[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M77HCKBBPQCGRVT0E8DN2A5W":3,"skill-same:01M77HCKBBPQCGRVT0E8DN2A5W":47},{"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},"01M77HCKBBPQCGRVT0E8DN2A5W","disambiguation-score",null,"One repeatable pass that keeps fak's growing namespace CRYSTAL-CLEAR - each similar-sounding concept (cache \u002F vCache \u002F KV cache \u002F cachemeta \u002F the provider prompt-cache; guard vs gate; the two witnesses) given one canonical name, a written definition, and an explicit line drawn against the siblings it is confused with. Runs the concept-disambiguation scorecard (tools\u002Fconcept_disambiguation_scorecard.py) over a data dir of confusable-concept rows cross-checked against the tree (the grounding token must appear in the production corpus; the glossary anchor must exist. Use when this named workflow matches the task.","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\u002Fdisambiguation-score\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: disambiguation-score\ndescription: One repeatable pass that keeps fak's growing namespace CRYSTAL-CLEAR - each similar-sounding concept (cache \u002F vCache \u002F KV cache \u002F cachemeta \u002F the provider prompt-cache; guard vs gate; the two witnesses) given one canonical name, a written definition, and an explicit line drawn against the siblings it is confused with. Runs the concept-disambiguation scorecard (tools\u002Fconcept_disambiguation_scorecard.py) over a data dir of confusable-concept rows cross-checked against the tree (the grounding token must appear in the production corpus; the glossary anchor must exist. Use when this named workflow matches the task.\n---\n\n# disambiguation-score - the crystal-clarity \u002F naming pass\n\n> An instance of the generic **[scorecard](..\u002Fscorecard\u002FSKILL.md)** doctrine. Read that\n> for the five laws and the RSI loop; this file is the per-surface specialization.\n\n## Why this scorecard exists\n\nfak has grown a large vocabulary, and several roots are badly overloaded. The word\n\"cache\" alone names at least a dozen distinct things (KV cache, vCache, cachemeta, the\nprovider prompt-cache, ViewCache, enginecache, RadixKV, ...); \"guard\" and \"gate\" blur;\n\"witness\" means two unrelated ideas. As the system grows, a reader cannot tell the\nconcepts apart - and a name a reader cannot pin is a name they will misuse.\n\nThe crystal-clarity law, in one line: **every distinct concept gets one canonical\nname, a written definition, and an explicit line drawn against the siblings it is\nconfused with - and that distinction lives in a doc that exists, not tribal memory.**\n\nThis is orthogonal to its two easily-confused siblings (an irony the glossary notes):\n`conflation-score` keeps every reported NUMBER labeled by provenance (WITNESSED vs\nOBSERVED); `product-score` asks whether a person can USE a concept. This one asks\nwhether the NAME is unambiguous.\n\n## The KPIs (what it grades)\n\n- **well_formed (HARD)** - required fields present, enums in the closed vocabulary,\n  unique id, family declared.\n- **canonical_unique (HARD)** - no two concepts share THE canonical name. A real\n  collision is fixed by a RENAME, never a note.\n- **defined (HARD)** - every concept carries one distinguishing definition sentence.\n- **disambiguated (HARD)** - the heart: a concept in a family with >= 1 positioned\n  sibling must carry a `distinction` line AND a `distinct_from` that resolves to a real\n  catalog id. A confusable concept that never says what it is NOT is the core debt.\n- **grounded (HARD)** - the grounding token must appear in the production corpus by\n  STRICT identity (a fabricated `policyloaded` that merely contains `policy` is refused).\n- **anchored (HARD)** - a concept claiming `crystal` clarity must have its distinction\n  written in a glossary_anchor that exists; any non-empty anchor must resolve on disk.\n- **clarity_consistent (HARD)** - the declared verdict must match the evidence\n  (crystal \u002F defined \u002F drifting \u002F colliding \u002F undocumented). Calling an unanchored\n  concept `crystal` is the overclaim this catches.\n- **kind_grounding \u002F hierarchy (SOFT)** - advisory: kind agrees with grounding; an\n  optional `parent` resolves and does not cycle.\n\nPlus **coverage**: for each watched family the scorecard DISCOVERS the confusable\ntokens in the tree (a token counts only when it spans >= `min_files` production files,\nor is a package\u002Fdir name, or a doc heading), and `coverage_debt` is the count not yet\npositioned. This is the ungameable engine - you cannot shrink the universe by editing\ndata, only by disambiguating the real concept.\n\n## The pass (the shared five-step loop)\n\n1. **Run it** - `python tools\u002Fconcept_disambiguation_scorecard.py` (work-list),\n   `--json` (payload), `--critical` (worst-first), `--gaps` (the coverage backlog by\n   family), `--compare baseline.json` (prove the drop).\n2. **Retire disambiguation-debt worst-first** - fix the heaviest KPI by changing\n   REALITY: rename a true canonical collision, write a missing definition, draw the\n   `distinction` + point `distinct_from` at a real sibling id, replace a fabricated\n   grounding with a real token. Close a real coverage gap atomically with `fak concept\n   position --id ID --canonical NAME --family FAMILY --definition TEXT --distinction\n   TEXT --kind KIND --grounding TOKEN --grounding-kind KIND --glossary\n   docs\u002Ffak\u002Fconcept-glossary.md --distinct-from SIBLING_ID`; classify a genuine\n   incidental\u002Ffalse-positive discovery with `fak concept classify --family FAMILY\n   --token TOKEN --category CATEGORY --reason TEXT`. Preview either mutation with\n   `--dry-run --json`. Never hand-edit a row, family classification, glossary anchor,\n   and generated README as separate operations.\n3. **Weigh the SOFT signals** - fix the cheap real ones (kind\u002Fgrounding, a dangling\n   parent); do not chase them to zero.\n4. **Re-measure + prove** - `--compare` prints the debt delta; the positioned rows must\n   stay clean (0 clarity-debt) while coverage rises.\n5. **Commit exactly the files reported by the authoring verb** - verify with `--critical`\n   and regenerate\u002Fcheck the scorecard baseline when the measured metric changes. Run\n   `fak sync reconcile --apply`, use `fak commit --preview` followed by `fak commit --path` for\n   each reported path (never `git add -A`), and push via `fak sync push`:\n   ```bash\n   fak sync reconcile --apply\n   fak commit --preview -m \"docs(concept): disambiguate \u003Cconcept> (fak concept)\" --path \u003Cpaths>...\n   fak commit --path \u003Cpaths>... -m \"docs(concept): disambiguate \u003Cconcept> (fak concept)\"\n   fak sync push\n   ```\n   End the subject with the `(fak \u003Cleaf>)` trailer.\n\n## The anti-gaming rule (specific to this surface)\n\n**Disambiguate a concept by making the name + the written distinction real, never by\nweakening the cross-check.** A coverage gap is closed by ADDING an honest, grounded,\nanchored row - not by dropping the family root so the token stops being discovered, and\nnot by listing a `distinct_from` id that does not exist. A `crystal` verdict is earned\nby writing the distinction into the glossary - not by pointing the anchor at a doc that\nhappens to exist. The grounding cross-check is STRICT identity on purpose: if a real\nconcept's token genuinely is not in the production corpus, the honest fix is to rename\nthe concept toward the name the code actually uses, not to relax the match.\n\n## Adding a surface\n\nWhen a new overloaded root appears (a fresh `*-thing` family proliferating across the\ntree), add a family entry to `_meta.json` (`roots`, optional `ignore` inflections,\noptional `exclude` substrings, `min_files`); the scorecard then discovers its\nconfusable tokens and the coverage backlog grows until you position them. Keep the\nglossary (`docs\u002Ffak\u002Fconcept-glossary.md`) as the single anchor the `crystal` rows cite.\n\n## ASCII gotcha\n\nKeep the scorecard source + data + glossary ASCII-only (use ` - ` for a dash, straight\nquotes). The repo's provenance pre-commit hook crashes on non-cp1252 UTF-8 before its\nown escape fires.\n","# disambiguation-score - the crystal-clarity \u002F naming pass\n\n> An instance of the generic **[scorecard](..\u002Fscorecard\u002FSKILL.md)** doctrine. Read that\n> for the five laws and the RSI loop; this file is the per-surface specialization.\n\n## Why this scorecard exists\n\nfak has grown a large vocabulary, and several roots are badly overloaded. The word\n\"cache\" alone names at least a dozen distinct things (KV cache, vCache, cachemeta, the\nprovider prompt-cache, ViewCache, enginecache, RadixKV, ...); \"guard\" and \"gate\" blur;\n\"witness\" means two unrelated ideas. As the system grows, a reader cannot tell the\nconcepts apart - and a name a reader cannot pin is a name they will misuse.\n\nThe crystal-clarity law, in one line: **every distinct concept gets one canonical\nname, a written definition, and an explicit line drawn against the siblings it is\nconfused with - and that distinction lives in a doc that exists, not tribal memory.**\n\nThis is orthogonal to its two easily-confused siblings (an irony the glossary notes):\n`conflation-score` keeps every reported NUMBER labeled by provenance (WITNESSED vs\nOBSERVED); `product-score` asks whether a person can USE a concept. This one asks\nwhether the NAME is unambiguous.\n\n## The KPIs (what it grades)\n\n- **well_formed (HARD)** - required fields present, enums in the closed vocabulary,\n  unique id, family declared.\n- **canonical_unique (HARD)** - no two concepts share THE canonical name. A real\n  collision is fixed by a RENAME, never a note.\n- **defined (HARD)** - every concept carries one distinguishing definition sentence.\n- **disambiguated (HARD)** - the heart: a concept in a family with >= 1 positioned\n  sibling must carry a `distinction` line AND a `distinct_from` that resolves to a real\n  catalog id. A confusable concept that never says what it is NOT is the core debt.\n- **grounded (HARD)** - the grounding token must appear in the production corpus by\n  STRICT identity (a fabricated `policyloaded` that merely contains `policy` is refused).\n- **anchored (HARD)** - a concept claiming `crystal` clarity must have its distinction\n  written in a glossary_anchor that exists; any non-empty anchor must resolve on disk.\n- **clarity_consistent (HARD)** - the declared verdict must match the evidence\n  (crystal \u002F defined \u002F drifting \u002F colliding \u002F undocumented). Calling an unanchored\n  concept `crystal` is the overclaim this catches.\n- **kind_grounding \u002F hierarchy (SOFT)** - advisory: kind agrees with grounding; an\n  optional `parent` resolves and does not cycle.\n\nPlus **coverage**: for each watched family the scorecard DISCOVERS the confusable\ntokens in the tree (a token counts only when it spans >= `min_files` production files,\nor is a package\u002Fdir name, or a doc heading), and `coverage_debt` is the count not yet\npositioned. This is the ungameable engine - you cannot shrink the universe by editing\ndata, only by disambiguating the real concept.\n\n## The pass (the shared five-step loop)\n\n1. **Run it** - `python tools\u002Fconcept_disambiguation_scorecard.py` (work-list),\n   `--json` (payload), `--critical` (worst-first), `--gaps` (the coverage backlog by\n   family), `--compare baseline.json` (prove the drop).\n2. **Retire disambiguation-debt worst-first** - fix the heaviest KPI by changing\n   REALITY: rename a true canonical collision, write a missing definition, draw the\n   `distinction` + point `distinct_from` at a real sibling id, replace a fabricated\n   grounding with a real token. Close a real coverage gap atomically with `fak concept\n   position --id ID --canonical NAME --family FAMILY --definition TEXT --distinction\n   TEXT --kind KIND --grounding TOKEN --grounding-kind KIND --glossary\n   docs\u002Ffak\u002Fconcept-glossary.md --distinct-from SIBLING_ID`; classify a genuine\n   incidental\u002Ffalse-positive discovery with `fak concept classify --family FAMILY\n   --token TOKEN --category CATEGORY --reason TEXT`. Preview either mutation with\n   `--dry-run --json`. Never hand-edit a row, family classification, glossary anchor,\n   and generated README as separate operations.\n3. **Weigh the SOFT signals** - fix the cheap real ones (kind\u002Fgrounding, a dangling\n   parent); do not chase them to zero.\n4. **Re-measure + prove** - `--compare` prints the debt delta; the positioned rows must\n   stay clean (0 clarity-debt) while coverage rises.\n5. **Commit exactly the files reported by the authoring verb** - verify with `--critical`\n   and regenerate\u002Fcheck the scorecard baseline when the measured metric changes. Run\n   `fak sync reconcile --apply`, use `fak commit --preview` followed by `fak commit --path` for\n   each reported path (never `git add -A`), and push via `fak sync push`:\n   ```bash\n   fak sync reconcile --apply\n   fak commit --preview -m \"docs(concept): disambiguate \u003Cconcept> (fak concept)\" --path \u003Cpaths>...\n   fak commit --path \u003Cpaths>... -m \"docs(concept): disambiguate \u003Cconcept> (fak concept)\"\n   fak sync push\n   ```\n   End the subject with the `(fak \u003Cleaf>)` trailer.\n\n## The anti-gaming rule (specific to this surface)\n\n**Disambiguate a concept by making the name + the written distinction real, never by\nweakening the cross-check.** A coverage gap is closed by ADDING an honest, grounded,\nanchored row - not by dropping the family root so the token stops being discovered, and\nnot by listing a `distinct_from` id that does not exist. A `crystal` verdict is earned\nby writing the distinction into the glossary - not by pointing the anchor at a doc that\nhappens to exist. The grounding cross-check is STRICT identity on purpose: if a real\nconcept's token genuinely is not in the production corpus, the honest fix is to rename\nthe concept toward the name the code actually uses, not to relax the match.\n\n## Adding a surface\n\nWhen a new overloaded root appears (a fresh `*-thing` family proliferating across the\ntree), add a family entry to `_meta.json` (`roots`, optional `ignore` inflections,\noptional `exclude` substrings, `min_files`); the scorecard then discovers its\nconfusable tokens and the coverage backlog grows until you position them. Keep the\nglossary (`docs\u002Ffak\u002Fconcept-glossary.md`) as the single anchor the `crystal` rows cite.\n\n## ASCII gotcha\n\nKeep the scorecard source + data + glossary ASCII-only (use ` - ` for a dash, straight\nquotes). The repo's provenance pre-commit hook crashes on non-cp1252 UTF-8 before its\nown escape fires.\n",{"name":5,"description":7},"main","f565b7b7db63e79649f3a02c08108132a86c5d05",".claude\u002Fskills\u002Fdisambiguation-score",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 disambiguation-score",{"tool":39,"command":40},"bunx","bunx skills add anthony-chaudhary\u002Ffak --skill disambiguation-score",{"tool":42,"command":43},"pnpm","pnpm dlx skills add anthony-chaudhary\u002Ffak --skill disambiguation-score","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fanthony-chaudhary\u002Ffak\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Fdisambiguation-score\u002FSKILL.md",true,[],[48,55,64,71,78,83],{"skillNo":49,"name":50,"nameZh":6,"description":51,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":52,"categories":53,"keywords":54,"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":56,"name":57,"nameZh":6,"description":58,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":59,"licenseFileUrl":60,"sourceHtmlUrl":61,"categories":62,"keywords":63,"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":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},"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":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},"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":79,"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":80,"categories":81,"keywords":82,"publishedAt":19},"01M77HR7XQ9X8F2CY9Z4F2ZEZ3","https:\u002F\u002Fgithub.com\u002Fanthony-chaudhary\u002Ffak\u002Fblob\u002Fmain\u002Finternal\u002Fctxplanlint\u002Ftestdata\u002Frepo\u002F.claude\u002Fskills\u002Fquality-report\u002FSKILL.md",[],[],{"skillNo":84,"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":85,"categories":86,"keywords":87,"publishedAt":19},"01M77HR5BVKCTR1WNJGRBSDNX7","https:\u002F\u002Fgithub.com\u002Fanthony-chaudhary\u002Ffak\u002Fblob\u002Fmain\u002Finternal\u002Fctxplanlint\u002Ftestdata\u002Frepo\u002F.claude\u002Fskills\u002Fctx-overlay\u002FSKILL.md",[],[]]