[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M77HC6JMV7S2XXT8RWHSSNNR":3,"skill-same:01M77HC6JMV7S2XXT8RWHSSNNR":49},{"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":27,"commitSha":28,"skillDirectory":29,"forksCount":30,"repositoryHtmlUrl":31,"repositoryHomepageUrl":32,"ownerHtmlUrl":33,"ownerBlogUrl":34,"ownerDescription":6,"updatedAt":35,"install":36,"resources":48},"01M77HC6JMV7S2XXT8RWHSSNNR","debt-clean",null,"One repeatable, evidence-backed pass that retires a bounded batch of maturity debt worst-first across the system's dedicated debt lanes. Features rich queryability (--query, --health), cross-indexes related items (dual-repo companions, tests, runtime-proofs, benchmarks, inbound blast radius), targets high-carrying-cost or degraded hotspots, advances maturity with tests, integration, and benchmarks, re-measures with --compare to prove the denominator was level-set, and commits by explicit path with (fak \u003Cleaf>). Use when cleaning or retiring maturity debt across units of work.","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\u002Fdebt-clean\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: debt-clean\ndescription: One repeatable, evidence-backed pass that retires a bounded batch of maturity debt worst-first across the system's dedicated debt lanes. Features rich queryability (--query, --health), cross-indexes related items (dual-repo companions, tests, runtime-proofs, benchmarks, inbound blast radius), targets high-carrying-cost or degraded hotspots, advances maturity with tests, integration, and benchmarks, re-measures with --compare to prove the denominator was level-set, and commits by explicit path with (fak \u003Cleaf>). Use when cleaning or retiring maturity debt across units of work.\ndisable-model-invocation: false\nuser-invocable: true\nallowed-tools: Read, Bash, Write, Edit, Grep, Glob\nargument-hint: \"[--lane \u003Cname>] [--query \u003Ctext>] [--health healthy|degraded|critical] [--cross-index] [--target-repo both|fak|fak-private] [--top N]  (no args = baseline + clean top 1-3 debt hotspots)\"\n---\n\n# \u002Fdebt-clean — retire maturity debt worst-first in bounded batches\n\n> **What this does.** Every unit of work (feature, module, leaf) in the system carries a\n> dedicated debt lane scored on a continuous 0.0–10.0 maturity curve. When new work is added\n> at a partial maturity (e.g. 1\u002F10 stub), it immediately enters the production grade\n> denominator as debt with an accrued carrying cost.\n>\n> This skill executes a **bounded, disciplined cleaning pass**: query and baseline the debt lanes,\n> cross-index related things (dual-repo companions, dependents, proofs, benchmarks), run pre-flight\n> health diagnostics, pick 1–3 high-leverage hotspots (worst carrying cost, critical compounding interest,\n> or degraded health), fulfill the exact next action that advances the maturity curve, prove the debt dropped\n> and health upgraded with `--compare`, and commit by explicit path.\n\nThe shape: **query & baseline debt lanes → cross-index related things & pre-flight health → pick bounded batch (1–3 units) → execute next action\n(tests\u002Fintegration\u002Fbenchmarks\u002Fclean bloat) → verify package → prove debt drop & health upgrade with `--compare` → commit by\nexplicit path.**\n\n---\n\n## The Rule of Bounded Batches\n\nNever attempt a repository-wide sweep in one pass (hundreds of WIP lanes cannot and should\nnot be rushed in a single turn). Enforce strict scoping:\n\n1. **Max 1–3 units of work per batch**: Focus on 1–3 closely related leaves or a single\n   critical hotspot.\n2. **Shift-left proof**: Every maturity climb requires genuine disk evidence (passing\n   `*_test.go`, benchmarks, real runtime wiring), never synthetic markers or mock-only claims.\n3. **No comment gaming; excess comments is BAD debt**: Comments are NOT tracked as positive\n   debt retirement. Do not add formulaic \"Contract:\", \"Invariant:\", or \"Fail-closed:\" comment headers\n   or restate syntax. In fact, excess comments and comment bloat (>35% comment ratio or formulaic\n   keyword clutter) are penalized as BAD debt with interest rate penalties.\n4. **Denominator honesty**: Advancing maturity increases realized points without shrinking\n   the denominator, genuinely raising the production-grade percentage.\n5. **Multi-dimensional health upgrade**: Debt retirement must elevate the lane's health status\n   from `degraded` or `critical` toward `healthy`, resolving flagged issue tokens.\n\n---\n\n## Step 1 — Measure Baseline & Query Health\n\nRun `fak debt-lanes` to capture the current state, query candidate work, and audit system health:\n\n```bash\n# Capture full baseline:\nfak debt-lanes --json > baseline.json\nfak debt-lanes --top 5\n\n# Query lanes by keyword (matches lane name, unit of work, companion, drivers, or health issues):\nfak debt-lanes --query \u003Ckeyword> --top 5\n\n# Filter lanes by multi-dimensional health verdict (healthy, degraded, critical):\nfak debt-lanes --health degraded,critical --top 5\n\n# Cross-index related things, dual-repo companions, and blast radius:\nfak debt-lanes --cross-index --top 10\n```\n\n### Multi-Dimensional Lane Health Dimensions\n- **`healthy`**: Score >= 0.85, test passing, clean comment hygiene, integrated into production graph, documented\u002Fbenchmarked if core, low carrying interest.\n- **`degraded`**: Untested stubs (`missing_tests`), excess comment bloat (`comment_ratio > 35%` or formulaic keyword noise), disconnected wiring (`integrated=false`), unbenchmarked, or unproven in runtime.\n- **`critical`**: Compounding carrying cost (>25% interest rate) or untested core paths (`criticality=core && has_tests=false`) with high inbound dependents.\n\nNote the headline figures:\n- **Production Grade**: current letter and percentage (e.g. `Grade C, 75.4%`).\n- **Fleet Health**: healthy, degraded, and critical counts with average health score.\n- **Denominator Points**: total production baseline points.\n- **Total Debt**: total principal + carrying cost.\n- **Top Hotspots**: lanes carrying the highest carrying cost or highest maturity gap.\n\n---\n\n## Step 2 — Cross-Index Related Things & Select Target (1–3 Units)\n\nInspect the specific target's status, evidence, health findings, and cross-indexed artifacts:\n\n```bash\nfak debt-lanes --lane \u003Clane-name> --json\n```\n\n### Cross-Indexing Checklist for Target Lane\n1. **Dual-Repo Companion**:\n   - If working in `fak` (`internal\u002F\u003Clane>`), check `Related.CompanionUnitOfWork` for counterpart in `fak-private` (`platform\u002F\u003Clane>`).\n   - If working in `fak-private`, check counterpart in `fak` (`internal\u002F\u003Clane>` or `pkg\u002F\u003Clane>`).\n   - Run `go run .\u002Fcmd\u002Ffak-boundary explain \u003Cunit_of_work>` before making cross-repo edits to ensure 5-gate compliance.\n2. **Blast Radius & Inbound Dependents**:\n   - Inspect `Related.Dependents` (packages importing this lane). Core leaves with >10 dependents require non-breaking public APIs.\n   - Inspect `Related.Dependencies` (packages imported by this lane).\n3. **Registered DOS Trees**:\n   - Check `Related.DosTrees` declared in `dos.toml` to verify directory boundaries for subagent task fencing.\n4. **Witness Proofs & Benchmarks**:\n   - Check `Related.ProofWitnesses` against `internal\u002Fmaturity\u002Fruntime-proofs.json`.\n   - Check `Related.BenchmarkWitnesses` against `BENCHMARK-AUTHORITY.md`.\n\nChoose targets based on leverage:\n- **Option A: High Carrying Risk (Critical Compounding Interest)**:\n  Lanes where `interest.band == \"critical\"` (>25% rate) or `health.status == \"critical\"`.\n- **Option B: Untested \u002F Skeleton Stubs (Highest Maturity Gap)**:\n  Lanes sitting at `0.0` or `1.0\u002F8.0` (`proposed` or `stub`). Adding core types and tests jumps maturity from `1.0` to `4.0+`.\n- **Option C: Comment Bloat \u002F Hygiene Cleanup**:\n  Lanes flagged with `excess_comments` where pruning formulaic comments restores clean structure and cuts bad debt interest.\n\nRead the lane's `next_action` field—this is the exact action required to climb the curve.\n\n---\n\n## Step 3 — Delegate to Subagent (Keep Coordinator Context Clean)\n\nPer `AGENTS.md`, the primary agent coordinates; substantive investigation, code editing, and test runs are delegated to isolated subagents via the `task` tool so coordinator context stays clean and focused.\n\nLaunch a targeted subagent:\n```json\n{\n  \"subagent_type\": \"general\",\n  \"description\": \"Clean debt in \u003Clane>\",\n  \"prompt\": \"You are an isolated worker advancing the maturity curve for \u003Cunit_of_work> (internal\u002F\u003Clane> or pkg\u002F\u003Clane>).\\nGoal: fulfill the exact next action: \u003Cnext_action>.\\nTarget Directory: \u003Cunit_of_work>\\nBoundaries: Edit ONLY files inside \u003Cunit_of_work>\u002F. Do not touch sibling packages.\\nVerification: Execute `go test -v .\u002F\u003Cunit_of_work>` and `go vet .\u002F\u003Cunit_of_work>`.\\nReturn Contract: Return a compact receipt with: (1) files modified\u002Fcreated, (2) test result receipt, (3) brief 1-line rationale. Do not return full command logs.\"\n}\n```\n\nThe subagent executes the concrete work needed:\n- **If missing tests (`HasTests == false`)**:\n  Writes real unit tests (`\u003Cname>_test.go`) in `\u003Cunit_of_work>\u002F`. Covers positive and\n  negative branches, edge cases, and ensures `go test .\u002F\u003Cunit_of_work>\u002F...` passes cleanly.\n\n- **If missing implementation (`HasCode == false` or stub)**:\n  Implements core functions, types, and logic in `\u003Cunit_of_work>\u002F`. Adheres to existing\n  patterns and keeps the package focused.\n\n- **If unintegrated (`Integrated == false`)**:\n  Connects the package into production commands or registration graph.\n\n- **If undogfooded (`Dogfooded == false`)**:\n  Executes real runtime path and captures passing proof in `internal\u002Fmaturity\u002Fruntime-proofs.json`.\n\n- **If unbenchmarked (`Benchmarked == false`)**:\n  Adds substantive `Benchmark*` functions with `b.N` loops measuring production operations.\n\n- **If carrying excess comments (`ExcessComments == true`)**:\n  Prunes formulaic comment bloat, redundant syntax explanations, and keyword clutter. Code\n  must be clean and self-documenting; invariants belong in tests and code assertions. NEVER\n  add formulaic \"Contract:\", \"Invariant:\", \"Fail-closed:\" comments.\n\n---\n\n## Step 4 — Coordinator Independent Witnessing\n\nThe coordinator does NOT trust worker narration—it independently witnesses the result (the `dos-witness-claim` invariant):\n\n1. **Verify toolchain execution**:\n   - For public `fak` units (`internal\u002F\u003Ctarget>` or `pkg\u002F\u003Ctarget>`):\n     ```bash\n     go vet .\u002F\u003Cunit_of_work>\n     go test -v .\u002F\u003Cunit_of_work>\n     ```\n   - For private `fak-private` units (`platform\u002F\u003Ctarget>`):\n     ```bash\n     go -C ..\\fak-private vet .\u002Fplatform\u002F\u003Ctarget>\n     go -C ..\\fak-private test -v .\u002Fplatform\u002F\u003Ctarget>\n     ```\n\n2. **Verify maturity curve ascent & health upgrade**:\n   ```bash\n   fak debt-lanes --lane \u003Ctarget> --json\n   ```\n\nVerify that:\n- `Maturity` increased (e.g. from `1.0` or `2.0` to `4.0` or `7.5+`).\n- `MaturityGap` decreased.\n- `DebtPrincipal` and `CarryingCost` dropped.\n- `RealizedContribution` increased.\n- `Health.Status` improved (e.g. from `critical` to `degraded`, or `degraded` to `healthy`).\n- `Health.Issues` resolved target issue tokens (e.g. `missing_tests`, `excess_comments`, `disconnected_wiring`).\n\n---\n\n## Step 5 — Re-Measure and Prove Debt Drop & Health Upgrade\n\nRun the scorecard against the saved baseline to prove the drop:\n\n```bash\nfak debt-lanes --compare baseline.json\nfak debt-lanes --lane \u003Ctarget>\n```\n\nConfirm:\n- `Total Debt` shows a negative delta (`-X.X pts`).\n- `Health Status` shows the lane upgraded with no regression in companion lanes.\n- `Production Grade` percentage improved or held steady.\n- `Denominator` remained stable (no work was deleted to cheat the score).\n- `WIP Dilution` decreased.\n\n---\n\n## Step 6 — Commit Cleanly by Explicit Path\n\nFollow trunk discipline: stage only the explicit paths modified for this single unit of\nwork. Include a Conventional-Commits subject, signed-off DCO (`-s`), and the required repo trailer:\n\n- **For public `fak` commits**:\n  ```bash\n  fak sync reconcile --apply\n  python tools\u002Fscrub_public_copy.py --audit-staged --root .\n  fak commit --path \u003Cunit_of_work> -m \"fix(\u003Ctarget>): advance maturity curve and retire debt (fak \u003Ctarget>)\" [--push]\n  fak sync push\n  ```\n- **For private `fak-private` commits**:\n  ```bash\n  git -C ..\\fak-private add platform\u002F\u003Ctarget>\n  git -C ..\\fak-private commit -s -m \"fix(\u003Ctarget>): advance maturity curve and retire debt (fak-private \u003Ctarget>)\" -- platform\u002F\u003Ctarget>\n  ```\n\nVerify `git status` shows your lane is committed and no peer WIP was touched.\n","# \u002Fdebt-clean — retire maturity debt worst-first in bounded batches\n\n> **What this does.** Every unit of work (feature, module, leaf) in the system carries a\n> dedicated debt lane scored on a continuous 0.0–10.0 maturity curve. When new work is added\n> at a partial maturity (e.g. 1\u002F10 stub), it immediately enters the production grade\n> denominator as debt with an accrued carrying cost.\n>\n> This skill executes a **bounded, disciplined cleaning pass**: query and baseline the debt lanes,\n> cross-index related things (dual-repo companions, dependents, proofs, benchmarks), run pre-flight\n> health diagnostics, pick 1–3 high-leverage hotspots (worst carrying cost, critical compounding interest,\n> or degraded health), fulfill the exact next action that advances the maturity curve, prove the debt dropped\n> and health upgraded with `--compare`, and commit by explicit path.\n\nThe shape: **query & baseline debt lanes → cross-index related things & pre-flight health → pick bounded batch (1–3 units) → execute next action\n(tests\u002Fintegration\u002Fbenchmarks\u002Fclean bloat) → verify package → prove debt drop & health upgrade with `--compare` → commit by\nexplicit path.**\n\n---\n\n## The Rule of Bounded Batches\n\nNever attempt a repository-wide sweep in one pass (hundreds of WIP lanes cannot and should\nnot be rushed in a single turn). Enforce strict scoping:\n\n1. **Max 1–3 units of work per batch**: Focus on 1–3 closely related leaves or a single\n   critical hotspot.\n2. **Shift-left proof**: Every maturity climb requires genuine disk evidence (passing\n   `*_test.go`, benchmarks, real runtime wiring), never synthetic markers or mock-only claims.\n3. **No comment gaming; excess comments is BAD debt**: Comments are NOT tracked as positive\n   debt retirement. Do not add formulaic \"Contract:\", \"Invariant:\", or \"Fail-closed:\" comment headers\n   or restate syntax. In fact, excess comments and comment bloat (>35% comment ratio or formulaic\n   keyword clutter) are penalized as BAD debt with interest rate penalties.\n4. **Denominator honesty**: Advancing maturity increases realized points without shrinking\n   the denominator, genuinely raising the production-grade percentage.\n5. **Multi-dimensional health upgrade**: Debt retirement must elevate the lane's health status\n   from `degraded` or `critical` toward `healthy`, resolving flagged issue tokens.\n\n---\n\n## Step 1 — Measure Baseline & Query Health\n\nRun `fak debt-lanes` to capture the current state, query candidate work, and audit system health:\n\n```bash\n# Capture full baseline:\nfak debt-lanes --json > baseline.json\nfak debt-lanes --top 5\n\n# Query lanes by keyword (matches lane name, unit of work, companion, drivers, or health issues):\nfak debt-lanes --query \u003Ckeyword> --top 5\n\n# Filter lanes by multi-dimensional health verdict (healthy, degraded, critical):\nfak debt-lanes --health degraded,critical --top 5\n\n# Cross-index related things, dual-repo companions, and blast radius:\nfak debt-lanes --cross-index --top 10\n```\n\n### Multi-Dimensional Lane Health Dimensions\n- **`healthy`**: Score >= 0.85, test passing, clean comment hygiene, integrated into production graph, documented\u002Fbenchmarked if core, low carrying interest.\n- **`degraded`**: Untested stubs (`missing_tests`), excess comment bloat (`comment_ratio > 35%` or formulaic keyword noise), disconnected wiring (`integrated=false`), unbenchmarked, or unproven in runtime.\n- **`critical`**: Compounding carrying cost (>25% interest rate) or untested core paths (`criticality=core && has_tests=false`) with high inbound dependents.\n\nNote the headline figures:\n- **Production Grade**: current letter and percentage (e.g. `Grade C, 75.4%`).\n- **Fleet Health**: healthy, degraded, and critical counts with average health score.\n- **Denominator Points**: total production baseline points.\n- **Total Debt**: total principal + carrying cost.\n- **Top Hotspots**: lanes carrying the highest carrying cost or highest maturity gap.\n\n---\n\n## Step 2 — Cross-Index Related Things & Select Target (1–3 Units)\n\nInspect the specific target's status, evidence, health findings, and cross-indexed artifacts:\n\n```bash\nfak debt-lanes --lane \u003Clane-name> --json\n```\n\n### Cross-Indexing Checklist for Target Lane\n1. **Dual-Repo Companion**:\n   - If working in `fak` (`internal\u002F\u003Clane>`), check `Related.CompanionUnitOfWork` for counterpart in `fak-private` (`platform\u002F\u003Clane>`).\n   - If working in `fak-private`, check counterpart in `fak` (`internal\u002F\u003Clane>` or `pkg\u002F\u003Clane>`).\n   - Run `go run .\u002Fcmd\u002Ffak-boundary explain \u003Cunit_of_work>` before making cross-repo edits to ensure 5-gate compliance.\n2. **Blast Radius & Inbound Dependents**:\n   - Inspect `Related.Dependents` (packages importing this lane). Core leaves with >10 dependents require non-breaking public APIs.\n   - Inspect `Related.Dependencies` (packages imported by this lane).\n3. **Registered DOS Trees**:\n   - Check `Related.DosTrees` declared in `dos.toml` to verify directory boundaries for subagent task fencing.\n4. **Witness Proofs & Benchmarks**:\n   - Check `Related.ProofWitnesses` against `internal\u002Fmaturity\u002Fruntime-proofs.json`.\n   - Check `Related.BenchmarkWitnesses` against `BENCHMARK-AUTHORITY.md`.\n\nChoose targets based on leverage:\n- **Option A: High Carrying Risk (Critical Compounding Interest)**:\n  Lanes where `interest.band == \"critical\"` (>25% rate) or `health.status == \"critical\"`.\n- **Option B: Untested \u002F Skeleton Stubs (Highest Maturity Gap)**:\n  Lanes sitting at `0.0` or `1.0\u002F8.0` (`proposed` or `stub`). Adding core types and tests jumps maturity from `1.0` to `4.0+`.\n- **Option C: Comment Bloat \u002F Hygiene Cleanup**:\n  Lanes flagged with `excess_comments` where pruning formulaic comments restores clean structure and cuts bad debt interest.\n\nRead the lane's `next_action` field—this is the exact action required to climb the curve.\n\n---\n\n## Step 3 — Delegate to Subagent (Keep Coordinator Context Clean)\n\nPer `AGENTS.md`, the primary agent coordinates; substantive investigation, code editing, and test runs are delegated to isolated subagents via the `task` tool so coordinator context stays clean and focused.\n\nLaunch a targeted subagent:\n```json\n{\n  \"subagent_type\": \"general\",\n  \"description\": \"Clean debt in \u003Clane>\",\n  \"prompt\": \"You are an isolated worker advancing the maturity curve for \u003Cunit_of_work> (internal\u002F\u003Clane> or pkg\u002F\u003Clane>).\\nGoal: fulfill the exact next action: \u003Cnext_action>.\\nTarget Directory: \u003Cunit_of_work>\\nBoundaries: Edit ONLY files inside \u003Cunit_of_work>\u002F. Do not touch sibling packages.\\nVerification: Execute `go test -v .\u002F\u003Cunit_of_work>` and `go vet .\u002F\u003Cunit_of_work>`.\\nReturn Contract: Return a compact receipt with: (1) files modified\u002Fcreated, (2) test result receipt, (3) brief 1-line rationale. Do not return full command logs.\"\n}\n```\n\nThe subagent executes the concrete work needed:\n- **If missing tests (`HasTests == false`)**:\n  Writes real unit tests (`\u003Cname>_test.go`) in `\u003Cunit_of_work>\u002F`. Covers positive and\n  negative branches, edge cases, and ensures `go test .\u002F\u003Cunit_of_work>\u002F...` passes cleanly.\n\n- **If missing implementation (`HasCode == false` or stub)**:\n  Implements core functions, types, and logic in `\u003Cunit_of_work>\u002F`. Adheres to existing\n  patterns and keeps the package focused.\n\n- **If unintegrated (`Integrated == false`)**:\n  Connects the package into production commands or registration graph.\n\n- **If undogfooded (`Dogfooded == false`)**:\n  Executes real runtime path and captures passing proof in `internal\u002Fmaturity\u002Fruntime-proofs.json`.\n\n- **If unbenchmarked (`Benchmarked == false`)**:\n  Adds substantive `Benchmark*` functions with `b.N` loops measuring production operations.\n\n- **If carrying excess comments (`ExcessComments == true`)**:\n  Prunes formulaic comment bloat, redundant syntax explanations, and keyword clutter. Code\n  must be clean and self-documenting; invariants belong in tests and code assertions. NEVER\n  add formulaic \"Contract:\", \"Invariant:\", \"Fail-closed:\" comments.\n\n---\n\n## Step 4 — Coordinator Independent Witnessing\n\nThe coordinator does NOT trust worker narration—it independently witnesses the result (the `dos-witness-claim` invariant):\n\n1. **Verify toolchain execution**:\n   - For public `fak` units (`internal\u002F\u003Ctarget>` or `pkg\u002F\u003Ctarget>`):\n     ```bash\n     go vet .\u002F\u003Cunit_of_work>\n     go test -v .\u002F\u003Cunit_of_work>\n     ```\n   - For private `fak-private` units (`platform\u002F\u003Ctarget>`):\n     ```bash\n     go -C ..\\fak-private vet .\u002Fplatform\u002F\u003Ctarget>\n     go -C ..\\fak-private test -v .\u002Fplatform\u002F\u003Ctarget>\n     ```\n\n2. **Verify maturity curve ascent & health upgrade**:\n   ```bash\n   fak debt-lanes --lane \u003Ctarget> --json\n   ```\n\nVerify that:\n- `Maturity` increased (e.g. from `1.0` or `2.0` to `4.0` or `7.5+`).\n- `MaturityGap` decreased.\n- `DebtPrincipal` and `CarryingCost` dropped.\n- `RealizedContribution` increased.\n- `Health.Status` improved (e.g. from `critical` to `degraded`, or `degraded` to `healthy`).\n- `Health.Issues` resolved target issue tokens (e.g. `missing_tests`, `excess_comments`, `disconnected_wiring`).\n\n---\n\n## Step 5 — Re-Measure and Prove Debt Drop & Health Upgrade\n\nRun the scorecard against the saved baseline to prove the drop:\n\n```bash\nfak debt-lanes --compare baseline.json\nfak debt-lanes --lane \u003Ctarget>\n```\n\nConfirm:\n- `Total Debt` shows a negative delta (`-X.X pts`).\n- `Health Status` shows the lane upgraded with no regression in companion lanes.\n- `Production Grade` percentage improved or held steady.\n- `Denominator` remained stable (no work was deleted to cheat the score).\n- `WIP Dilution` decreased.\n\n---\n\n## Step 6 — Commit Cleanly by Explicit Path\n\nFollow trunk discipline: stage only the explicit paths modified for this single unit of\nwork. Include a Conventional-Commits subject, signed-off DCO (`-s`), and the required repo trailer:\n\n- **For public `fak` commits**:\n  ```bash\n  fak sync reconcile --apply\n  python tools\u002Fscrub_public_copy.py --audit-staged --root .\n  fak commit --path \u003Cunit_of_work> -m \"fix(\u003Ctarget>): advance maturity curve and retire debt (fak \u003Ctarget>)\" [--push]\n  fak sync push\n  ```\n- **For private `fak-private` commits**:\n  ```bash\n  git -C ..\\fak-private add platform\u002F\u003Ctarget>\n  git -C ..\\fak-private commit -s -m \"fix(\u003Ctarget>): advance maturity curve and retire debt (fak-private \u003Ctarget>)\" -- platform\u002F\u003Ctarget>\n  ```\n\nVerify `git status` shows your lane is committed and no peer WIP was touched.\n",{"name":5,"description":7,"allowed-tools":24,"argument-hint":25,"user-invocable":26,"disable-model-invocation":20},"Read, Bash, Write, Edit, Grep, Glob","[--lane \u003Cname>] [--query \u003Ctext>] [--health healthy|degraded|critical] [--cross-index] [--target-repo both|fak|fak-private] [--top N]  (no args = baseline + clean top 1-3 debt hotspots)",true,"main","f565b7b7db63e79649f3a02c08108132a86c5d05",".claude\u002Fskills\u002Fdebt-clean",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":37,"prompt":47,"zipAvailable":26},[38,41,44],{"tool":39,"command":40},"npx","npx skills add anthony-chaudhary\u002Ffak --skill debt-clean",{"tool":42,"command":43},"bunx","bunx skills add anthony-chaudhary\u002Ffak --skill debt-clean",{"tool":45,"command":46},"pnpm","pnpm dlx skills add anthony-chaudhary\u002Ffak --skill debt-clean","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fanthony-chaudhary\u002Ffak\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Fdebt-clean\u002FSKILL.md",[],[50,57,66,73,80,85],{"skillNo":51,"name":52,"nameZh":6,"description":53,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":54,"categories":55,"keywords":56,"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":58,"name":59,"nameZh":6,"description":60,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":61,"licenseFileUrl":62,"sourceHtmlUrl":63,"categories":64,"keywords":65,"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":67,"name":68,"nameZh":6,"description":69,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":70,"categories":71,"keywords":72,"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":74,"name":75,"nameZh":6,"description":76,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":77,"categories":78,"keywords":79,"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":81,"name":68,"nameZh":6,"description":69,"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},"01M77HR7XQ9X8F2CY9Z4F2ZEZ3","https:\u002F\u002Fgithub.com\u002Fanthony-chaudhary\u002Ffak\u002Fblob\u002Fmain\u002Finternal\u002Fctxplanlint\u002Ftestdata\u002Frepo\u002F.claude\u002Fskills\u002Fquality-report\u002FSKILL.md",[],[],{"skillNo":86,"name":75,"nameZh":6,"description":76,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":87,"categories":88,"keywords":89,"publishedAt":19},"01M77HR5BVKCTR1WNJGRBSDNX7","https:\u002F\u002Fgithub.com\u002Fanthony-chaudhary\u002Ffak\u002Fblob\u002Fmain\u002Finternal\u002Fctxplanlint\u002Ftestdata\u002Frepo\u002F.claude\u002Fskills\u002Fctx-overlay\u002FSKILL.md",[],[]]