[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M77HDENM431TFVJS9D2H0EPQ":3,"skill-same:01M77HDENM431TFVJS9D2H0EPQ":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},"01M77HDENM431TFVJS9D2H0EPQ","dos-witness-claim",null,"Verify subagent or worker results before folding them into a synthesis. Use when another agent claims it shipped, created, found, or changed something and your next step would otherwise trust its return string.","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\u002Fdos-witness-claim\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: dos-witness-claim\ndescription: \"Verify subagent or worker results before folding them into a synthesis. Use when another agent claims it shipped, created, found, or changed something and your next step would otherwise trust its return string.\"\n---\n\n# dos-witness-claim - fold witnessed effects, not narration\n\nA worker result is a claim, not a fact. Before using it as input to another\nprompt, report, plan, or commit, witness the claimed effect from a surface the\nworker did not author. Fold only confirmed effects; route unconfirmed results\nseparately and count them in the denominator.\n\n## Load-Bearing Rule\n\nNever interpolate a worker's return string directly into a synthesis as ground\ntruth. Extract the checkable effect, gather a non-agent-authored witness, and\nfold only the confirmed bucket.\n\n## Step 0 - Discover The Workspace\n\n```bash\ndos doctor --workspace . --json\n```\n\nRead `paths`, `lanes`, and `stamp` from the result. If a claim names a\n`(plan, phase)`, `dos verify` applies this workspace's stamp grammar; do not\ngrep commit subjects yourself.\n\n## Step 1 - Check Worker Terminal State\n\nIf you have a worker transcript path, verify the result is not a harness-authored\ndeath before reading it as a worker result:\n\n```bash\ndos verify-result --workspace . --transcript \u003Cagent-transcript.jsonl>\n```\n\nRoute by exit code:\n\n- `0`: terminal result is usable for claim extraction; still witness the effect.\n- `3`: worker is dead or synthetic. Do not fold its return string; re-dispatch or\n  surface the failed unit.\n- `2`: contract error. Fix the transcript wiring; do not treat it as healthy.\n\nIf `verify-result` is not available in the installed DOS version, log the gap and\ncontinue to effect witnessing. The gap is not a pass.\n\n## Step 2 - Extract The Checkable Claim\n\nClassify each result into one of these claim types:\n\n| Claim type | Example | Witness |\n|---|---|---|\n| Git phase | \"`PLAN` \u002F `PHASE` shipped\" | `dos verify` over git ancestry and stamp grammar |\n| Commit claim | \"commit `\u003Csha>` did X\" | `dos commit-audit \u003Csha>` |\n| File\u002Feffect claim | \"created file X\", \"sent id Y\" | fresh read-back, OS exit code, API GET, or state diff |\n| No checkable claim | \"done\", \"looks good\" | no fold; surface as `NO_CLAIM` |\n\nAbstain rather than inventing identifiers from prose. A result without a named\neffect is not confirmed.\n\n## Step 3 - Witness Git-Backed Claims\n\nFor a `(plan, phase)` claim:\n\n```bash\ndos verify --workspace . \u003CPLAN> \u003CPHASE> --json\n```\n\nFold only when the exit code is shipped and the JSON carries a positive source\nsuch as `registry` or `grep-subject`. Preserve the source rung in the synthesis;\n`grep-subject` is weaker than a registry row.\n\nFor a commit claim:\n\n```bash\ndos commit-audit --workspace . \u003Csha>\n```\n\nTreat `OK` \u002F `diff-witnessed` as foldable shape evidence. Treat\n`CLAIM_UNWITNESSED` as residual review work, not as success.\n\n## Step 4 - Witness Non-Git Effects\n\nThere is no generic `dos verify-effect` CLI verb. For created files, DB rows,\nmessages, deploys, or external side effects, gather a fresh read-back from a\nsurface the worker did not author:\n\n- file claim: fresh filesystem read\u002Fstat of the exact path;\n- API claim: GET the object by id;\n- DB claim: read the row by key;\n- command claim: run the relevant command and check its exit\u002Fstatus output.\n\nIf the read-back confirms the effect, fold it as `CONFIRMED`. If it contradicts\nthe claim, route it as `REFUTED`. If no accountable read-back exists, route it as\n`UNWITNESSED`; never fold it as success.\n\n## Step 5 - Return A Partition, Not A Story\n\nReturn results in four buckets:\n\n- `CONFIRMED`: safe to fold into the next prompt or report.\n- `REFUTED` \u002F `NOT_SHIPPED` \u002F `DEAD`: do not fold; re-dispatch or surface.\n- `UNWITNESSED`: do not fold; identify the missing witness.\n- `NO_CLAIM`: do not fold; ask for a checkable effect if needed.\n\nCarry coverage forward:\n\n```text\nconfirmed M of N declared results; refuted R; unwitnessed U; no-claim C\n```\n\nDownstream synthesis must see the coverage. Do not let `4\u002F7 confirmed` become\n`7\u002F7 returned`.\n\n## Anti-Patterns\n\n- Folding `${result}` directly because it is non-empty.\n- Asking a model whether a worker's own output looks complete.\n- Counting only returned strings in the denominator.\n- Treating `UNWITNESSED` or `NO_CLAIM` as probably successful.\n- Grepping commit subjects yourself instead of calling `dos verify`.\n","# dos-witness-claim - fold witnessed effects, not narration\n\nA worker result is a claim, not a fact. Before using it as input to another\nprompt, report, plan, or commit, witness the claimed effect from a surface the\nworker did not author. Fold only confirmed effects; route unconfirmed results\nseparately and count them in the denominator.\n\n## Load-Bearing Rule\n\nNever interpolate a worker's return string directly into a synthesis as ground\ntruth. Extract the checkable effect, gather a non-agent-authored witness, and\nfold only the confirmed bucket.\n\n## Step 0 - Discover The Workspace\n\n```bash\ndos doctor --workspace . --json\n```\n\nRead `paths`, `lanes`, and `stamp` from the result. If a claim names a\n`(plan, phase)`, `dos verify` applies this workspace's stamp grammar; do not\ngrep commit subjects yourself.\n\n## Step 1 - Check Worker Terminal State\n\nIf you have a worker transcript path, verify the result is not a harness-authored\ndeath before reading it as a worker result:\n\n```bash\ndos verify-result --workspace . --transcript \u003Cagent-transcript.jsonl>\n```\n\nRoute by exit code:\n\n- `0`: terminal result is usable for claim extraction; still witness the effect.\n- `3`: worker is dead or synthetic. Do not fold its return string; re-dispatch or\n  surface the failed unit.\n- `2`: contract error. Fix the transcript wiring; do not treat it as healthy.\n\nIf `verify-result` is not available in the installed DOS version, log the gap and\ncontinue to effect witnessing. The gap is not a pass.\n\n## Step 2 - Extract The Checkable Claim\n\nClassify each result into one of these claim types:\n\n| Claim type | Example | Witness |\n|---|---|---|\n| Git phase | \"`PLAN` \u002F `PHASE` shipped\" | `dos verify` over git ancestry and stamp grammar |\n| Commit claim | \"commit `\u003Csha>` did X\" | `dos commit-audit \u003Csha>` |\n| File\u002Feffect claim | \"created file X\", \"sent id Y\" | fresh read-back, OS exit code, API GET, or state diff |\n| No checkable claim | \"done\", \"looks good\" | no fold; surface as `NO_CLAIM` |\n\nAbstain rather than inventing identifiers from prose. A result without a named\neffect is not confirmed.\n\n## Step 3 - Witness Git-Backed Claims\n\nFor a `(plan, phase)` claim:\n\n```bash\ndos verify --workspace . \u003CPLAN> \u003CPHASE> --json\n```\n\nFold only when the exit code is shipped and the JSON carries a positive source\nsuch as `registry` or `grep-subject`. Preserve the source rung in the synthesis;\n`grep-subject` is weaker than a registry row.\n\nFor a commit claim:\n\n```bash\ndos commit-audit --workspace . \u003Csha>\n```\n\nTreat `OK` \u002F `diff-witnessed` as foldable shape evidence. Treat\n`CLAIM_UNWITNESSED` as residual review work, not as success.\n\n## Step 4 - Witness Non-Git Effects\n\nThere is no generic `dos verify-effect` CLI verb. For created files, DB rows,\nmessages, deploys, or external side effects, gather a fresh read-back from a\nsurface the worker did not author:\n\n- file claim: fresh filesystem read\u002Fstat of the exact path;\n- API claim: GET the object by id;\n- DB claim: read the row by key;\n- command claim: run the relevant command and check its exit\u002Fstatus output.\n\nIf the read-back confirms the effect, fold it as `CONFIRMED`. If it contradicts\nthe claim, route it as `REFUTED`. If no accountable read-back exists, route it as\n`UNWITNESSED`; never fold it as success.\n\n## Step 5 - Return A Partition, Not A Story\n\nReturn results in four buckets:\n\n- `CONFIRMED`: safe to fold into the next prompt or report.\n- `REFUTED` \u002F `NOT_SHIPPED` \u002F `DEAD`: do not fold; re-dispatch or surface.\n- `UNWITNESSED`: do not fold; identify the missing witness.\n- `NO_CLAIM`: do not fold; ask for a checkable effect if needed.\n\nCarry coverage forward:\n\n```text\nconfirmed M of N declared results; refuted R; unwitnessed U; no-claim C\n```\n\nDownstream synthesis must see the coverage. Do not let `4\u002F7 confirmed` become\n`7\u002F7 returned`.\n\n## Anti-Patterns\n\n- Folding `${result}` directly because it is non-empty.\n- Asking a model whether a worker's own output looks complete.\n- Counting only returned strings in the denominator.\n- Treating `UNWITNESSED` or `NO_CLAIM` as probably successful.\n- Grepping commit subjects yourself instead of calling `dos verify`.\n",{"name":5,"description":7},"main","f565b7b7db63e79649f3a02c08108132a86c5d05",".claude\u002Fskills\u002Fdos-witness-claim",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 dos-witness-claim",{"tool":39,"command":40},"bunx","bunx skills add anthony-chaudhary\u002Ffak --skill dos-witness-claim",{"tool":42,"command":43},"pnpm","pnpm dlx skills add anthony-chaudhary\u002Ffak --skill dos-witness-claim","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fanthony-chaudhary\u002Ffak\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Fdos-witness-claim\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",[],[]]