[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7EJB5JN5SSP4CQSWNKXTWQW":3,"skill-same:01M7EJB5JN5SSP4CQSWNKXTWQW":63},{"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":25,"commitSha":26,"skillDirectory":27,"forksCount":14,"repositoryHtmlUrl":28,"repositoryHomepageUrl":29,"ownerHtmlUrl":30,"ownerBlogUrl":31,"ownerDescription":6,"updatedAt":32,"install":33,"resources":46},"01M7EJB5JN5SSP4CQSWNKXTWQW","cold-email-ops",null,"Plan and audit a cold-email program at volume and keep it from degrading: computes inbox and domain capacity from a monthly send target, sets per-domain reply-rate floors, burn-replacement cadence, shadow-ban tests, and automation error budgets, and reports prospects-to-lead with per-client averages. Use when someone is scaling outbound, asks how many inboxes or domains they need, why reply rates are falling or a domain might be shadow banned, or reviews an AI outbound stack for failure points. Not for pre-load list QA (cold-email-list-gate), writing or polishing the emails themselves (wordsmith), inbound SEO (seo-audit, programmatic-seo), WhatsApp\u002FRCS messaging (integrate-whatsapp, sent-two-way-messaging), or finding the market\u002FICP.","arm-pz\u002Fcaffeinity-skills","arm-pz","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F29532099?v=4","01M7EJ726AAB9GD0C5C5G9NJEG","Abdul Rahman","01M7EJ726X4ZD3R4ESGX90K47M",0,"MIT","https:\u002F\u002Fgithub.com\u002Farm-pz\u002Fcaffeinity-skills\u002Fblob\u002Fmain\u002Fplugins\u002Fcaffeinity\u002Fskills\u002Fcold-email-ops\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: cold-email-ops\ndescription: >-\n  Plan and audit a cold-email program at volume and keep it from degrading: computes\n  inbox and domain capacity from a monthly send target, sets per-domain reply-rate\n  floors, burn-replacement cadence, shadow-ban tests, and automation error budgets,\n  and reports prospects-to-lead with per-client averages. Use when someone is scaling\n  outbound, asks how many inboxes or domains they need, why reply rates are falling\n  or a domain might be shadow banned, or reviews an AI outbound stack for failure\n  points. Not for pre-load list QA (cold-email-list-gate), writing or polishing the\n  emails themselves (wordsmith), inbound SEO (seo-audit, programmatic-seo),\n  WhatsApp\u002FRCS messaging (integrate-whatsapp, sent-two-way-messaging), or finding\n  the market\u002FICP.\nversion: 1.0.0\n---\n\n# Cold email ops\n\nOperating model distilled from Will Breton's account of running 3.5M+ cold emails a month (source and caveats in `references\u002Fbenchmarks.md`). Treat outbound as four human roles wired into one math budget: list builder, copywriter, deliverability person, reply handler. Every automated step keeps an owner and a check. Plan for the volume you want, not the volume you have.\n\n## Classify the job first\n\n- **Plan** — new program or a volume target. Output capacity, gate design, monitoring spec, and the role\u002Fautomation map.\n- **Audit** — a running program is degrading. Output area verdicts and findings with evidence.\n- **Stack review** — automation reliability. Output the step map and blast radius.\n- **List gate** — one list before load is a different job. Use `cold-email-list-gate` and return its GO\u002FHOLD; do not run the ten-row check inside this skill.\n\nOpen `references\u002Freport-format.md` for the section list of the job you picked.\n\n## Collect inputs once\n\nAsk for: monthly send target; current domains and inboxes; sending tool and data provider; sends, replies, and bounces by domain and by receiving provider; who answers replies and how fast; client roster when the work is agency-side. A missing metric becomes INCONCLUSIVE — never estimate it silently, and never present the source's numbers as the client's results.\n\n## Volume is inbox math\n\nRun the arithmetic with `scripts\u002Fcold_email_math.py` instead of by hand (paths resolve from this skill's base directory):\n\n```\npython scripts\u002Fcold_email_math.py capacity --monthly 500000\npython scripts\u002Fcold_email_math.py errors 0.8 0.8 0.8 0.8\npython scripts\u002Fcold_email_math.py ptl --contacts 20000 --leads 53\n```\n\n- Budget ~10 cold sends per inbox per day (up to 20 only while the inbox is healthy), 3 inboxes per domain, ~22 sending days per month. At those defaults 100k\u002Fmonth needs ≈455 inboxes and ≈152 domains; 1M\u002Fmonth needs ≈4,546 and ≈1,516. The 22-day assumption is what reconciles the source's 450 \u002F 4,500 figures; say so when quoting them.\n- Build for the target volume from day one. Capacity added after the list is ready becomes a bottleneck with a deadline.\n- Every inbox burns in 6–9 months even with clean SPF, DKIM, and DMARC. Steady-state replacement is inboxes ÷ burn months; replace weekly, same day when one fails, so total volume does not dip.\n- Split every report by receiving provider (Google \u002F Outlook \u002F other). The source saw ~6.5× more replies from Google recipients than Microsoft ones; treat that as directional and verify it in the account's own data. Lumping providers hides what works. For Microsoft-heavy enterprise TAMs, match the sending provider to the receiving one.\n\n## The list breaks before deliverability does\n\n- Pre-load checks belong to `cold-email-list-gate`. In an audit, judge the list from outcomes: bounce rate, valid-contact rate, and whether the bad rows share one filter. Hand a pre-load sample to the gate skill rather than re-deriving it here.\n- Lead quality is decided at the data provider. Compare providers on the same criteria with a sample, using valid-contact rate (dials per in-profile person for phone work). Switching providers is a delivery lever, not a cleanup task.\n- A list that failed in production is audit evidence, not a sample. Name the shared fail pattern and the query or provider that produced it.\n\n## Deliverability rules\n\n- **Domain floor:** ≥1% reply rate, automated replies included. Below the floor, schedule replacement — do not \"keep monitoring\".\n- **Slope beats level:** two consecutive weeks of falling reply rate puts a domain on watch even while it clears 1%. The slope catches the failure before the floor does.\n- Monitor every inbox daily; alert on a reply dip or a bounce rise; swap the same day. Keep per-inbox volume low so one dead inbox barely moves the total.\n- **Shadow-ban test:** 0% bounce, healthy placement, zero replies. Rewrite the copy once, not the infrastructure. No change within 48 hours — retire the inboxes. Dead infrastructure stays dead.\n- One bad week is not a burned domain. Require the two-week slope or a failed floor before condemning infrastructure.\n\n## Errors multiply — harden the automation\n\n- End-to-end reliability is the product of step accuracies: 0.8 × 0.8 × 0.8 × 0.8 leaves ≈41%. Compute it before trusting a pipeline; even 0.99 four times over leaves ≈96%, which at 100k sends is thousands of misses.\n- Give agents menus, not free text; gate every bulk run behind a sample you approve; keep history append-only so you can see what it did.\n- Rules get gamed. \"Get 5,000 leads\" invites fabrication; gate on quality checks (the 10-row sample, valid-contact rate) and keep volume quotas as reporting, not instructions.\n- For each automated step record owner, check, accuracy estimate, and blast radius (how many emails a failure reaches before detection). A step with no check is where the audit starts.\n\n## Replies and results\n\n- Speed to lead is the biggest lever after the reply: answering within 5 minutes lifts positive-reply-to-meeting from ~20% to ~80%; a day later the lead is effectively lost. Name who is on replies and their hours before scaling volume.\n- Track prospects-to-lead (PTL) = contacts sent ÷ leads. Under 500 is strong. At high volume prefer PTL to reply rate, which stops discriminating once volume is large.\n- Run both motions: tight 500-contact lists with tailored messaging (~5% reply) alongside broad universal messaging (~1% at scale). Do not re-contact a tight list for at least a month. 5% of 500 is 25 replies; 1% of 100,000 is 1,000.\n- Agency work: track each client against agency-wide averages. A client under average is an early warning weeks before they complain — surface it as a warning, not a verdict.\n\n## Report with evidence\n\n- Every number is an input, a script output, or an assumption labeled as one. Source benchmarks stay labeled \"source benchmark\".\n- Verdicts are PASS \u002F WATCH \u002F FAIL per area, plus INCONCLUSIVE where data is missing. A missing metric never becomes a PASS.\n- End with an owner and a next check date for every open finding.\n\n## Boundaries\n\n- Emails need writing or rewriting → `wordsmith`. Hand it the diagnosis (segment, what the reply data says) plus the current copy.\n- One list before load → `cold-email-list-gate`. This skill audits lists that already sent.\n- Inbound search → `seo-audit` or `programmatic-seo`. WhatsApp or RCS messaging → `integrate-whatsapp` or `sent-two-way-messaging`.\n- ICP discovery, offer design, and list acquisition tooling are out of scope. State the assumed market and sender, then stop.\n- This skill produces plans and audits. It does not send mail, buy lists, or scrape contacts.\n\n## References\n\n- `references\u002Fbenchmarks.md` — every threshold used here, its source, and when it may be overridden. Read before defending or changing a number.\n- `references\u002Freport-format.md` — plan, audit, and list-gate templates with table columns and verdict definitions. Read when writing the deliverable.\n","# Cold email ops\n\nOperating model distilled from Will Breton's account of running 3.5M+ cold emails a month (source and caveats in `references\u002Fbenchmarks.md`). Treat outbound as four human roles wired into one math budget: list builder, copywriter, deliverability person, reply handler. Every automated step keeps an owner and a check. Plan for the volume you want, not the volume you have.\n\n## Classify the job first\n\n- **Plan** — new program or a volume target. Output capacity, gate design, monitoring spec, and the role\u002Fautomation map.\n- **Audit** — a running program is degrading. Output area verdicts and findings with evidence.\n- **Stack review** — automation reliability. Output the step map and blast radius.\n- **List gate** — one list before load is a different job. Use `cold-email-list-gate` and return its GO\u002FHOLD; do not run the ten-row check inside this skill.\n\nOpen `references\u002Freport-format.md` for the section list of the job you picked.\n\n## Collect inputs once\n\nAsk for: monthly send target; current domains and inboxes; sending tool and data provider; sends, replies, and bounces by domain and by receiving provider; who answers replies and how fast; client roster when the work is agency-side. A missing metric becomes INCONCLUSIVE — never estimate it silently, and never present the source's numbers as the client's results.\n\n## Volume is inbox math\n\nRun the arithmetic with `scripts\u002Fcold_email_math.py` instead of by hand (paths resolve from this skill's base directory):\n\n```\npython scripts\u002Fcold_email_math.py capacity --monthly 500000\npython scripts\u002Fcold_email_math.py errors 0.8 0.8 0.8 0.8\npython scripts\u002Fcold_email_math.py ptl --contacts 20000 --leads 53\n```\n\n- Budget ~10 cold sends per inbox per day (up to 20 only while the inbox is healthy), 3 inboxes per domain, ~22 sending days per month. At those defaults 100k\u002Fmonth needs ≈455 inboxes and ≈152 domains; 1M\u002Fmonth needs ≈4,546 and ≈1,516. The 22-day assumption is what reconciles the source's 450 \u002F 4,500 figures; say so when quoting them.\n- Build for the target volume from day one. Capacity added after the list is ready becomes a bottleneck with a deadline.\n- Every inbox burns in 6–9 months even with clean SPF, DKIM, and DMARC. Steady-state replacement is inboxes ÷ burn months; replace weekly, same day when one fails, so total volume does not dip.\n- Split every report by receiving provider (Google \u002F Outlook \u002F other). The source saw ~6.5× more replies from Google recipients than Microsoft ones; treat that as directional and verify it in the account's own data. Lumping providers hides what works. For Microsoft-heavy enterprise TAMs, match the sending provider to the receiving one.\n\n## The list breaks before deliverability does\n\n- Pre-load checks belong to `cold-email-list-gate`. In an audit, judge the list from outcomes: bounce rate, valid-contact rate, and whether the bad rows share one filter. Hand a pre-load sample to the gate skill rather than re-deriving it here.\n- Lead quality is decided at the data provider. Compare providers on the same criteria with a sample, using valid-contact rate (dials per in-profile person for phone work). Switching providers is a delivery lever, not a cleanup task.\n- A list that failed in production is audit evidence, not a sample. Name the shared fail pattern and the query or provider that produced it.\n\n## Deliverability rules\n\n- **Domain floor:** ≥1% reply rate, automated replies included. Below the floor, schedule replacement — do not \"keep monitoring\".\n- **Slope beats level:** two consecutive weeks of falling reply rate puts a domain on watch even while it clears 1%. The slope catches the failure before the floor does.\n- Monitor every inbox daily; alert on a reply dip or a bounce rise; swap the same day. Keep per-inbox volume low so one dead inbox barely moves the total.\n- **Shadow-ban test:** 0% bounce, healthy placement, zero replies. Rewrite the copy once, not the infrastructure. No change within 48 hours — retire the inboxes. Dead infrastructure stays dead.\n- One bad week is not a burned domain. Require the two-week slope or a failed floor before condemning infrastructure.\n\n## Errors multiply — harden the automation\n\n- End-to-end reliability is the product of step accuracies: 0.8 × 0.8 × 0.8 × 0.8 leaves ≈41%. Compute it before trusting a pipeline; even 0.99 four times over leaves ≈96%, which at 100k sends is thousands of misses.\n- Give agents menus, not free text; gate every bulk run behind a sample you approve; keep history append-only so you can see what it did.\n- Rules get gamed. \"Get 5,000 leads\" invites fabrication; gate on quality checks (the 10-row sample, valid-contact rate) and keep volume quotas as reporting, not instructions.\n- For each automated step record owner, check, accuracy estimate, and blast radius (how many emails a failure reaches before detection). A step with no check is where the audit starts.\n\n## Replies and results\n\n- Speed to lead is the biggest lever after the reply: answering within 5 minutes lifts positive-reply-to-meeting from ~20% to ~80%; a day later the lead is effectively lost. Name who is on replies and their hours before scaling volume.\n- Track prospects-to-lead (PTL) = contacts sent ÷ leads. Under 500 is strong. At high volume prefer PTL to reply rate, which stops discriminating once volume is large.\n- Run both motions: tight 500-contact lists with tailored messaging (~5% reply) alongside broad universal messaging (~1% at scale). Do not re-contact a tight list for at least a month. 5% of 500 is 25 replies; 1% of 100,000 is 1,000.\n- Agency work: track each client against agency-wide averages. A client under average is an early warning weeks before they complain — surface it as a warning, not a verdict.\n\n## Report with evidence\n\n- Every number is an input, a script output, or an assumption labeled as one. Source benchmarks stay labeled \"source benchmark\".\n- Verdicts are PASS \u002F WATCH \u002F FAIL per area, plus INCONCLUSIVE where data is missing. A missing metric never becomes a PASS.\n- End with an owner and a next check date for every open finding.\n\n## Boundaries\n\n- Emails need writing or rewriting → `wordsmith`. Hand it the diagnosis (segment, what the reply data says) plus the current copy.\n- One list before load → `cold-email-list-gate`. This skill audits lists that already sent.\n- Inbound search → `seo-audit` or `programmatic-seo`. WhatsApp or RCS messaging → `integrate-whatsapp` or `sent-two-way-messaging`.\n- ICP discovery, offer design, and list acquisition tooling are out of scope. State the assumed market and sender, then stop.\n- This skill produces plans and audits. It does not send mail, buy lists, or scrape contacts.\n\n## References\n\n- `references\u002Fbenchmarks.md` — every threshold used here, its source, and when it may be overridden. Read before defending or changing a number.\n- `references\u002Freport-format.md` — plan, audit, and list-gate templates with table columns and verdict definitions. Read when writing the deliverable.\n",{"name":5,"version":24,"description":7},"1.0.0","main","523bc2bf98727c9fd981424f86ecba66c6d6ecd6","plugins\u002Fcaffeinity\u002Fskills\u002Fcold-email-ops","https:\u002F\u002Fgithub.com\u002Farm-pz\u002Fcaffeinity-skills","https:\u002F\u002Fskills.caffeinity.com\u002F","https:\u002F\u002Fgithub.com\u002Farm-pz","skills.caffeinity.com","2026-11-14 01:22:10",{"source":8,"skillName":5,"commands":34,"prompt":44,"zipAvailable":45},[35,38,41],{"tool":36,"command":37},"npx","npx skills add arm-pz\u002Fcaffeinity-skills --skill cold-email-ops",{"tool":39,"command":40},"bunx","bunx skills add arm-pz\u002Fcaffeinity-skills --skill cold-email-ops",{"tool":42,"command":43},"pnpm","pnpm dlx skills add arm-pz\u002Fcaffeinity-skills --skill cold-email-ops","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Farm-pz\u002Fcaffeinity-skills\u002Fblob\u002Fmain\u002Fplugins\u002Fcaffeinity\u002Fskills\u002Fcold-email-ops\u002FSKILL.md",true,[47,53,57],{"path":48,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":51,"sourceHtmlUrl":52},"references\u002Fbenchmarks.md","REFERENCE","参考文档",4381,"https:\u002F\u002Fgithub.com\u002Farm-pz\u002Fcaffeinity-skills\u002Fblob\u002Fmain\u002Fplugins\u002Fcaffeinity\u002Fskills\u002Fcold-email-ops\u002Freferences\u002Fbenchmarks.md",{"path":54,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":55,"sourceHtmlUrl":56},"references\u002Freport-format.md",3226,"https:\u002F\u002Fgithub.com\u002Farm-pz\u002Fcaffeinity-skills\u002Fblob\u002Fmain\u002Fplugins\u002Fcaffeinity\u002Fskills\u002Fcold-email-ops\u002Freferences\u002Freport-format.md",{"path":58,"resourceType":59,"resourceTypeDesc":60,"sizeBytes":61,"sourceHtmlUrl":62},"scripts\u002Fcold_email_math.py","SCRIPT","脚本",5709,"https:\u002F\u002Fgithub.com\u002Farm-pz\u002Fcaffeinity-skills\u002Fblob\u002Fmain\u002Fplugins\u002Fcaffeinity\u002Fskills\u002Fcold-email-ops\u002Fscripts\u002Fcold_email_math.py",[64,71,78,85,92,99],{"skillNo":65,"name":66,"nameZh":6,"description":67,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":68,"categories":69,"keywords":70,"publishedAt":19},"01M7EJR8K8FDPBY02RFPRRW19M","tune-and-ship","Takes one published skill at a time from as-is to tuned, fact-checked, released and live, then moves to the next one in the catalog. Each run tunes the skill with tune-skill, checks every version number, flag, price and command it states against the primary source, re-reads its siblings' real SKILL.md files, polishes the listing with findable-polish, writes the version and release notes, opens one PR, and after the merge confirms the site page and marketplace copy are live. Use whenever the user wants to fine-tune their other skills, work through the catalog, give a published skill the full treatment, fact-check a skill's claims, or ship a tune instead of drafting it, even if they never say \"ship\". Not for a tune with no release (use tune-skill), drafts with nothing pushed (use tune-and-polish), a new skill (use skill-launch), regressions from the nightly health check (use caffeinity-routing's Descale brew), or a whole collection (use skill-estate).","https:\u002F\u002Fgithub.com\u002Farm-pz\u002Fcaffeinity-skills\u002Fblob\u002Fmain\u002Fplugins\u002Ftune-and-ship\u002Fskills\u002Ftune-and-ship\u002FSKILL.md",[],[],{"skillNo":72,"name":73,"nameZh":6,"description":74,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":75,"categories":76,"keywords":77,"publishedAt":19},"01M7EJR2D3H3EA8PT9PVR8DVTS","skill-estate","Takes a whole collection of agent skill repos from scattered to published, consistent and self-maintaining, in gated phases: inventory every repo, reconcile site, marketplace and README listings, test and tune the family, close workflow gaps, wire publishing so new skill repos go live on their own, bundle a plugin with agents, add trigger tests and directory listings, and leave a maintenance loop and a map. Each phase hands off to the skill that owns it and ends in PRs. Use when someone's skills site and GitHub disagree, wants all their skill repos audited or cleaned up, wants new skills to publish themselves, or wants that cleanup repeated on another org, even if they never say estate. Not for one skill (use tune-skill), one listing (use findable), the site pipeline alone (use publish-pipeline), or weekly upkeep (use caffeinity-routing's Descale brew).","https:\u002F\u002Fgithub.com\u002Farm-pz\u002Fcaffeinity-skills\u002Fblob\u002Fmain\u002Fplugins\u002Fskill-estate\u002Fskills\u002Fskill-estate\u002FSKILL.md",[],[],{"skillNo":79,"name":80,"nameZh":6,"description":81,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":82,"categories":83,"keywords":84,"publishedAt":19},"01M7EJQVD17QR594SGFS5Z1T34","paper-trail","Drafts the policy pages a small product needs before it takes money or data (privacy policy, terms of service, refund policy, cookie notice) from a fact sheet about what the product actually collects, stores, shares and charges, then checks the drafts for placeholders, missing sections and facts nobody supplied. Use when someone needs a privacy policy, terms, refund or cookie page for a site, app, SaaS, newsletter or digital product, asks what legal pages they need before launch, or wants existing policy pages checked against what the product really does, even if they never say \"legal\". Not legal advice and not for contracts, NDAs or employment documents (use a lawyer), and not for the launch plan itself (use solo-income-blueprint) or the site build (use site-prompt).","https:\u002F\u002Fgithub.com\u002Farm-pz\u002Fcaffeinity-skills\u002Fblob\u002Fmain\u002Fplugins\u002Fpaper-trail\u002Fskills\u002Fpaper-trail\u002FSKILL.md",[],[],{"skillNo":86,"name":87,"nameZh":6,"description":88,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":89,"categories":90,"keywords":91,"publishedAt":19},"01M7EJQM55D4W6D9SJB8WDVP27","course-builder","Designs a course for a group of learners (a class, cohort, workshop series, bootcamp or internal training): measurable outcomes, a module sequence with prerequisites, activities and assessments aligned to each outcome, a time budget that fits the hours available, and a rubric, then checks the plan with a script so no outcome goes untaught or unassessed. Use when someone is teaching others and asks for a curriculum, syllabus, course outline, module plan, cohort or workshop structure, or wants an existing course checked for gaps and overload, even if they never say \"curriculum\". Not for one person's own learning plan (use study-system), for being taught the topic (use topic-primer), or for marketing the course (use sales-copy).","https:\u002F\u002Fgithub.com\u002Farm-pz\u002Fcaffeinity-skills\u002Fblob\u002Fmain\u002Fplugins\u002Fcourse-builder\u002Fskills\u002Fcourse-builder\u002FSKILL.md",[],[],{"skillNo":93,"name":94,"nameZh":6,"description":95,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":96,"categories":97,"keywords":98,"publishedAt":19},"01M7EJQDFT8K0PW1HF7RPS6M03","wordsmith","Write, draft, rewrite, edit, proofread, polish and improve text while preserving the author's intended meaning, facts and voice. Use when the user wants clearer, shorter or better-toned writing; grammar, structure or flow fixes; emails, website or marketing copy, headlines, outlines or summaries; a different reading level; an accessibility, inclusivity or accuracy review; or content prepared for publication, even if they never say \"edit\". Also handles \u002Fwordsmith commands such as draft, critique, audit, tighten, tone and final. Not for resumes, CVs or LinkedIn profiles (use recruiter-lens if installed), not for code or code comments, and not for building .docx or .pdf files (write the text here, then use the file skill).","https:\u002F\u002Fgithub.com\u002Farm-pz\u002Fcaffeinity-skills\u002Fblob\u002Fmain\u002Fplugins\u002Fcaffeinity\u002Fskills\u002Fwordsmith\u002FSKILL.md",[],[],{"skillNo":100,"name":101,"nameZh":6,"description":102,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":103,"categories":104,"keywords":105,"publishedAt":19},"01M7EJQ3TFWMSW96T0E49W310A","web-preflight","Use when shipping, deploying, publishing, launching, reviewing, or pre-flighting a website or API and you want a lightweight check for accidental exposure of secrets, source or configuration files, admin and debug surfaces, unsafe redirects, missing security controls, and misleading 200 responses. Trigger phrases include \"before we ship\", \"security check\", \"preflight\", \"audit the site\", \"check the production URL\", \"is my .env exposed\", and \"why does \u002F.env return 200\", including when access-log or analytics evidence is supplied. Checks only sites the user owns or is authorized to assess, with bounded GET and HEAD requests and a fixed compact path set; distinguishes genuine resources from SPA catch-all and blanket WAF responses. Not for penetration testing, exploitation, credential testing, broad port scanning, or application-code review; use a dedicated authorized security-testing or code-review workflow instead.","https:\u002F\u002Fgithub.com\u002Farm-pz\u002Fcaffeinity-skills\u002Fblob\u002Fmain\u002Fplugins\u002Fcaffeinity\u002Fskills\u002Fweb-preflight\u002FSKILL.md",[],[]]