[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M77HKFQRSVM76T151WHAX7GD":3,"skill-same:01M77HKFQRSVM76T151WHAX7GD":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":24,"commitSha":25,"skillDirectory":26,"forksCount":27,"repositoryHtmlUrl":28,"repositoryHomepageUrl":29,"ownerHtmlUrl":30,"ownerBlogUrl":31,"ownerDescription":6,"updatedAt":32,"install":33,"resources":46},"01M77HKFQRSVM76T151WHAX7GD","skill-overlap",null,"Flag content-redundant SKILL.md pairs as merge candidates — pairwise body cosine similarity over the skill pack, sorted highest-first. Use when the pack feels bloated or two skills seem to overlap, to find \"skills A and B are N% token-similar — consider merging\" candidates before a skill-lifecycle archive pass. Proposal only — never merges, edits, or deletes a skill.","anthony-chaudhary\u002Ffak","anthony-chaudhary","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F18080164?v=4","01M77GSKCAEKV3JS07J40B94DY","Anthony Chaudhary","01M77GSKD26Z7F4FQQD4VA30VX",48,"Apache-2.0","https:\u002F\u002Fgithub.com\u002Fanthony-chaudhary\u002Ffak\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Fskill-overlap\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: skill-overlap\ndescription: Flag content-redundant SKILL.md pairs as merge candidates — pairwise body cosine similarity over the skill pack, sorted highest-first. Use when the pack feels bloated or two skills seem to overlap, to find \"skills A and B are N% token-similar — consider merging\" candidates before a skill-lifecycle archive pass. Proposal only — never merges, edits, or deletes a skill.\n---\n\n# \u002Fskill-overlap — flag content-redundant SKILL.md pairs (never merge)\n\nThe one context-cost technique from the Comet\u002FPerplexity writeup that fak did\n*not* already cover (#3930): **skill-to-skill content redundancy**.\n[`skill-lifecycle`](..\u002Fskill-lifecycle\u002FSKILL.md) archives *dead* skills and\n[`skill-score`](..\u002Fskill-score\u002FSKILL.md) audits over-budget ones — neither measures\nwhether two *live* skills say the same thing. With 55+ `SKILL.md` files (many\n`*-score` scorecards), that overlap is where the pack quietly bloats.\n\nThis skill measures it and stops. **Max action is to PRINT candidates** for a\nhuman to judge — like `skill-lifecycle`'s dry-run archive verdicts, it proposes,\nit never merges. Deciding two skills are genuinely one is a semantic call the\ndetector deliberately does not make; there is no `--apply`.\n\n## The witnessed helper\n\n`skill_overlap.py` runs a pairwise token-similarity primitive over every\n`.claude\u002Fskills\u002F*\u002FSKILL.md` **body** and emits the pairs above a threshold,\nsorted by similarity:\n\n```\npython .claude\u002Fskills\u002Fskill-overlap\u002Fskill_overlap.py [--threshold T] [--top N] [--json]\n```\n\n- **Front-matter is stripped first** — the shared `name:`\u002F`description:` YAML\n  skeleton is structural, not redundant, so it must not inflate the score.\n- **Similarity is body cosine over token frequency** with a small function-word\n  stoplist — \"skills A and B are N% token-similar\" in the issue's own words. Same\n  posture as `fak dup` \u002F `fak traj` (block- and query-level near-dup detection),\n  self-contained so the witness runs with no built `fak` binary.\n- **Default threshold 0.5**; drop to `--threshold 0.4` to see the long tail.\n- **`shared_top`** names the highest-weight tokens both bodies carry — the *why*\n  behind each score, so a human can judge the merge without re-reading both.\n\nExit code is always 0: this is advisory, and \"no candidates\" is a clean answer.\n\n## How to read a candidate\n\nA high score means *lexical* overlap, not that a merge is correct. Two `*-score`\nscorecards may share vocabulary (`debt`, `scorecard`, `commit`) yet tend\ngenuinely different surfaces. Before proposing a merge:\n\n1. Read both `SKILL.md` bodies. Do they tend the *same* surface, or just share\n   the scorecard idiom?\n2. If genuinely redundant → open an issue proposing the merge, or route the\n   weaker one through [`skill-lifecycle`](..\u002Fskill-lifecycle\u002FSKILL.md) to archive\n   (reversible), never a raw delete.\n3. If distinct-but-similar → the overlap is a *discoverability* smell; sharpen\n   each `description:`'s \"Use when…\" trigger via [`skill-score`](..\u002Fskill-score\u002FSKILL.md)\n   so the two stop colliding in recall.\n\n## Witness\n\n`python .claude\u002Fskills\u002Fskill-overlap\u002Fskill_overlap_test.py` — a fixture skill\npack with one deliberately-overlapping pair asserts that pair is surfaced above\nthe threshold while two unrelated skills are not, plus the front-matter-stripped,\nproposal-only, deterministic, and archived-skip invariants. This is the skill's\nproof-of-correctness; run it after any change to the detector.\n","# \u002Fskill-overlap — flag content-redundant SKILL.md pairs (never merge)\n\nThe one context-cost technique from the Comet\u002FPerplexity writeup that fak did\n*not* already cover (#3930): **skill-to-skill content redundancy**.\n[`skill-lifecycle`](..\u002Fskill-lifecycle\u002FSKILL.md) archives *dead* skills and\n[`skill-score`](..\u002Fskill-score\u002FSKILL.md) audits over-budget ones — neither measures\nwhether two *live* skills say the same thing. With 55+ `SKILL.md` files (many\n`*-score` scorecards), that overlap is where the pack quietly bloats.\n\nThis skill measures it and stops. **Max action is to PRINT candidates** for a\nhuman to judge — like `skill-lifecycle`'s dry-run archive verdicts, it proposes,\nit never merges. Deciding two skills are genuinely one is a semantic call the\ndetector deliberately does not make; there is no `--apply`.\n\n## The witnessed helper\n\n`skill_overlap.py` runs a pairwise token-similarity primitive over every\n`.claude\u002Fskills\u002F*\u002FSKILL.md` **body** and emits the pairs above a threshold,\nsorted by similarity:\n\n```\npython .claude\u002Fskills\u002Fskill-overlap\u002Fskill_overlap.py [--threshold T] [--top N] [--json]\n```\n\n- **Front-matter is stripped first** — the shared `name:`\u002F`description:` YAML\n  skeleton is structural, not redundant, so it must not inflate the score.\n- **Similarity is body cosine over token frequency** with a small function-word\n  stoplist — \"skills A and B are N% token-similar\" in the issue's own words. Same\n  posture as `fak dup` \u002F `fak traj` (block- and query-level near-dup detection),\n  self-contained so the witness runs with no built `fak` binary.\n- **Default threshold 0.5**; drop to `--threshold 0.4` to see the long tail.\n- **`shared_top`** names the highest-weight tokens both bodies carry — the *why*\n  behind each score, so a human can judge the merge without re-reading both.\n\nExit code is always 0: this is advisory, and \"no candidates\" is a clean answer.\n\n## How to read a candidate\n\nA high score means *lexical* overlap, not that a merge is correct. Two `*-score`\nscorecards may share vocabulary (`debt`, `scorecard`, `commit`) yet tend\ngenuinely different surfaces. Before proposing a merge:\n\n1. Read both `SKILL.md` bodies. Do they tend the *same* surface, or just share\n   the scorecard idiom?\n2. If genuinely redundant → open an issue proposing the merge, or route the\n   weaker one through [`skill-lifecycle`](..\u002Fskill-lifecycle\u002FSKILL.md) to archive\n   (reversible), never a raw delete.\n3. If distinct-but-similar → the overlap is a *discoverability* smell; sharpen\n   each `description:`'s \"Use when…\" trigger via [`skill-score`](..\u002Fskill-score\u002FSKILL.md)\n   so the two stop colliding in recall.\n\n## Witness\n\n`python .claude\u002Fskills\u002Fskill-overlap\u002Fskill_overlap_test.py` — a fixture skill\npack with one deliberately-overlapping pair asserts that pair is surfaced above\nthe threshold while two unrelated skills are not, plus the front-matter-stripped,\nproposal-only, deterministic, and archived-skip invariants. This is the skill's\nproof-of-correctness; run it after any change to the detector.\n",{"name":5,"description":7},"main","f565b7b7db63e79649f3a02c08108132a86c5d05",".claude\u002Fskills\u002Fskill-overlap",16,"https:\u002F\u002Fgithub.com\u002Fanthony-chaudhary\u002Ffak","https:\u002F\u002Fanthony-chaudhary.github.io\u002Ffak\u002Fshowcase.html","https:\u002F\u002Fgithub.com\u002Fanthony-chaudhary","https:\u002F\u002Flinkedin.com\u002Fin\u002Fanthonychaudhary","2026-11-15 03:06:00",{"source":8,"skillName":5,"commands":34,"prompt":44,"zipAvailable":45},[35,38,41],{"tool":36,"command":37},"npx","npx skills add anthony-chaudhary\u002Ffak --skill skill-overlap",{"tool":39,"command":40},"bunx","bunx skills add anthony-chaudhary\u002Ffak --skill skill-overlap",{"tool":42,"command":43},"pnpm","pnpm dlx skills add anthony-chaudhary\u002Ffak --skill skill-overlap","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fanthony-chaudhary\u002Ffak\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Fskill-overlap\u002FSKILL.md",true,[47,53],{"path":48,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":51,"sourceHtmlUrl":52},"skill_overlap_test.py","SCRIPT","脚本",7376,"https:\u002F\u002Fgithub.com\u002Fanthony-chaudhary\u002Ffak\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Fskill-overlap\u002Fskill_overlap_test.py",{"path":54,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":55,"sourceHtmlUrl":56},"skill_overlap.py",7751,"https:\u002F\u002Fgithub.com\u002Fanthony-chaudhary\u002Ffak\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Fskill-overlap\u002Fskill_overlap.py",[58,65,74,81,88,93],{"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},"01M78V4059KRP2T88YR6Z05MJQ","serve-receipt","On-demand research protocol + deterministic receipt for serving a Hugging Face model on a concrete GPU target — fan out research lanes (model facts\u002Ffiles, engine support matrix, serving recipes, KV\u002Fstate memory math), compute the tiered feasibility verdict with `fak serve-receipt` (never narrated math), and emit a witnessed launch receipt. Use when asked for an \"initial config\", \"serving receipt\", or \"how do I serve \u003Cmodel> on \u003CGPUs>\".","https:\u002F\u002Fgithub.com\u002Fanthony-chaudhary\u002Ffak\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Fserve-receipt\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":69,"licenseFileUrl":70,"sourceHtmlUrl":71,"categories":72,"keywords":73,"publishedAt":19},"01M77HRGKQV2CJ2K6ZFN4YQ32K","caveman","Ultra-compressed communication mode. Cuts output tokens 65% (measured) by speaking like caveman while keeping full technical accuracy. Supports intensity levels: lite, full (default), ultra, wenyan-lite, wenyan-full, wenyan-ultra. Use when user says \"caveman mode\", \"talk like caveman\", \"use caveman\", \"less tokens\", \"be brief\", or invokes \u002Fcaveman. Also auto-triggers when token efficiency is requested.","MIT","https:\u002F\u002Fgithub.com\u002Fanthony-chaudhary\u002Ffak\u002Fblob\u002Fmain\u002Finternal\u002Fsyspromptmmu\u002Fthird_party\u002Fcaveman\u002FLICENSE","https:\u002F\u002Fgithub.com\u002Fanthony-chaudhary\u002Ffak\u002Fblob\u002Fmain\u002Finternal\u002Fsyspromptmmu\u002Fthird_party\u002Fcaveman\u002FSKILL.md",[],[],{"skillNo":75,"name":76,"nameZh":6,"description":77,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":78,"categories":79,"keywords":80,"publishedAt":19},"01M77HRAY3Y3BE7APN5PVJF7NV","quality-report","Score the repo quality and emit a report card.","https:\u002F\u002Fgithub.com\u002Fanthony-chaudhary\u002Ffak\u002Fblob\u002Fmain\u002Finternal\u002Fctxplans\u002Ftestdata\u002Frepo\u002F.claude\u002Fskills\u002Fquality-report\u002FSKILL.md",[],[],{"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":15,"licenseFileUrl":6,"sourceHtmlUrl":85,"categories":86,"keywords":87,"publishedAt":19},"01M77HR9807KHAX13DG9PW2K2Q","ctx-overlay","Compact the context window and prune the memory store when a session grows too long.","https:\u002F\u002Fgithub.com\u002Fanthony-chaudhary\u002Ffak\u002Fblob\u002Fmain\u002Finternal\u002Fctxplans\u002Ftestdata\u002Frepo\u002F.claude\u002Fskills\u002Fctx-overlay\u002FSKILL.md",[],[],{"skillNo":89,"name":76,"nameZh":6,"description":77,"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},"01M77HR7XQ9X8F2CY9Z4F2ZEZ3","https:\u002F\u002Fgithub.com\u002Fanthony-chaudhary\u002Ffak\u002Fblob\u002Fmain\u002Finternal\u002Fctxplanlint\u002Ftestdata\u002Frepo\u002F.claude\u002Fskills\u002Fquality-report\u002FSKILL.md",[],[],{"skillNo":94,"name":83,"nameZh":6,"description":84,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":95,"categories":96,"keywords":97,"publishedAt":19},"01M77HR5BVKCTR1WNJGRBSDNX7","https:\u002F\u002Fgithub.com\u002Fanthony-chaudhary\u002Ffak\u002Fblob\u002Fmain\u002Finternal\u002Fctxplanlint\u002Ftestdata\u002Frepo\u002F.claude\u002Fskills\u002Fctx-overlay\u002FSKILL.md",[],[]]