[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6QPT9TPT1QA02PJS53QJ7VC":3,"skill-same:01M6QPT9TPT1QA02PJS53QJ7VC":77},{"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":23,"publishedAt":44,"linkOnly":45,"markdownContent":46,"markdownBody":47,"frontMatter":48,"refName":54,"commitSha":55,"skillDirectory":56,"forksCount":14,"repositoryHtmlUrl":57,"repositoryHomepageUrl":58,"ownerHtmlUrl":59,"ownerBlogUrl":60,"ownerDescription":61,"updatedAt":62,"install":63,"resources":76},"01M6QPT9TPT1QA02PJS53QJ7VC","skill-doctor",null,"Use when the user wants their agent setup graded from real conversation history, asks which installed skills are actually working, or wants evidence-backed skill edits — scores recent local Claude Code \u002F Codex sessions against efficiency and code-quality rubrics, then drafts skill changes gated by a deterministic aggregator and renders one local shareable report.","Tashima-Tarsh\u002FDisha6.6","Tashima-Tarsh","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F269906498?v=4","01M6PBH98X03XERH0HFT4PFB1P","NITISH KUMAR","01M6PBH9DA0M6KM3Z12P848F0K",0,"MIT","https:\u002F\u002Fgithub.com\u002FTashima-Tarsh\u002FDisha6.6\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fskill-doctor\u002FSKILL.md",[18],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000023","Skill与智能体开发","SCENARIO","使用场景",[24,25,26,27,28,29,30,31,32,33,34,35,36,37,38,39,40,41,42,43],"doctor","skill doctor","agent setup","code","which","sleep","adopt","SkillOpt","efficiency","aggregator","local","self","conversation","rebuild","question","eval","work","common","html report","loop","2026-11-10 10:12:30",false,"---\nname: skill-doctor\ndescription: Use when the user wants their agent setup graded from real conversation history, asks which installed skills are actually working, or wants evidence-backed skill edits — scores recent local Claude Code \u002F Codex sessions against efficiency and code-quality rubrics, then drafts skill changes gated by a deterministic aggregator and renders one local shareable report.\nargument-hint: \"[optional: --repo PATH, --days N, or a question about the setup]\"\nlicense: MIT\nmetadata:\n  version: 1.0.0\n  build_pattern: \"Rebuild of warpdotdev\u002Fcommon-skills skill-doctor (MIT): harvest → LLM-judges-with-rubrics → deterministic aggregation gate → self-contained HTML report\"\n  distinct_from: \"skillopt-sleep (nightly automated replay loop with adopt gate; this is one interactive graded pass); write-a-skill (authors a skill from expertise; this improves skills from observed session evidence); self-eval (grades this session's own work; this grades a window of past sessions)\"\n---\n\n# skill-doctor — grade the agent setup from real sessions\n\n> **Privacy is the contract.** Everything runs locally. Transcripts are condensed,\n> secret-redacted, chmod-0600, and never uploaded — the only shareable artifact is\n> the report the user chooses to share.\n\nRun from the repo being graded. Every artifact goes to one fresh scratch dir, never\ninto the repo:\n\n```bash\nRUN=\"$(mktemp -d \"${TMPDIR:-\u002Ftmp}\u002Fskill-doctor-XXXXXXXX\")\"\npython scripts\u002Fcollect_sessions.py --out \"$RUN\"          # 1 — harvest + redact\n```\n\n**1 — Collect.** Scans Claude Code project-history JSONL and Codex rollouts,\ndiscovers repo skills (`.claude\u002Fskills`, `.agents\u002Fskills`, `.codex\u002Fskills`, plugin\nlayouts), detects skill usage (`Skill` invocations, slash commands, SKILL.md paths), samples\nnewest-first, and writes redacted transcripts. Read `$RUN\u002Finventory.json`: if\n`sessions_sampled` is 0, tell the user there is nothing recent to score (suggest\n`--days 90` or `--repo`) and stop. `skills_found` 0 is fine — the report becomes a\ncase for creating skills.\n\n**2 — Score.** `python scripts\u002Fscore_aggregator.py --inventory \"$RUN\u002Finventory.json\"\n--emit-template > \"$RUN\u002Fsession_scores.json\"`. Read each transcript in\n`$RUN\u002Ftranscripts\u002F` and judge it against **both** rubrics — `scorers\u002Fefficiency.md`\nand `scorers\u002Fcode-quality.md`. Fill the template with a **label from the rubric's\ntable** and a 1–3 sentence reason citing transcript specifics. Never invent numeric\nscores — the aggregator derives them from labels. Use `insufficient_evidence` when\na transcript shows no judgeable diff. Also write 1–5 `top_findings`: the most\nimpactful cross-session patterns, concrete and specific.\n\n**3 — Draft edits.** Follow `references\u002Fskill_edit_governance.md` (the filing bar:\nwould a competent agent with the current instructions still fail this way?). For\neach suggestion that clears it, write the full improved SKILL.md to\n`$RUN\u002Fproposed\u002F\u003Cskill>\u002FSKILL.md`, produce `diff -u \u003Ccurrent> \u003Cproposed>`, and record\nit in `$RUN\u002Fsuggestions.json` citing the sampled session id(s) that motivated it.\nZero suggestions is a valid success — say why per finding. Never modify the user's\nreal skill files in this step.\n\n**4 — Aggregate (the gate).** `python scripts\u002Fscore_aggregator.py --inventory\n\"$RUN\u002Finventory.json\" --scores \"$RUN\u002Fsession_scores.json\" --suggestions\n\"$RUN\u002Fsuggestions.json\"`. It validates labels against the rubric tables, refuses\nscores for unsampled sessions, requires substantive reasons, rejects suggestions\nthat cite no scored session, computes `overall = 0.5·efficiency +\n0.35·code_quality + 0.15·skill_coverage`, and writes `report.json`. **Exit 4 is a\nstop**: fix what it names and re-run; never hand-edit report.json around it.\n\n**5 — Render + tell.** `python scripts\u002Frender_report.py --report \"$RUN\u002Freport.json\"`\n→ one self-contained `report.html` (no JS, no CDN, dark-mode + print-to-PDF). Then\ntell the user the grade and the top findings in text, link\n`file:\u002F\u002F$RUN\u002Freport.html`, and ask whether to apply the proposed diffs to their\nreal skills — apply only on an explicit yes, skill by skill.\n\n## Hard rules\n\n1. **Never upload transcripts, session files, or any excerpt.** Local only.\n2. **Labels only, from the rubric tables.** The aggregator owns all arithmetic.\n3. **Every suggestion traces to a scored session** — or it is dropped. Generic best practice is not evidence.\n4. **Zero suggestions is a success**, not a failure to report around.\n5. **Exit 4 from the aggregator is a stop**, not an error to swallow or bypass.\n6. **Never touch the user's real skill files** without an explicit per-skill yes; proposed edits live under `$RUN\u002Fproposed\u002F`.\n7. **A proposed skill edit follows write-a-skill discipline** — trigger phrase in the description, smallest change that expresses the rule, replace over append.\n\n## Scripts\n\n| Script | Role | Exit codes |\n|---|---|---|\n| `scripts\u002Fcollect_sessions.py` | Harvest Claude Code + Codex sessions, redact secrets, sample, inventory | 0 · 3 bad input |\n| `scripts\u002Fscore_aggregator.py` | Validate labels\u002Freasons\u002Fsuggestions, compute grade, emit report.json | 0 · 2 warnings · 3 bad input · 4 validation failure |\n| `scripts\u002Frender_report.py` | report.json → single self-contained report.html | 0 · 3 bad input |\n\nAll support `--help`, `--output json`, and `--sample` (no real history needed).\n\n## References and assets\n\n- [`scorers\u002Fefficiency.md`](scorers\u002Fefficiency.md) · [`scorers\u002Fcode-quality.md`](scorers\u002Fcode-quality.md) — the two rubrics, preserved verbatim from upstream\n- [`references\u002Ftranscript_scoring_canon.md`](references\u002Ftranscript_scoring_canon.md) — why rubric-anchored LLM judging works and where it fails (7 sources)\n- [`references\u002Fsession_mining_privacy.md`](references\u002Fsession_mining_privacy.md) — the local-only contract, redaction pattern canon (7 sources)\n- [`references\u002Fskill_edit_governance.md`](references\u002Fskill_edit_governance.md) — the filing bar for proposing skill edits (7 sources)\n- [`assets\u002Fsession_scores.example.json`](assets\u002Fsession_scores.example.json) · [`assets\u002Fsuggestions.example.json`](assets\u002Fsuggestions.example.json) · [`assets\u002Freport.example.json`](assets\u002Freport.example.json) — the three handoff shapes\n","# skill-doctor — grade the agent setup from real sessions\n\n> **Privacy is the contract.** Everything runs locally. Transcripts are condensed,\n> secret-redacted, chmod-0600, and never uploaded — the only shareable artifact is\n> the report the user chooses to share.\n\nRun from the repo being graded. Every artifact goes to one fresh scratch dir, never\ninto the repo:\n\n```bash\nRUN=\"$(mktemp -d \"${TMPDIR:-\u002Ftmp}\u002Fskill-doctor-XXXXXXXX\")\"\npython scripts\u002Fcollect_sessions.py --out \"$RUN\"          # 1 — harvest + redact\n```\n\n**1 — Collect.** Scans Claude Code project-history JSONL and Codex rollouts,\ndiscovers repo skills (`.claude\u002Fskills`, `.agents\u002Fskills`, `.codex\u002Fskills`, plugin\nlayouts), detects skill usage (`Skill` invocations, slash commands, SKILL.md paths), samples\nnewest-first, and writes redacted transcripts. Read `$RUN\u002Finventory.json`: if\n`sessions_sampled` is 0, tell the user there is nothing recent to score (suggest\n`--days 90` or `--repo`) and stop. `skills_found` 0 is fine — the report becomes a\ncase for creating skills.\n\n**2 — Score.** `python scripts\u002Fscore_aggregator.py --inventory \"$RUN\u002Finventory.json\"\n--emit-template > \"$RUN\u002Fsession_scores.json\"`. Read each transcript in\n`$RUN\u002Ftranscripts\u002F` and judge it against **both** rubrics — `scorers\u002Fefficiency.md`\nand `scorers\u002Fcode-quality.md`. Fill the template with a **label from the rubric's\ntable** and a 1–3 sentence reason citing transcript specifics. Never invent numeric\nscores — the aggregator derives them from labels. Use `insufficient_evidence` when\na transcript shows no judgeable diff. Also write 1–5 `top_findings`: the most\nimpactful cross-session patterns, concrete and specific.\n\n**3 — Draft edits.** Follow `references\u002Fskill_edit_governance.md` (the filing bar:\nwould a competent agent with the current instructions still fail this way?). For\neach suggestion that clears it, write the full improved SKILL.md to\n`$RUN\u002Fproposed\u002F\u003Cskill>\u002FSKILL.md`, produce `diff -u \u003Ccurrent> \u003Cproposed>`, and record\nit in `$RUN\u002Fsuggestions.json` citing the sampled session id(s) that motivated it.\nZero suggestions is a valid success — say why per finding. Never modify the user's\nreal skill files in this step.\n\n**4 — Aggregate (the gate).** `python scripts\u002Fscore_aggregator.py --inventory\n\"$RUN\u002Finventory.json\" --scores \"$RUN\u002Fsession_scores.json\" --suggestions\n\"$RUN\u002Fsuggestions.json\"`. It validates labels against the rubric tables, refuses\nscores for unsampled sessions, requires substantive reasons, rejects suggestions\nthat cite no scored session, computes `overall = 0.5·efficiency +\n0.35·code_quality + 0.15·skill_coverage`, and writes `report.json`. **Exit 4 is a\nstop**: fix what it names and re-run; never hand-edit report.json around it.\n\n**5 — Render + tell.** `python scripts\u002Frender_report.py --report \"$RUN\u002Freport.json\"`\n→ one self-contained `report.html` (no JS, no CDN, dark-mode + print-to-PDF). Then\ntell the user the grade and the top findings in text, link\n`file:\u002F\u002F$RUN\u002Freport.html`, and ask whether to apply the proposed diffs to their\nreal skills — apply only on an explicit yes, skill by skill.\n\n## Hard rules\n\n1. **Never upload transcripts, session files, or any excerpt.** Local only.\n2. **Labels only, from the rubric tables.** The aggregator owns all arithmetic.\n3. **Every suggestion traces to a scored session** — or it is dropped. Generic best practice is not evidence.\n4. **Zero suggestions is a success**, not a failure to report around.\n5. **Exit 4 from the aggregator is a stop**, not an error to swallow or bypass.\n6. **Never touch the user's real skill files** without an explicit per-skill yes; proposed edits live under `$RUN\u002Fproposed\u002F`.\n7. **A proposed skill edit follows write-a-skill discipline** — trigger phrase in the description, smallest change that expresses the rule, replace over append.\n\n## Scripts\n\n| Script | Role | Exit codes |\n|---|---|---|\n| `scripts\u002Fcollect_sessions.py` | Harvest Claude Code + Codex sessions, redact secrets, sample, inventory | 0 · 3 bad input |\n| `scripts\u002Fscore_aggregator.py` | Validate labels\u002Freasons\u002Fsuggestions, compute grade, emit report.json | 0 · 2 warnings · 3 bad input · 4 validation failure |\n| `scripts\u002Frender_report.py` | report.json → single self-contained report.html | 0 · 3 bad input |\n\nAll support `--help`, `--output json`, and `--sample` (no real history needed).\n\n## References and assets\n\n- [`scorers\u002Fefficiency.md`](scorers\u002Fefficiency.md) · [`scorers\u002Fcode-quality.md`](scorers\u002Fcode-quality.md) — the two rubrics, preserved verbatim from upstream\n- [`references\u002Ftranscript_scoring_canon.md`](references\u002Ftranscript_scoring_canon.md) — why rubric-anchored LLM judging works and where it fails (7 sources)\n- [`references\u002Fsession_mining_privacy.md`](references\u002Fsession_mining_privacy.md) — the local-only contract, redaction pattern canon (7 sources)\n- [`references\u002Fskill_edit_governance.md`](references\u002Fskill_edit_governance.md) — the filing bar for proposing skill edits (7 sources)\n- [`assets\u002Fsession_scores.example.json`](assets\u002Fsession_scores.example.json) · [`assets\u002Fsuggestions.example.json`](assets\u002Fsuggestions.example.json) · [`assets\u002Freport.example.json`](assets\u002Freport.example.json) — the three handoff shapes\n",{"name":5,"license":15,"metadata":49,"description":7,"argument-hint":53},{"version":50,"build_pattern":51,"distinct_from":52},"1.0.0","Rebuild of warpdotdev\u002Fcommon-skills skill-doctor (MIT): harvest → LLM-judges-with-rubrics → deterministic aggregation gate → self-contained HTML report","skillopt-sleep (nightly automated replay loop with adopt gate; this is one interactive graded pass); write-a-skill (authors a skill from expertise; this improves skills from observed session evidence); self-eval (grades this session's own work; this grades a window of past sessions)","[optional: --repo PATH, --days N, or a question about the setup]","main","0da4485785ee599388900be50db1635489d53056",".agents\u002Fskills\u002Fskill-doctor","https:\u002F\u002Fgithub.com\u002FTashima-Tarsh\u002FDisha6.6","https:\u002F\u002Fdisha6.6.thenitishkr.in\u002F","https:\u002F\u002Fgithub.com\u002FTashima-Tarsh","www.thenitishkr","thenitishkr | AI • Cyber-security • Research\r\n","2026-11-08 03:33:25",{"source":8,"skillName":5,"commands":64,"prompt":74,"zipAvailable":75},[65,68,71],{"tool":66,"command":67},"npx","npx skills add Tashima-Tarsh\u002FDisha6.6 --skill skill-doctor",{"tool":69,"command":70},"bunx","bunx skills add Tashima-Tarsh\u002FDisha6.6 --skill skill-doctor",{"tool":72,"command":73},"pnpm","pnpm dlx skills add Tashima-Tarsh\u002FDisha6.6 --skill skill-doctor","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FTashima-Tarsh\u002FDisha6.6\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fskill-doctor\u002FSKILL.md",true,[],[78,108,133,158,183,205],{"skillNo":79,"name":80,"nameZh":6,"description":81,"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":87,"publishedAt":44},"01M6QRD07D4TGNDK6VJ4EHF8BV","youtube-full","Use when the user needs YouTube transcripts, video search, channel browsing, playlist extraction, or content monitoring. Trigger phrases: 'get the transcript for', 'search YouTube for', 'what are the latest videos on', 'list this playlist', 'monitor this channel', or any request involving a YouTube URL, video ID, or @handle. Do NOT use for downloading video or audio files, YouTube engagement data (likes, comments), or private\u002Fage-restricted videos.","https:\u002F\u002Fgithub.com\u002FTashima-Tarsh\u002FDisha6.6\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fyoutube-full\u002FSKILL.md",[84],{"categoryNo":85,"categoryName":86,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000016","图像与多媒体",[88,89,90,91,92,93,94,95,96,97,98,99,100,101,102,103,104,105,106,107],"youtube full","youtube","full","transcript","search","monitoring","data","Video","Audio","list","files","do","get","age","trigger","URL","for","browsing","request","youtube transcripts",{"skillNo":109,"name":110,"nameZh":6,"description":111,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":112,"categories":113,"keywords":114,"publishedAt":44},"01M6QRCJ3112VYPA97YG7KGMC2","x-twitter-growth","X\u002FTwitter growth engine for building audience, crafting viral content, and analyzing engagement. Use when the user wants to grow on X\u002FTwitter, write tweets or threads, analyze their X profile, research competitors on X, plan a posting strategy, or optimize engagement. Complements social-content (generic multi-platform) with X-specific depth: algorithm mechanics, thread engineering, reply strategy, profile optimization, and competitive intelligence via web search.","https:\u002F\u002Fgithub.com\u002FTashima-Tarsh\u002FDisha6.6\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fx-twitter-growth\u002FSKILL.md",[],[115,116,117,118,92,119,120,121,122,123,124,125,126,127,128,129,130,131,132,104],"twitter","x twitter growth","growth","research","content","engineering","plan","web search","competitors","analyze","engine","write","strategy","use","platform","grow","posting","competitive",{"skillNo":134,"name":135,"nameZh":6,"description":136,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":137,"categories":138,"keywords":140,"publishedAt":44},"01M6QRBN3EHQNJY42RERP7A149","write-a-skill","Create new agent skills with proper structure, progressive disclosure, and bundled resources. Use when user wants to create, write, build, or author a new skill.","https:\u002F\u002Fgithub.com\u002FTashima-Tarsh\u002FDisha6.6\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fwrite-a-skill\u002FSKILL.md",[139],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},[141,126,142,143,144,145,146,147,128,148,149,54,150,151,152,153,154,155,156,157],"write a skill","github","create","https","productivity","matt pocock","direct","example","build","new skill","structure","new agent","resources","with","tree","progressive disclosure","author",{"skillNo":159,"name":160,"nameZh":6,"description":161,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":162,"categories":163,"keywords":164,"publishedAt":44},"01M6QRB6G8P33PNGAF9Y69EJ9T","wrap-up","Close out a launched Claude Managed Agent — recap every primitive the founder now owns, regenerate the single-file overview page, and suggest the next 1-2 upgrades. Use when the user says \"wrap up\", \"close this out\", \"what do I own now\", \"give me the summary\", \"recap the agent\", or when the orchestrator routes phase=wrap-up. primitives_inventory.py tables everything owned (agent, environment, session, memory, outcome, deployment); overview_page.py regenerates a self-contained .\u002Fmy-agent\u002Fagent-overview.html; upgrade_suggester.py ranks the next moves from recorded deferrals plus standing hardening steps. Companion to run-without-you; the last stop before phase=done.","https:\u002F\u002Fgithub.com\u002FTashima-Tarsh\u002FDisha6.6\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fwrap-up\u002FSKILL.md",[],[165,166,167,168,169,170,171,172,173,128,174,99,175,176,177,178,179,180,181,182],"wrap up","up","wrap","gemini","deployment","run","file","hardening","closeout","stop","upgrade","founder","close","companion","you","tables","directions","phase",{"skillNo":184,"name":185,"nameZh":6,"description":186,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":187,"categories":188,"keywords":190,"publishedAt":44},"01M6QRA5AYC1RBFZ39GTWGS3N8","workflow-builder","Design and write deterministic multi-agent workflow scripts (.js files in .claude\u002Fworkflows\u002F) for Claude Code's Workflow tool. Use when a user wants to build, create, author, scaffold, or run a custom Claude Code workflow, orchestrate sub-agents (fan-out, pipeline, loop, judge-panel), or automate a repeatable multi-step task across fresh-context agents.","https:\u002F\u002Fgithub.com\u002FTashima-Tarsh\u002FDisha6.6\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fworkflow-builder\u002FSKILL.md",[189],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},[191,192,193,194,195,143,170,27,196,197,43,198,126,199,98,200,201,202,203,204],"workflow","workflow builder","builder","design","workflows","orchestrate","pipeline","multi-agent","context","across","fresh","scripts","judge","claude code workflow",{"skillNo":206,"name":207,"nameZh":6,"description":208,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":209,"categories":210,"keywords":211,"publishedAt":44},"01M6QR7QMCZESKQA0ERW1E657M","weekly-review","Use when someone wants to run a weekly review, close open loops, audit stalled projects and commitments, get their system back to trusted, restart a lapsed review habit, or says \"\u002Fcs:weekly-review\". Walks David Allen's three-phase loop — GET CLEAR, GET CURRENT, GET CREATIVE — with deterministic scripts that inventory open loops, gate the checklist with named gaps, and score commitment health 0-100.","https:\u002F\u002Fgithub.com\u002FTashima-Tarsh\u002FDisha6.6\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fweekly-review\u002FSKILL.md",[],[212,213,214,215,216,217,218,219,220,43,221,222,223,36,224,225,100,226,227,182],"review","weekly review","weekly","deterministic scripts","reflect","feeds","inventory","open","team","projects","project-management","scanner","back","project","sprint","cadence"]