[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7ECSHZDB7JK6QGQPDFYBPR1":3,"skill-same:01M7ECSHZDB7JK6QGQPDFYBPR1":71},{"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":43,"commitSha":44,"skillDirectory":45,"forksCount":46,"repositoryHtmlUrl":47,"repositoryHomepageUrl":6,"ownerHtmlUrl":48,"ownerBlogUrl":6,"ownerDescription":49,"updatedAt":50,"install":51,"resources":64},"01M7ECSHZDB7JK6QGQPDFYBPR1","linkedin-post-writer",null,"Draft LinkedIn posts from 16 tested hook formulas mapped to engagement goals (comments, reposts, likes, saves), with 2026 algorithm formatting rules and an AI-tell scrub pass before publishing.","lza6\u002FArmor-piercing-system-prompts","lza6","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F128880206?v=4","01M7EB3K7WPX5T28EJ2NVHE6EG","Chinese-tingfeng","01M7EB3K97E1KQ16QWKJMFNGX8",11,"MIT","https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F03-逆向工程\u002Flinkedin-post-writer\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: linkedin-post-writer\ndescription: \"Draft LinkedIn posts from 16 tested hook formulas mapped to engagement goals (comments, reposts, likes, saves), with 2026 algorithm formatting rules and an AI-tell scrub pass before publishing.\"\ncategory: marketing\nrisk: none\nsource: community\nsource_repo: sergebulaev\u002Flinkedin-skills\nsource_type: community\ndate_added: \"2026-07-06\"\nauthor: sergebulaev\ntags: [linkedin, copywriting, hooks, social-media, personal-brand, content-marketing]\ntools: [claude, codex, cursor, gemini]\nlicense: \"MIT\"\nlicense_source: \"https:\u002F\u002Fgithub.com\u002Fsergebulaev\u002Flinkedin-skills\u002Fblob\u002Fmain\u002FLICENSE\"\n---\n\n# LinkedIn Post Writer\n\n## Overview\n\nDrafts long-form LinkedIn posts using 16 hook formulas that were reverse-engineered from posts that outperformed their authors' baselines in 2025-2026, each with a reference engagement number. Instead of asking \"what should I write\", the workflow asks \"what should this post earn\" (comments, reposts, likes, or saves), shortlists 2-3 matching formulas, fills the chosen skeleton with the user's voice, then scrubs the draft for AI tells before it ships.\n\nThis is the flagship skill from [sergebulaev\u002Flinkedin-skills](https:\u002F\u002Fgithub.com\u002Fsergebulaev\u002Flinkedin-skills), a 10-skill LinkedIn bundle (writer, humanizer, pre-publish audit, comment drafter, reply handler, hook extractor, content planner, profile optimizer, engager analytics, thread monitor) installable as a Claude Code or Codex plugin. This standalone version covers the drafting workflow; scheduling and publishing automation live in the full bundle.\n\n## When to Use This Skill\n\n- Use when the user says \"write me a LinkedIn post about X\"\n- Use when the user has a topic and a rough angle but needs a hook and structure\n- Use when the user wants to pick from proven post formats instead of improvising\n- Use when a draft exists but the hook is weak and needs a formula-based rebuild\n- Not for replying to comments or optimizing profiles; this skill only drafts posts\n\n## How It Works\n\n### Step 1: Gather inputs\n\nCollect: topic, angle, target audience (founders, operators, marketers), desired length (short 300-500, medium 900-1,300, or long 1,500-1,900 characters), and any raw material the user already has (numbers, anecdotes, names).\n\n### Step 2: Pick the formula by engagement goal first\n\nAsk (or infer) what the post should earn, then shortlist:\n\n| Goal | Earned by | Formulas |\n|---|---|---|\n| Comments | questions, contrarian takes, vulnerability | F4 Time-Anchor Confession, F10 Contrarian + Receipts, F12 Permission Slip, F9 Curiosity-Gap |\n| Reposts | quotable maxims, tributes, \"X isn't Y\" distinctions | F14 Named Gratitude, F2 R.I.P. Obituary, F8 Paid-vs-Free Reversal |\n| Likes | emotional stories, celebrations, status-strip | F11 Emotional Cold-Open, F13 Bait-and-Switch Reversal, F16 Status-Strip Humility |\n| Saves | simplifications, exact how-to, frameworks | F15 Explain-to-Kids, F7 Odd-Precision Money Ledger, F8 Paid-vs-Free Reversal |\n\nThe full set of 16, with reference engagement:\n\n| Code | Formula | Reference | Best for |\n|---|---|---|---|\n| F1 | Platform Risk Anaphora | 4,240 eng | Category and platform-risk arguments |\n| F2 | R.I.P. Obituary | 3,822 eng | Era-ending claims, industry pivots |\n| F3 | Year-over-Year Pivot | 494 eng, 3.74x baseline | Identity shifts, founder reflection |\n| F4 | Time-Anchor Confession | 1,519+ eng | Vulnerability, voice reset |\n| F5 | Self-Proving Meta | 1,082 eng, 435 comments | Commitments and tests in public |\n| F6 | Comment-Gate Lead Magnet | 717-3,008 eng | List building (max once a month) |\n| F7 | Odd-Precision Money Ledger | 1,755 eng, 9.4x baseline | Build logs, cost breakdowns |\n| F8 | Paid-vs-Free Reversal | 550 eng, 19.64x baseline | Framework giveaways |\n| F9 | Curiosity-Gap Teaser | 306 eng, 4.25x baseline | Surprise and behind-the-scenes stories |\n| F10 | Contrarian + Historical Receipts | 3,083 eng | Sacred-cow takes backed by history |\n| F11 | Emotional Cold-Open | high raw reach | Real stories with emotional stakes |\n| F12 | Permission Slip | comment-heavy | Encouragement to a discouraged audience |\n| F13 | Bait-and-Switch Reversal | high raw reach | Bad-news framing that turns into an upgrade |\n| F14 | Named Gratitude \u002F Tribute | repost-heavy | Thanking mentors, teams, departing colleagues |\n| F15 | Explain-to-Kids | save-heavy | Demystifying jargon into a reference post |\n| F16 | Status-Strip Humility | like-heavy | Senior voices trading prestige for warmth |\n\nImportant caveat: F1-F10 references are engagement counts or format multipliers against the author's own baseline; F11-F16 references are raw corpus reach, often inflated by a famous author or a reshare. The two groups measure different things, so never rank formulas across groups by number.\n\nThe full skeletons for all 16 formulas are bundled with this skill in [references\u002Fhook-formulas.md](references\u002Fhook-formulas.md), along with per-formula warnings and the \"Never do\" list.\n\n### Step 3: Draft the post\n\nRead the chosen formula's skeleton from the bundled [references\u002Fhook-formulas.md](references\u002Fhook-formulas.md) and fill it with the user's voice and material, respecting the 2026 formatting rules:\n\n- Hook lands in the first 210 characters (before the \"... see more\" fold)\n- 900-1,300 characters is the sweet spot for text posts\n- Double line-breaks between ideas, never walls of text\n- 0-2 hashtags, placed at the end\n- No external links in the body (put links in the first comment)\n- Prefer \"How I\" over \"How to\": first-person experience hooks outperform generic instruction 2-3x\n- Put one specific number in the first sentence ($873.47 beats $900; 40,000 beats \"a lot\")\n\n### Step 4: Scrub AI tells\n\nBefore showing the draft: strip em dashes, AI vocabulary (\"game-changer\", \"deep dive\", \"delve\"), rule-of-three lists without receipts, and generic openers like \"In today's fast-paced world\". Add human fingerprints: at least one specific number, one named entity, and one first-person concrete detail per 100 words. Vary sentence length aggressively (mix 3-word and 25-word sentences).\n\n### Step 5: Present the result\n\nShow the user: formula used, full draft, character count, and a suggested posting window (Tuesday to Thursday, 7:30-9:00 AM local time performs best for B2B audiences).\n\n## Examples\n\n### Example 1: Founder build-log (F7 Odd-Precision Money Ledger)\n\n```text\nUser:  write a post about what my bootstrapped SaaS actually costs to run\nAgent: Goal check: this reads like a saves play (people screenshot cost\n       breakdowns). Best fit is F7 Odd-Precision Money Ledger (9.4x baseline).\n       Draft hook:\n\n       \"My SaaS costs $412.83 a month to run. Here is every line item.\"\n\n       Then the ledger: hosting $94.20, email $35.00, monitoring $18.63...\n       exact numbers only, totals that actually add up, one lesson at the end.\n```\n\n### Example 2: Goal-first selection\n\n```text\nUser:  I want a post that gets real comments, topic: why I stopped doing demos\nAgent: Comment-earners are F4 Confession, F10 Contrarian, F12 Permission Slip.\n       For \"I stopped doing X\" the strongest is F10 Contrarian + Receipts:\n       open with the unpopular claim, back it with 2 historical parallels,\n       close with a question that forces side-picking. Reference: 3,083 eng.\n```\n\n## Best Practices\n\n- ✅ Pick the formula by engagement goal first, topic second\n- ✅ Lead with a real failure or a specific number in the first 3 lines\n- ✅ Include one moment of genuine vulnerability or concrete stakes; pure insight posts underperform in 2026\n- ❌ Don't blend two hook formulas in one post; it dilutes both\n- ❌ Don't use F5 Self-Proving Meta unless the user will actually keep the promise\n- ❌ Don't pair F7 Money Ledger with rounded or invented numbers; readers notice\n- ❌ Don't open with an all-caps line (\"THIS CHANGED EVERYTHING\")\n- ❌ Don't frame LinkedIn as inferior inside a LinkedIn post\n\n## Limitations\n\n- Reference engagement numbers describe the 2025-2026 corpus the formulas were extracted from; they are priors, not guarantees, and LinkedIn's ranking changes over time.\n- The skill drafts text posts; it does not generate images, carousels, or video scripts.\n- This standalone version does not schedule or publish. Scheduling, comment drafting, reply handling, and engagement analytics require the full bundle from the source repo.\n- Voice quality depends on the raw material the user provides; a formula cannot invent authentic anecdotes, and the skill should ask for real details rather than fabricate them.\n\n## Common Pitfalls\n\n- **Problem:** The draft sounds like every other AI-written LinkedIn post.\n  **Solution:** Run Step 4 ruthlessly. Cut em dashes, cut \"game-changer\" vocabulary, and force one concrete first-person detail per 100 words.\n- **Problem:** The hook is buried in paragraph two.\n  **Solution:** The first 210 characters must carry the hook; everything before the fold decides the expand rate.\n- **Problem:** Comparing F11's raw reach to F8's 19.64x multiplier and picking F11 \"because the number is bigger\".\n  **Solution:** The columns measure different things. Match formula to goal and topic, not to the largest number.\n- **Problem:** Post gets reach but zero comments.\n  **Solution:** The formula was picked for the wrong goal. Comment-earners end with a question or a side-picking claim, not a summary.\n\n## Related Skills\n\n- `@linkedin-content-generator` - broader LinkedIn content suite (carousels, newsletters, calendars)\n- `@linkedin-profile-optimizer` - profile and authority optimization rather than post drafting\n- `@social-post-writer-seo` - multi-platform social copy when LinkedIn is not the only target\n\n## Additional Resources\n\n- [Source repo with all 16 formula skeletons and worked examples](https:\u002F\u002Fgithub.com\u002Fsergebulaev\u002Flinkedin-skills)\n- [Full 10-skill bundle install (Claude Code \u002F Codex plugin)](https:\u002F\u002Fgithub.com\u002Fsergebulaev\u002Flinkedin-skills#install)\n","# LinkedIn Post Writer\n\n## Overview\n\nDrafts long-form LinkedIn posts using 16 hook formulas that were reverse-engineered from posts that outperformed their authors' baselines in 2025-2026, each with a reference engagement number. Instead of asking \"what should I write\", the workflow asks \"what should this post earn\" (comments, reposts, likes, or saves), shortlists 2-3 matching formulas, fills the chosen skeleton with the user's voice, then scrubs the draft for AI tells before it ships.\n\nThis is the flagship skill from [sergebulaev\u002Flinkedin-skills](https:\u002F\u002Fgithub.com\u002Fsergebulaev\u002Flinkedin-skills), a 10-skill LinkedIn bundle (writer, humanizer, pre-publish audit, comment drafter, reply handler, hook extractor, content planner, profile optimizer, engager analytics, thread monitor) installable as a Claude Code or Codex plugin. This standalone version covers the drafting workflow; scheduling and publishing automation live in the full bundle.\n\n## When to Use This Skill\n\n- Use when the user says \"write me a LinkedIn post about X\"\n- Use when the user has a topic and a rough angle but needs a hook and structure\n- Use when the user wants to pick from proven post formats instead of improvising\n- Use when a draft exists but the hook is weak and needs a formula-based rebuild\n- Not for replying to comments or optimizing profiles; this skill only drafts posts\n\n## How It Works\n\n### Step 1: Gather inputs\n\nCollect: topic, angle, target audience (founders, operators, marketers), desired length (short 300-500, medium 900-1,300, or long 1,500-1,900 characters), and any raw material the user already has (numbers, anecdotes, names).\n\n### Step 2: Pick the formula by engagement goal first\n\nAsk (or infer) what the post should earn, then shortlist:\n\n| Goal | Earned by | Formulas |\n|---|---|---|\n| Comments | questions, contrarian takes, vulnerability | F4 Time-Anchor Confession, F10 Contrarian + Receipts, F12 Permission Slip, F9 Curiosity-Gap |\n| Reposts | quotable maxims, tributes, \"X isn't Y\" distinctions | F14 Named Gratitude, F2 R.I.P. Obituary, F8 Paid-vs-Free Reversal |\n| Likes | emotional stories, celebrations, status-strip | F11 Emotional Cold-Open, F13 Bait-and-Switch Reversal, F16 Status-Strip Humility |\n| Saves | simplifications, exact how-to, frameworks | F15 Explain-to-Kids, F7 Odd-Precision Money Ledger, F8 Paid-vs-Free Reversal |\n\nThe full set of 16, with reference engagement:\n\n| Code | Formula | Reference | Best for |\n|---|---|---|---|\n| F1 | Platform Risk Anaphora | 4,240 eng | Category and platform-risk arguments |\n| F2 | R.I.P. Obituary | 3,822 eng | Era-ending claims, industry pivots |\n| F3 | Year-over-Year Pivot | 494 eng, 3.74x baseline | Identity shifts, founder reflection |\n| F4 | Time-Anchor Confession | 1,519+ eng | Vulnerability, voice reset |\n| F5 | Self-Proving Meta | 1,082 eng, 435 comments | Commitments and tests in public |\n| F6 | Comment-Gate Lead Magnet | 717-3,008 eng | List building (max once a month) |\n| F7 | Odd-Precision Money Ledger | 1,755 eng, 9.4x baseline | Build logs, cost breakdowns |\n| F8 | Paid-vs-Free Reversal | 550 eng, 19.64x baseline | Framework giveaways |\n| F9 | Curiosity-Gap Teaser | 306 eng, 4.25x baseline | Surprise and behind-the-scenes stories |\n| F10 | Contrarian + Historical Receipts | 3,083 eng | Sacred-cow takes backed by history |\n| F11 | Emotional Cold-Open | high raw reach | Real stories with emotional stakes |\n| F12 | Permission Slip | comment-heavy | Encouragement to a discouraged audience |\n| F13 | Bait-and-Switch Reversal | high raw reach | Bad-news framing that turns into an upgrade |\n| F14 | Named Gratitude \u002F Tribute | repost-heavy | Thanking mentors, teams, departing colleagues |\n| F15 | Explain-to-Kids | save-heavy | Demystifying jargon into a reference post |\n| F16 | Status-Strip Humility | like-heavy | Senior voices trading prestige for warmth |\n\nImportant caveat: F1-F10 references are engagement counts or format multipliers against the author's own baseline; F11-F16 references are raw corpus reach, often inflated by a famous author or a reshare. The two groups measure different things, so never rank formulas across groups by number.\n\nThe full skeletons for all 16 formulas are bundled with this skill in [references\u002Fhook-formulas.md](references\u002Fhook-formulas.md), along with per-formula warnings and the \"Never do\" list.\n\n### Step 3: Draft the post\n\nRead the chosen formula's skeleton from the bundled [references\u002Fhook-formulas.md](references\u002Fhook-formulas.md) and fill it with the user's voice and material, respecting the 2026 formatting rules:\n\n- Hook lands in the first 210 characters (before the \"... see more\" fold)\n- 900-1,300 characters is the sweet spot for text posts\n- Double line-breaks between ideas, never walls of text\n- 0-2 hashtags, placed at the end\n- No external links in the body (put links in the first comment)\n- Prefer \"How I\" over \"How to\": first-person experience hooks outperform generic instruction 2-3x\n- Put one specific number in the first sentence ($873.47 beats $900; 40,000 beats \"a lot\")\n\n### Step 4: Scrub AI tells\n\nBefore showing the draft: strip em dashes, AI vocabulary (\"game-changer\", \"deep dive\", \"delve\"), rule-of-three lists without receipts, and generic openers like \"In today's fast-paced world\". Add human fingerprints: at least one specific number, one named entity, and one first-person concrete detail per 100 words. Vary sentence length aggressively (mix 3-word and 25-word sentences).\n\n### Step 5: Present the result\n\nShow the user: formula used, full draft, character count, and a suggested posting window (Tuesday to Thursday, 7:30-9:00 AM local time performs best for B2B audiences).\n\n## Examples\n\n### Example 1: Founder build-log (F7 Odd-Precision Money Ledger)\n\n```text\nUser:  write a post about what my bootstrapped SaaS actually costs to run\nAgent: Goal check: this reads like a saves play (people screenshot cost\n       breakdowns). Best fit is F7 Odd-Precision Money Ledger (9.4x baseline).\n       Draft hook:\n\n       \"My SaaS costs $412.83 a month to run. Here is every line item.\"\n\n       Then the ledger: hosting $94.20, email $35.00, monitoring $18.63...\n       exact numbers only, totals that actually add up, one lesson at the end.\n```\n\n### Example 2: Goal-first selection\n\n```text\nUser:  I want a post that gets real comments, topic: why I stopped doing demos\nAgent: Comment-earners are F4 Confession, F10 Contrarian, F12 Permission Slip.\n       For \"I stopped doing X\" the strongest is F10 Contrarian + Receipts:\n       open with the unpopular claim, back it with 2 historical parallels,\n       close with a question that forces side-picking. Reference: 3,083 eng.\n```\n\n## Best Practices\n\n- ✅ Pick the formula by engagement goal first, topic second\n- ✅ Lead with a real failure or a specific number in the first 3 lines\n- ✅ Include one moment of genuine vulnerability or concrete stakes; pure insight posts underperform in 2026\n- ❌ Don't blend two hook formulas in one post; it dilutes both\n- ❌ Don't use F5 Self-Proving Meta unless the user will actually keep the promise\n- ❌ Don't pair F7 Money Ledger with rounded or invented numbers; readers notice\n- ❌ Don't open with an all-caps line (\"THIS CHANGED EVERYTHING\")\n- ❌ Don't frame LinkedIn as inferior inside a LinkedIn post\n\n## Limitations\n\n- Reference engagement numbers describe the 2025-2026 corpus the formulas were extracted from; they are priors, not guarantees, and LinkedIn's ranking changes over time.\n- The skill drafts text posts; it does not generate images, carousels, or video scripts.\n- This standalone version does not schedule or publish. Scheduling, comment drafting, reply handling, and engagement analytics require the full bundle from the source repo.\n- Voice quality depends on the raw material the user provides; a formula cannot invent authentic anecdotes, and the skill should ask for real details rather than fabricate them.\n\n## Common Pitfalls\n\n- **Problem:** The draft sounds like every other AI-written LinkedIn post.\n  **Solution:** Run Step 4 ruthlessly. Cut em dashes, cut \"game-changer\" vocabulary, and force one concrete first-person detail per 100 words.\n- **Problem:** The hook is buried in paragraph two.\n  **Solution:** The first 210 characters must carry the hook; everything before the fold decides the expand rate.\n- **Problem:** Comparing F11's raw reach to F8's 19.64x multiplier and picking F11 \"because the number is bigger\".\n  **Solution:** The columns measure different things. Match formula to goal and topic, not to the largest number.\n- **Problem:** Post gets reach but zero comments.\n  **Solution:** The formula was picked for the wrong goal. Comment-earners end with a question or a side-picking claim, not a summary.\n\n## Related Skills\n\n- `@linkedin-content-generator` - broader LinkedIn content suite (carousels, newsletters, calendars)\n- `@linkedin-profile-optimizer` - profile and authority optimization rather than post drafting\n- `@social-post-writer-seo` - multi-platform social copy when LinkedIn is not the only target\n\n## Additional Resources\n\n- [Source repo with all 16 formula skeletons and worked examples](https:\u002F\u002Fgithub.com\u002Fsergebulaev\u002Flinkedin-skills)\n- [Full 10-skill bundle install (Claude Code \u002F Codex plugin)](https:\u002F\u002Fgithub.com\u002Fsergebulaev\u002Flinkedin-skills#install)\n",{"name":5,"risk":24,"tags":25,"tools":32,"author":37,"source":38,"license":15,"category":39,"date_added":40,"description":7,"source_repo":41,"source_type":38,"license_source":42},"none",[26,27,28,29,30,31],"linkedin","copywriting","hooks","social-media","personal-brand","content-marketing",[33,34,35,36],"claude","codex","cursor","gemini","sergebulaev","community","marketing","2026-07-06","sergebulaev\u002Flinkedin-skills","https:\u002F\u002Fgithub.com\u002Fsergebulaev\u002Flinkedin-skills\u002Fblob\u002Fmain\u002FLICENSE","main","d69096e239f2a89aabc2cd078c47664a9d3b1e11","03-逆向工程\u002Flinkedin-post-writer",3,"https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts","https:\u002F\u002Fgithub.com\u002Flza6","个人vx：Tf00798\r\n个人✈：@TFGY999","2026-10-08 14:29:22",{"source":8,"skillName":5,"commands":52,"prompt":62,"zipAvailable":63},[53,56,59],{"tool":54,"command":55},"npx","npx skills add lza6\u002FArmor-piercing-system-prompts --skill linkedin-post-writer",{"tool":57,"command":58},"bunx","bunx skills add lza6\u002FArmor-piercing-system-prompts --skill linkedin-post-writer",{"tool":60,"command":61},"pnpm","pnpm dlx skills add lza6\u002FArmor-piercing-system-prompts --skill linkedin-post-writer","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F03-逆向工程\u002Flinkedin-post-writer\u002FSKILL.md",true,[65],{"path":66,"resourceType":67,"resourceTypeDesc":68,"sizeBytes":69,"sourceHtmlUrl":70},"references\u002Fhook-formulas.md","REFERENCE","参考文档",16518,"https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F03-逆向工程\u002Flinkedin-post-writer\u002Freferences\u002Fhook-formulas.md",[72,80,85,92,99,106],{"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":79},"01M7FFG485KY83TD6HSC4YPCMC","obsidian-clipper-template-creator","Guide for creating templates for the Obsidian Web Clipper. Use when you want to create a new clipping template, understand available variables, or format clipped content.","https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F07-后端与架构\u002Fobsidian-clipper-template-creator\u002FSKILL.md",[],[],"2026-11-16 10:05:34",{"skillNo":81,"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":82,"categories":83,"keywords":84,"publishedAt":79},"01M7FFG0T6AZ0STEJPSB3CX84K","https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F07-后端与架构\u002Fobsidian-clipper-template-creator-antigravity-awesome-skills-main\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":79},"01M7FFFY0QEM14SKWPDYGMXM2P","python-api","Programmatic Object-Detection-Metrics API guidance for BoundingBox, BoundingBoxes, Evaluator, enums, coordinate conversion, AP\u002FmAP semantics, and source-style import diagnostics.","https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F07-后端与架构\u002Fobject-detection-metrics\u002Fsub-skills\u002Fpython-api\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":79},"01M7FFFVZQZ2GJ0C0TGP7JHD20","file-evaluation","Folder-based PASCAL VOC AP\u002FmAP evaluation from ground-truth and detection text files.","https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F07-后端与架构\u002Fobject-detection-metrics\u002Fsub-skills\u002Ffile-evaluation\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":79},"01M7FFFSFNYSE77SJ6PE1CK2DA","object-detection-metrics","Guides legacy Object-Detection-Metrics PASCAL VOC AP\u002FmAP evaluation from detection text folders and direct Python API classes.","https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F07-后端与架构\u002Fobject-detection-metrics\u002FSKILL.md",[],[],{"skillNo":107,"name":108,"nameZh":6,"description":109,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":110,"categories":111,"keywords":112,"publishedAt":79},"01M7FFFP0GCK1RVXBCPQ8APBMT","nx-workspace-patterns","Configure and optimize Nx monorepo workspaces. Use when setting up Nx, configuring project boundaries, optimizing build caching, or implementing affected commands.","https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F07-后端与架构\u002Fnx-workspace-patterns\u002FSKILL.md",[],[]]