[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M77HEQAMFC3N155T4DNVE09B":3,"skill-same:01M77HEQAMFC3N155T4DNVE09B":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},"01M77HEQAMFC3N155T4DNVE09B","harness-garden",null,"Use when recent trajectories, notes, or refusals should become one evidence-backed harness improvement ticket and at most one guarded worker.","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\u002Fharness-garden\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: harness-garden\ndescription: Use when recent trajectories, notes, or refusals should become one evidence-backed harness improvement ticket and at most one guarded worker.\n---\n\n# Harness garden\n\nClose one inward-looking improvement loop: **observe -> classify -> subtract or ticket -> admit one worker -> witness**. Compose existing project primitives; do not create another analytics stack, scheduler, or dispatch mechanism.\n\n## Fixed bounds\n\nOne pass may update or file **at most one issue** and launch **at most one worker**. It may conclude `drop` when fak already supports the capability or evidence is insufficient. Keep private trajectory content out of public artifacts.\n\n## 1. Observe recent work\n\nRun the supported cross-harness audit into allocated scratch:\n\n```powershell\nfak tree-doctor --scratch-dir harness-garden --json\nfak trajectory audit --since 7d --jsonl _scratch\u002Fharness-garden\u002Frecent.jsonl --md _scratch\u002Fharness-garden\u002Frecent.md\n```\n\nRead the report, recent operator notes, relevant guard\u002Frefusal evidence, and open\u002Fclosed issues. Follow [`..\u002Ftrajectory-audit\u002FSKILL.md`](..\u002Ftrajectory-audit\u002FSKILL.md) for sampling, privacy, baseline, and behavior classification.\n\nA nonzero audit is evidence, not an empty report. Preserve its typed refusal and partial counts; never infer that missing output means no bottleneck. If refusal prevents honest diagnosis, make that refusal the candidate defect or stop as `insufficient-evidence`.\n\n## 2. Classify before proposing\n\nClassify the highest-leverage repeated friction as exactly one:\n\n- `subtract`: stale, overlapping, or unnecessary instruction\u002Fmachinery;\n- `config`: an existing primitive is correct but poorly defaulted or connected;\n- `skill`: behavior can improve through concise, reusable guidance;\n- `tool`: deterministic code or schema support is missing;\n- `inherent`: no safe harness change can remove the constraint;\n- `insufficient-evidence`: current evidence cannot support a change.\n\nPrefer, in order: no change, deletion, configuration, an existing project primitive, standard library, then new machinery. Name the product defect separately from any guidance-side mitigation. Rank by repeated operator cost and breadth, not novelty.\n\n## 3. Dedupe and choose one durable action\n\nSearch open and closed GitHub issues with the observed error class, affected primitive, and desired outcome. Choose exactly one:\n\n1. `drop` - capability is present, evidence is weak, or cost exceeds value;\n2. `update` - add the new witness or narrowed done condition to the matching issue;\n3. `file` - create one issue only when no duplicate exists.\n\nFor `update` or `file`, include:\n\n- **For \u002F Problem \u002F Today \u002F Better because \u002F Witness** against the real next-best alternative;\n- centrality and P1-P4 from `docs\u002Fproblems-we-solve.md`;\n- smallest working spine, gold-plating boundary, done condition, operating envelope, privacy boundary, and follow-ons;\n- audit command, bounded counts, typed refusals, and artifact paths rather than private transcript content.\n\nApply [`..\u002Fticket-scope\u002FSKILL.md`](..\u002Fticket-scope\u002FSKILL.md). Validate through the supported issue-contract surface when available. If unavailable, preserve the full contract instead of inventing a substitute tool.\n\n## 4. Admit one bounded worker\n\nOnly after the durable issue exists, define a distinct file tree and ask DOS before launch:\n\n```powershell\ndos arbitrate --lane \u003Cleaf> --kind keyword --mode exclusive --tree \u003Cpath>... --output json --explain\npwsh tools\u002Flaunch_goal_detached.ps1 -PointerFile \u003Callocated-prompt> -Workspace C:\\work\\fak -WorkKind gardening -PlanOnly\n```\n\nThe packet names the issue, owned paths, non-goals, required test\u002Fwitness, and stop condition. Use `fak worktree worker prepare|land|reap` for implementation isolation as required by `AGENTS.md`.\n\nLaunch at most one worker after admission and detached preview are green. Keep the spawn preflight enabled. Never use a bypass, raw background process, alternate account, or broader tree to route around an account refusal, schema refusal, lease collision, or another typed gate. On refusal, record the ready-to-run command and typed outcome; that is a prepared packet, not a launch or shipped work.\n\n## 5. Witness and close\n\nA worker self-report is not evidence. Follow [`..\u002Fdos-witness-claim\u002FSKILL.md`](..\u002Fdos-witness-claim\u002FSKILL.md), independently read the diff\u002Fartifact, run the scope-correct gate, and land only witnessed green work. Reconcile the issue with discoveries and follow-ons.\n\nReport one claim per line:\n\n- **Decision:** `drop | update #N | file #N` with the evidence artifact.\n- **Bottleneck:** classification plus bounded count\u002Frefusal.\n- **Worker:** `not planned | prepared | refused \u003CTOKEN> | launched | witnessed \u003Cmodule@rev>`.\n- **Next check:** one command or issue URL.\n\n## Proof scenarios\n\nA pass is not dogfooded until evidence covers:\n\n1. existing capability -> `drop` and no issue;\n2. duplicate -> update one issue, no second ticket;\n3. absent capability -> one contract-complete issue;\n4. trajectory schema refusal -> partial evidence preserved, no false clean claim;\n5. account refusal -> worker remains prepared, not launched;\n6. lease refusal -> colliding worker does not launch;\n7. green worker -> independent witness before landing or done claim.\n\n## When not to use\n\n- External repository or paper scouting -> [`..\u002Fscout-loop\u002FSKILL.md`](..\u002Fscout-loop\u002FSKILL.md).\n- Broad issue execution -> [`..\u002Fsuper-loop\u002FSKILL.md`](..\u002Fsuper-loop\u002FSKILL.md).\n- Questions without implementation -> [`..\u002Fquestion-loop\u002FSKILL.md`](..\u002Fquestion-loop\u002FSKILL.md).\n- One known ticket -> ticket-specific dispatch, not another garden pass.\n","# Harness garden\n\nClose one inward-looking improvement loop: **observe -> classify -> subtract or ticket -> admit one worker -> witness**. Compose existing project primitives; do not create another analytics stack, scheduler, or dispatch mechanism.\n\n## Fixed bounds\n\nOne pass may update or file **at most one issue** and launch **at most one worker**. It may conclude `drop` when fak already supports the capability or evidence is insufficient. Keep private trajectory content out of public artifacts.\n\n## 1. Observe recent work\n\nRun the supported cross-harness audit into allocated scratch:\n\n```powershell\nfak tree-doctor --scratch-dir harness-garden --json\nfak trajectory audit --since 7d --jsonl _scratch\u002Fharness-garden\u002Frecent.jsonl --md _scratch\u002Fharness-garden\u002Frecent.md\n```\n\nRead the report, recent operator notes, relevant guard\u002Frefusal evidence, and open\u002Fclosed issues. Follow [`..\u002Ftrajectory-audit\u002FSKILL.md`](..\u002Ftrajectory-audit\u002FSKILL.md) for sampling, privacy, baseline, and behavior classification.\n\nA nonzero audit is evidence, not an empty report. Preserve its typed refusal and partial counts; never infer that missing output means no bottleneck. If refusal prevents honest diagnosis, make that refusal the candidate defect or stop as `insufficient-evidence`.\n\n## 2. Classify before proposing\n\nClassify the highest-leverage repeated friction as exactly one:\n\n- `subtract`: stale, overlapping, or unnecessary instruction\u002Fmachinery;\n- `config`: an existing primitive is correct but poorly defaulted or connected;\n- `skill`: behavior can improve through concise, reusable guidance;\n- `tool`: deterministic code or schema support is missing;\n- `inherent`: no safe harness change can remove the constraint;\n- `insufficient-evidence`: current evidence cannot support a change.\n\nPrefer, in order: no change, deletion, configuration, an existing project primitive, standard library, then new machinery. Name the product defect separately from any guidance-side mitigation. Rank by repeated operator cost and breadth, not novelty.\n\n## 3. Dedupe and choose one durable action\n\nSearch open and closed GitHub issues with the observed error class, affected primitive, and desired outcome. Choose exactly one:\n\n1. `drop` - capability is present, evidence is weak, or cost exceeds value;\n2. `update` - add the new witness or narrowed done condition to the matching issue;\n3. `file` - create one issue only when no duplicate exists.\n\nFor `update` or `file`, include:\n\n- **For \u002F Problem \u002F Today \u002F Better because \u002F Witness** against the real next-best alternative;\n- centrality and P1-P4 from `docs\u002Fproblems-we-solve.md`;\n- smallest working spine, gold-plating boundary, done condition, operating envelope, privacy boundary, and follow-ons;\n- audit command, bounded counts, typed refusals, and artifact paths rather than private transcript content.\n\nApply [`..\u002Fticket-scope\u002FSKILL.md`](..\u002Fticket-scope\u002FSKILL.md). Validate through the supported issue-contract surface when available. If unavailable, preserve the full contract instead of inventing a substitute tool.\n\n## 4. Admit one bounded worker\n\nOnly after the durable issue exists, define a distinct file tree and ask DOS before launch:\n\n```powershell\ndos arbitrate --lane \u003Cleaf> --kind keyword --mode exclusive --tree \u003Cpath>... --output json --explain\npwsh tools\u002Flaunch_goal_detached.ps1 -PointerFile \u003Callocated-prompt> -Workspace C:\\work\\fak -WorkKind gardening -PlanOnly\n```\n\nThe packet names the issue, owned paths, non-goals, required test\u002Fwitness, and stop condition. Use `fak worktree worker prepare|land|reap` for implementation isolation as required by `AGENTS.md`.\n\nLaunch at most one worker after admission and detached preview are green. Keep the spawn preflight enabled. Never use a bypass, raw background process, alternate account, or broader tree to route around an account refusal, schema refusal, lease collision, or another typed gate. On refusal, record the ready-to-run command and typed outcome; that is a prepared packet, not a launch or shipped work.\n\n## 5. Witness and close\n\nA worker self-report is not evidence. Follow [`..\u002Fdos-witness-claim\u002FSKILL.md`](..\u002Fdos-witness-claim\u002FSKILL.md), independently read the diff\u002Fartifact, run the scope-correct gate, and land only witnessed green work. Reconcile the issue with discoveries and follow-ons.\n\nReport one claim per line:\n\n- **Decision:** `drop | update #N | file #N` with the evidence artifact.\n- **Bottleneck:** classification plus bounded count\u002Frefusal.\n- **Worker:** `not planned | prepared | refused \u003CTOKEN> | launched | witnessed \u003Cmodule@rev>`.\n- **Next check:** one command or issue URL.\n\n## Proof scenarios\n\nA pass is not dogfooded until evidence covers:\n\n1. existing capability -> `drop` and no issue;\n2. duplicate -> update one issue, no second ticket;\n3. absent capability -> one contract-complete issue;\n4. trajectory schema refusal -> partial evidence preserved, no false clean claim;\n5. account refusal -> worker remains prepared, not launched;\n6. lease refusal -> colliding worker does not launch;\n7. green worker -> independent witness before landing or done claim.\n\n## When not to use\n\n- External repository or paper scouting -> [`..\u002Fscout-loop\u002FSKILL.md`](..\u002Fscout-loop\u002FSKILL.md).\n- Broad issue execution -> [`..\u002Fsuper-loop\u002FSKILL.md`](..\u002Fsuper-loop\u002FSKILL.md).\n- Questions without implementation -> [`..\u002Fquestion-loop\u002FSKILL.md`](..\u002Fquestion-loop\u002FSKILL.md).\n- One known ticket -> ticket-specific dispatch, not another garden pass.\n",{"name":5,"description":7},"main","f565b7b7db63e79649f3a02c08108132a86c5d05",".claude\u002Fskills\u002Fharness-garden",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 harness-garden",{"tool":39,"command":40},"bunx","bunx skills add anthony-chaudhary\u002Ffak --skill harness-garden",{"tool":42,"command":43},"pnpm","pnpm dlx skills add anthony-chaudhary\u002Ffak --skill harness-garden","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fanthony-chaudhary\u002Ffak\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Fharness-garden\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",[],[]]