scores worse than ordinary), treat the hiring *process* as the culture signal rather than the test result, and give the flip question to ask in interviews: \"how does the team actually use these results?\"\n\n## Improvement TODO Tracker\n\nMaintain one living tracker at the career-folder root (`00-Improvement-TODO.md`) — career-level facts about the user, per the vault rule in `career-artifact-prep`:\n\n- Horizon bands: 🔴 Now (dated window) \u002F 🟡 current-role window (probation, first months) \u002F 🟢 long-horizon \u002F ✅ Done.\n- **Done = artifact or evidence link, never intention.** Every open item wikilinks to the real vault artifact it will modify (STAR file, study base, relocation plan, assessment summary); no dangling TODOs.\n- Standing **hygiene item**: diff the master profile against reality each review (story counts, stale \"to be developed\" markers, last-updated dates) — the profile drifts after every prep session.\n- Cadence: weekly review (doubles as the load gauge) + monthly deep review; scheduled retests go in 🟢 with a target month.\n\n## Thai Market Specifics\n\nSee `references\u002Fthai-market.md` for salary ranges, job platforms, and conventions.\n\n**Quick reference:**\n- Mid-level SWE Bangkok: 40,000–70,000 THB\u002Fmonth\n- Remote\u002Finternational: 60,000–100,000+ THB\u002Fmonth\n- Key platforms: JobsDB Thailand, LinkedIn, Blognone\n- Always include language proficiency (Thai + English)\n- Indicate relocation willingness if applying to Bangkok from provinces\n\n## Fact Verification Pass (mandatory on EVERY review)\n\nAgent drafts accumulate fabrication over time — details carried from earlier drafts, wrong guesses, and plausible-sounding specifics survive rewrites. Run this pass before approving any artifact:\n\n1. **Primary-source check** — re-read the user's own resume PDF \u002F official documents; never trust details carried from earlier drafts. (Real cases that had to be removed: an NSTDA job entry, a KMUTNB degree\u002Faward for a CMU graduate, a Node upgrade attributed to an intern instead of the user.)\n2. **Official-name check** — web-search official names of tests, certifications, institutions before writing them. (Real case: CMU's English exit test is officially **CMU-eGrad** per reg.cmu.ac.th — guessed acronyms like \"CMU TEP\u002FTEGS\" were wrong twice in a row.)\n3. **URL check** — HTTP-check every GitHub\u002Fportfolio URL in the artifact (`curl -s -o \u002Fdev\u002Fnull -w \"%{http_code}\" \u003Curl>`); 404 = remove the link or mark \"none yet\". A 404 under a personal account does NOT prove the repo doesn't exist — university\u002Fteam projects often live under a GitHub **organization** account. Before deleting a link, probe `https:\u002F\u002Fapi.github.com\u002Forgs\u002F\u003COrg>\u002Frepos` or ask the user where the repo lives. (Real case: Transmatter lived under github.com\u002FTransmatter org; it was nearly cut because probes only hit personal accounts.)\n4. **Cross-file contradiction scan** — after ANY fact correction, grep ALL artifact files (resume, LinkedIn, master profile, STAR stories) for the old value and fix every occurrence, including memory. Verify clean with a final grep.\n5. **Same-file consistency scan** — look for numeric contradictions within one file (e.g., \"50-person team\" in About vs \"20+ developers\" in Experience).\n6. **Attribution check** — for every achievement claim, confirm who actually did the work (user vs intern vs team). Misattributed work collapses under interview probing. When two claims LOOK contradictory (e.g., \"user upgraded Node 12→24\" AND \"intern upgraded Node 12→24\"), do NOT assume one is wrong and flip the attribution — ask about project structure first. Real case: one legacy project had 4 modules (3 API + 1 web); user did the 3 API modules (0→90%+ tests), the intern independently did the web module (Babel→Vite, 100%). Both claims were true and both belong on the resume — module-level ownership questions resolve these. Split-ownership stories are STRONGER: one bullet shows technical execution, the parallel intern result shows mentoring.\n7. **Planned-but-never-used tech** — users often list tech they plan to learn. Confirm \"did you use this in production?\" — learning plans never go on resume\u002FLinkedIn.\n8. **Log corrections** — append a numbered \"Review Notes (date)\" section to the vault note documenting every correction and why, so future sessions don't reintroduce errors. Save durable corrections to memory too.\n\nWhen unsure about a fact, ask the user in ONE batched question (2–4 items) before rewriting — don't guess.\n\n### English Certification → Fluency Level (honest mapping)\n\n| Certification | LinkedIn\u002Fresume fluency |\n|---|---|\n| TOEIC \u003C 600 \u002F A2–B1 | Limited Working Proficiency |\n| TOEIC 600–780 \u002F B2 (e.g., CMU-eGrad B2) | Professional Working Proficiency |\n| TOEIC 785–900 \u002F C1 | Full Professional Proficiency |\n| TOEIC 900+ \u002F C2 | Native or Bilingual Proficiency |\n\nNever claim \"Full Professional\" on a B2 cert — interviewers probe English live and the mismatch reads as dishonesty. Keep resume and LinkedIn fluency identical.\n\n## Pitfalls\n\n- **Never invent metrics** — estimate and mark `[CONFIRM]`, let user verify\n- **Company names must be consistent across artifacts** — use full legal names everywhere (e.g., \"Agoda Services Co., Ltd.\", not \"Agoda\" in one artifact and the full name in another). Ask the user for the registered name if unknown.\n- **Headline vs discretion conflict** — \"Open to New Opportunities\" in a public headline contradicts a Recruiters-only Open to Work strategy (which hides the search from the current employer). Flag it; let the user choose.\n- **Every skills keyword must be evidenced** — only list skills backed by an experience bullet or project; cut the rest (they invite interview questions the user can't answer).\n- **Always show before\u002Fafter rewrites** — suggestions alone are not actionable\n- **Test ATS compatibility by extracting PDF** — if text is jumbled, ATS will reject it\n- **LinkedIn language levels are often wrong** — native speakers underrate themselves\n- **Curate LinkedIn projects** — 10 projects dilutes the strong ones; keep 2-4\n- **Don't skip market research** — Thai conventions differ from US\u002FEU conventions\n\n## Related Skills\n\n- `grill-me` — Use for STAR story extraction sessions\n- `grill-with-docs` — Use when grilling also needs domain modeling\n",{"name":5,"tags":24,"description":7},[25,26,27,28,29,30],"career","resume","linkedin","interview","star","job-search","main","2988869c5a7d7be2225c9ea7a54a4a56a59b0d45","workflow\u002Fcareer-coach\u002Fcareer-coaching",0,"https:\u002F\u002Fgithub.com\u002Foat431\u002Fhermes_config_backup","https:\u002F\u002Fgithub.com\u002Foat431","https:\u002F\u002Fpanomete.com\u002F","Hope and Luck is not a part of the strategy, \r\n\r\nSoftskill produces plan Hard skill produce product.","2026-11-03 00:43:08",{"source":8,"skillName":5,"commands":41,"prompt":51,"zipAvailable":52},[42,45,48],{"tool":43,"command":44},"npx","npx skills add oat431\u002Fhermes_config_backup --skill career-coaching",{"tool":46,"command":47},"bunx","bunx skills add oat431\u002Fhermes_config_backup --skill career-coaching",{"tool":49,"command":50},"pnpm","pnpm dlx skills add oat431\u002Fhermes_config_backup --skill career-coaching","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Foat431\u002Fhermes_config_backup\u002Fblob\u002Fmain\u002Fworkflow\u002Fcareer-coach\u002Fcareer-coaching\u002FSKILL.md",true,[54,60,64,68,72,76],{"path":55,"resourceType":56,"resourceTypeDesc":57,"sizeBytes":58,"sourceHtmlUrl":59},"references\u002Fassessment-interpretation.md","REFERENCE","参考文档",3566,"https:\u002F\u002Fgithub.com\u002Foat431\u002Fhermes_config_backup\u002Fblob\u002Fmain\u002Fworkflow\u002Fcareer-coach\u002Fcareer-coaching\u002Freferences\u002Fassessment-interpretation.md",{"path":61,"resourceType":56,"resourceTypeDesc":57,"sizeBytes":62,"sourceHtmlUrl":63},"references\u002Finterview-prep-fill-review.md",4145,"https:\u002F\u002Fgithub.com\u002Foat431\u002Fhermes_config_backup\u002Fblob\u002Fmain\u002Fworkflow\u002Fcareer-coach\u002Fcareer-coaching\u002Freferences\u002Finterview-prep-fill-review.md",{"path":65,"resourceType":56,"resourceTypeDesc":57,"sizeBytes":66,"sourceHtmlUrl":67},"references\u002Finterview-prep-vault.md",4109,"https:\u002F\u002Fgithub.com\u002Foat431\u002Fhermes_config_backup\u002Fblob\u002Fmain\u002Fworkflow\u002Fcareer-coach\u002Fcareer-coaching\u002Freferences\u002Finterview-prep-vault.md",{"path":69,"resourceType":56,"resourceTypeDesc":57,"sizeBytes":70,"sourceHtmlUrl":71},"references\u002Flinkedin-audit-checklist.md",7112,"https:\u002F\u002Fgithub.com\u002Foat431\u002Fhermes_config_backup\u002Fblob\u002Fmain\u002Fworkflow\u002Fcareer-coach\u002Fcareer-coaching\u002Freferences\u002Flinkedin-audit-checklist.md",{"path":73,"resourceType":56,"resourceTypeDesc":57,"sizeBytes":74,"sourceHtmlUrl":75},"references\u002Fresume-review-checklist.md",5289,"https:\u002F\u002Fgithub.com\u002Foat431\u002Fhermes_config_backup\u002Fblob\u002Fmain\u002Fworkflow\u002Fcareer-coach\u002Fcareer-coaching\u002Freferences\u002Fresume-review-checklist.md",{"path":77,"resourceType":56,"resourceTypeDesc":57,"sizeBytes":78,"sourceHtmlUrl":79},"references\u002Fthai-market.md",6831,"https:\u002F\u002Fgithub.com\u002Foat431\u002Fhermes_config_backup\u002Fblob\u002Fmain\u002Fworkflow\u002Fcareer-coach\u002Fcareer-coaching\u002Freferences\u002Fthai-market.md",[81,89,96,103,110,117],{"skillNo":82,"name":83,"nameZh":6,"description":84,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":85,"licenseFileUrl":6,"sourceHtmlUrl":86,"categories":87,"keywords":88,"publishedAt":19},"01M7AYZ2JY3NFKAPQSC39N5F3F","project-spec-docs","Fill\u002Fupdate project_spec docs (templates, MM handoffs).","MIT","https:\u002F\u002Fgithub.com\u002Foat431\u002Fhermes_config_backup\u002Fblob\u002Fmain\u002Fworkflow\u002Fui-ux\u002Fproject-spec-docs\u002FSKILL.md",[],[],{"skillNo":90,"name":91,"nameZh":6,"description":92,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":85,"licenseFileUrl":6,"sourceHtmlUrl":93,"categories":94,"keywords":95,"publishedAt":19},"01M7AYYRZPE7HQX7778558X52S","penpot-mcp","Penpot MCP: connect, verify, and fix streaming via nginx.","https:\u002F\u002Fgithub.com\u002Foat431\u002Fhermes_config_backup\u002Fblob\u002Fmain\u002Fworkflow\u002Fui-ux\u002Fpenpot-mcp\u002FSKILL.md",[],[],{"skillNo":97,"name":98,"nameZh":6,"description":99,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":100,"categories":101,"keywords":102,"publishedAt":19},"01M7AYYNKP61CN2281VMJDXMB5","nginx-streaming-proxy","Configure nginx for streaming endpoints (SSE, MCP, WS).","https:\u002F\u002Fgithub.com\u002Foat431\u002Fhermes_config_backup\u002Fblob\u002Fmain\u002Fworkflow\u002Fui-ux\u002Fnginx-streaming-proxy\u002FSKILL.md",[],[],{"skillNo":104,"name":105,"nameZh":6,"description":106,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":85,"licenseFileUrl":6,"sourceHtmlUrl":107,"categories":108,"keywords":109,"publishedAt":19},"01M7AYYJP0MDV1D3WVEEZB3SGA","branding-ci","Use for brand\u002FCI identity, style guides, and brand docs.","https:\u002F\u002Fgithub.com\u002Foat431\u002Fhermes_config_backup\u002Fblob\u002Fmain\u002Fworkflow\u002Fui-ux\u002Fbranding-ci\u002FSKILL.md",[],[],{"skillNo":111,"name":112,"nameZh":6,"description":113,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":114,"categories":115,"keywords":116,"publishedAt":19},"01M7AYYGCXVT97DDTCM0ZJT6F6","yuanbao","Yuanbao (元宝) groups: @mention users, query info\u002Fmembers.","https:\u002F\u002Fgithub.com\u002Foat431\u002Fhermes_config_backup\u002Fblob\u002Fmain\u002Fworkflow\u002Fshared-skills\u002Fyuanbao\u002FSKILL.md",[],[],{"skillNo":118,"name":119,"nameZh":6,"description":120,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":121,"categories":122,"keywords":123,"publishedAt":19},"01M7AYYC2Y65NMGMD4GQXAZMMS","slidev","Create and present web-based slidedecks for developers using Slidev with Markdown, Vue components, code highlighting, animations, and interactive features. Use when building technical presentations, conference talks, code walkthroughs, teaching materials, or developer decks.","https:\u002F\u002Fgithub.com\u002Foat431\u002Fhermes_config_backup\u002Fblob\u002Fmain\u002Fworkflow\u002Fshared-skills\u002Fslidev\u002FSKILL.md",[],[]]