[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7C1TF7T5XWJDH42PD06ADB3":3,"skill-same:01M7C1TF7T5XWJDH42PD06ADB3":50},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":15,"categories":16,"keywords":17,"publishedAt":18,"linkOnly":19,"markdownContent":20,"markdownBody":21,"frontMatter":22,"refName":23,"commitSha":24,"skillDirectory":25,"forksCount":26,"repositoryHtmlUrl":27,"repositoryHomepageUrl":6,"ownerHtmlUrl":28,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":29,"install":30,"resources":43},"01M7C1TF7T5XWJDH42PD06ADB3","audit-progress",null,"Use when an iteration has just finished and you need to verify behavior evidence quality in three tiers — deep evidence for current stories, impacted behavior for touched scenarios, and sentinel corpus for high-value regression detection.","zak-keown\u002Fmoe","zak-keown","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F320717241?v=4","01M7BZFXME0NW6TQX0H7AZM2KS","01M7BZFXN32VR0JN5AATRD53H4",0,"Apache-2.0","https:\u002F\u002Fgithub.com\u002Fzak-keown\u002Fmoe\u002Fblob\u002Fmain\u002Fplugins\u002Fmoe\u002Fskills\u002Faudit-progress\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: audit-progress\ndescription: Use when an iteration has just finished and you need to verify behavior evidence quality in three tiers — deep evidence for current stories, impacted behavior for touched scenarios, and sentinel corpus for high-value regression detection.\n---\n\n# Auditing Progress\n\n## Overview\n\nRuns after every iteration as part of the planning cycle. Verifies behavior evidence quality in three tiers using **parallel adversarial review (PAR)** — two paired auditor subagents evaluate the same work in parallel with competitive framing.\n\nThe audit answers: \"Does durable, reusable evidence exist at the correct seam for every externally observable behavior this iteration touched?\"\n\n## When to Use\n\nInvoked by `iterate` after every `run-iteration` call, before picking the next iteration.\n\n## Audit Process\n\n### 1. Partition the audit into three tiers\n\nRead the per-epic requirement files in `docs\u002Fmoe\u002Fiterations\u002Frequirements\u002F`, `docs\u002Fmoe\u002Fiterations\u002Fbehavior-scenarios.md`, and `docs\u002Fmoe\u002Fiterations\u002Fbehavior-corpus.md`:\n\n- **Tier 1 — Deep evidence:** stories marked `done:ITER-\u003Ccurrent>` and scenarios added or updated in this iteration. Audit every AC and its proof obligation thoroughly.\n- **Tier 2 — Impacted behavior:** all existing scenarios whose owning stories had code changes in this iteration (even if those stories were completed in earlier iterations). Verify the scenarios still pass.\n- **Tier 3 — Sentinel corpus:** all scenarios with run cadence `sentinel` in the behavior corpus. Compare against the pre-iteration baseline from `run-iteration` step 3.\n\n### 2. Dispatch paired auditor subagents (PAR)\n\nFollowing the PAR methodology in [skills\u002F_shared\u002Fparallel-adversarial-review.md](..\u002F_shared\u002Fparallel-adversarial-review.md), resolved relative to this loaded document:\n\n1. Build the auditor prompt using `auditor-subagent-prompt.md`. Include ALL THREE tiers:\n   - Tier 1: full story cards with proof obligations + new\u002Fchanged scenario cards\n   - Tier 2: impacted scenario cards + their current test results\n   - Tier 3: sentinel scenario IDs + baseline results + current results\n2. Resolve [skills\u002F_shared\u002Fpar-reviewer-wrapper.md](..\u002F_shared\u002Fpar-reviewer-wrapper.md) relative to this loaded document and wrap in its competitive framing\n3. Dispatch TWO auditor subagents in parallel\n4. Wait for both to return\n\n### 3. Aggregate findings\n\nFollowing PAR aggregation rules:\n- Same finding from both auditors → one finding, high confidence\n- Finding from only one auditor → separate finding, still actionable\n- Severity disagreement → take the more severe assessment, always fix it\n\n### 4. Process results\n\n- **If gaps found** (any AC fails, evidence is too weak, sentinel regression detected):\n  - For AC failures: append gap stories to `requirements\u002F` (status `pending`) or flip existing stories back from `done` to `pending`\n  - For weak evidence: create evidence-improvement stories (add scenario, strengthen seam)\n  - For sentinel regressions: create regression-fix stories with CRITICAL priority\n  - Revise `roadmap.md` to add a follow-up iteration for the gaps\n- **If clean** (all tiers pass, evidence is adequate):\n  - The iteration is confirmed done\n  - Return clean signal to the orchestrator\n\n### 5. Return control\n\nReturn the audit result (clean or gaps) to the orchestrator. The orchestrator decides whether to loop or terminate.\n\n## Quick Reference\n\n| Tier | What it checks | Failure means |\n|---|---|---|\n| Deep evidence | Every AC + proof obligation for current iteration | Story not done, evidence too weak |\n| Impacted behavior | Scenarios whose surfaces were touched | Stale or broken scenario |\n| Sentinel corpus | High-value journey scenarios | Regression in previously-working behavior |\n\n| Reads | Writes | Dispatches |\n|---|---|---|\n| `requirements\u002F`, `behavior-scenarios.md`, `behavior-corpus.md`, product code\u002Ftests | `requirements\u002F` (gaps), `roadmap.md` (new iteration) if gaps, `behavior-scenarios.md` (stale flags) | **Two** auditor subagents in parallel (PAR) |\n\n## References\n\n- [skills\u002F_shared\u002Fparallel-adversarial-review.md](..\u002F_shared\u002Fparallel-adversarial-review.md) — PAR methodology; resolve relative to this loaded document\n- [skills\u002F_shared\u002Fpar-reviewer-wrapper.md](..\u002F_shared\u002Fpar-reviewer-wrapper.md) — competitive framing wrapper; resolve relative to this loaded document\n- [skills\u002F_shared\u002Fbehavior-evidence-formats.md](..\u002F_shared\u002Fbehavior-evidence-formats.md) — scenario and proof obligation formats; resolve relative to this loaded document\n- `auditor-subagent-prompt.md` — auditor-specific prompt template\n","# Auditing Progress\n\n## Overview\n\nRuns after every iteration as part of the planning cycle. Verifies behavior evidence quality in three tiers using **parallel adversarial review (PAR)** — two paired auditor subagents evaluate the same work in parallel with competitive framing.\n\nThe audit answers: \"Does durable, reusable evidence exist at the correct seam for every externally observable behavior this iteration touched?\"\n\n## When to Use\n\nInvoked by `iterate` after every `run-iteration` call, before picking the next iteration.\n\n## Audit Process\n\n### 1. Partition the audit into three tiers\n\nRead the per-epic requirement files in `docs\u002Fmoe\u002Fiterations\u002Frequirements\u002F`, `docs\u002Fmoe\u002Fiterations\u002Fbehavior-scenarios.md`, and `docs\u002Fmoe\u002Fiterations\u002Fbehavior-corpus.md`:\n\n- **Tier 1 — Deep evidence:** stories marked `done:ITER-\u003Ccurrent>` and scenarios added or updated in this iteration. Audit every AC and its proof obligation thoroughly.\n- **Tier 2 — Impacted behavior:** all existing scenarios whose owning stories had code changes in this iteration (even if those stories were completed in earlier iterations). Verify the scenarios still pass.\n- **Tier 3 — Sentinel corpus:** all scenarios with run cadence `sentinel` in the behavior corpus. Compare against the pre-iteration baseline from `run-iteration` step 3.\n\n### 2. Dispatch paired auditor subagents (PAR)\n\nFollowing the PAR methodology in [skills\u002F_shared\u002Fparallel-adversarial-review.md](..\u002F_shared\u002Fparallel-adversarial-review.md), resolved relative to this loaded document:\n\n1. Build the auditor prompt using `auditor-subagent-prompt.md`. Include ALL THREE tiers:\n   - Tier 1: full story cards with proof obligations + new\u002Fchanged scenario cards\n   - Tier 2: impacted scenario cards + their current test results\n   - Tier 3: sentinel scenario IDs + baseline results + current results\n2. Resolve [skills\u002F_shared\u002Fpar-reviewer-wrapper.md](..\u002F_shared\u002Fpar-reviewer-wrapper.md) relative to this loaded document and wrap in its competitive framing\n3. Dispatch TWO auditor subagents in parallel\n4. Wait for both to return\n\n### 3. Aggregate findings\n\nFollowing PAR aggregation rules:\n- Same finding from both auditors → one finding, high confidence\n- Finding from only one auditor → separate finding, still actionable\n- Severity disagreement → take the more severe assessment, always fix it\n\n### 4. Process results\n\n- **If gaps found** (any AC fails, evidence is too weak, sentinel regression detected):\n  - For AC failures: append gap stories to `requirements\u002F` (status `pending`) or flip existing stories back from `done` to `pending`\n  - For weak evidence: create evidence-improvement stories (add scenario, strengthen seam)\n  - For sentinel regressions: create regression-fix stories with CRITICAL priority\n  - Revise `roadmap.md` to add a follow-up iteration for the gaps\n- **If clean** (all tiers pass, evidence is adequate):\n  - The iteration is confirmed done\n  - Return clean signal to the orchestrator\n\n### 5. Return control\n\nReturn the audit result (clean or gaps) to the orchestrator. The orchestrator decides whether to loop or terminate.\n\n## Quick Reference\n\n| Tier | What it checks | Failure means |\n|---|---|---|\n| Deep evidence | Every AC + proof obligation for current iteration | Story not done, evidence too weak |\n| Impacted behavior | Scenarios whose surfaces were touched | Stale or broken scenario |\n| Sentinel corpus | High-value journey scenarios | Regression in previously-working behavior |\n\n| Reads | Writes | Dispatches |\n|---|---|---|\n| `requirements\u002F`, `behavior-scenarios.md`, `behavior-corpus.md`, product code\u002Ftests | `requirements\u002F` (gaps), `roadmap.md` (new iteration) if gaps, `behavior-scenarios.md` (stale flags) | **Two** auditor subagents in parallel (PAR) |\n\n## References\n\n- [skills\u002F_shared\u002Fparallel-adversarial-review.md](..\u002F_shared\u002Fparallel-adversarial-review.md) — PAR methodology; resolve relative to this loaded document\n- [skills\u002F_shared\u002Fpar-reviewer-wrapper.md](..\u002F_shared\u002Fpar-reviewer-wrapper.md) — competitive framing wrapper; resolve relative to this loaded document\n- [skills\u002F_shared\u002Fbehavior-evidence-formats.md](..\u002F_shared\u002Fbehavior-evidence-formats.md) — scenario and proof obligation formats; resolve relative to this loaded document\n- `auditor-subagent-prompt.md` — auditor-specific prompt template\n",{"name":5,"description":7},"main","728894f3f85fbd4e788f015ddfd72bb6155d5dd5","plugins\u002Fmoe\u002Fskills\u002Faudit-progress",1,"https:\u002F\u002Fgithub.com\u002Fzak-keown\u002Fmoe","https:\u002F\u002Fgithub.com\u002Fzak-keown","2026-09-05 06:29:06",{"source":8,"skillName":5,"commands":31,"prompt":41,"zipAvailable":42},[32,35,38],{"tool":33,"command":34},"npx","npx skills add zak-keown\u002Fmoe --skill audit-progress",{"tool":36,"command":37},"bunx","bunx skills add zak-keown\u002Fmoe --skill audit-progress",{"tool":39,"command":40},"pnpm","pnpm dlx skills add zak-keown\u002Fmoe --skill audit-progress","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fzak-keown\u002Fmoe\u002Fblob\u002Fmain\u002Fplugins\u002Fmoe\u002Fskills\u002Faudit-progress\u002FSKILL.md",true,[44],{"path":45,"resourceType":46,"resourceTypeDesc":47,"sizeBytes":48,"sourceHtmlUrl":49},"auditor-subagent-prompt.md","REFERENCE","参考文档",3719,"https:\u002F\u002Fgithub.com\u002Fzak-keown\u002Fmoe\u002Fblob\u002Fmain\u002Fplugins\u002Fmoe\u002Fskills\u002Faudit-progress\u002Fauditor-subagent-prompt.md",[51,58,65,72,79,86],{"skillNo":52,"name":53,"nameZh":6,"description":54,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":55,"categories":56,"keywords":57,"publishedAt":18},"01M7C1Z5362Y8NVRZ69HWP0ZD0","write-skill","Use when creating new skills, editing existing skills, or verifying skills work before deployment","https:\u002F\u002Fgithub.com\u002Fzak-keown\u002Fmoe\u002Fblob\u002Fmain\u002Fplugins\u002Fmoe\u002Fskills\u002Fwrite-skill\u002FSKILL.md",[],[],{"skillNo":59,"name":60,"nameZh":6,"description":61,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":62,"categories":63,"keywords":64,"publishedAt":18},"01M7C1YZ9966WK9R6ZRPCGWF3G","write-plan","Use when you have a spec or requirements for a multi-step task, before touching code","https:\u002F\u002Fgithub.com\u002Fzak-keown\u002Fmoe\u002Fblob\u002Fmain\u002Fplugins\u002Fmoe\u002Fskills\u002Fwrite-plan\u002FSKILL.md",[],[],{"skillNo":66,"name":67,"nameZh":6,"description":68,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":69,"categories":70,"keywords":71,"publishedAt":18},"01M7C1YMR4SJD7BPBBPXZCVGVH","write-clearly","Apply Strunk's timeless writing rules to ANY prose humans will read—documentation, commit messages, error messages, explanations, reports, or UI text. Makes your writing clearer, stronger, and more professional.","https:\u002F\u002Fgithub.com\u002Fzak-keown\u002Fmoe\u002Fblob\u002Fmain\u002Fplugins\u002Fmoe\u002Fskills\u002Fwrite-clearly\u002FSKILL.md",[],[],{"skillNo":73,"name":74,"nameZh":6,"description":75,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":76,"categories":77,"keywords":78,"publishedAt":18},"01M7C1YH9805YSM0N20VQAVSXF","windows-vm","Create, manage, or connect to a headless Windows 11 VM running in Docker with SSH access. Use when the user wants to spin up, stop, restart, or SSH into a Windows VM.","https:\u002F\u002Fgithub.com\u002Fzak-keown\u002Fmoe\u002Fblob\u002Fmain\u002Fplugins\u002Fmoe\u002Fskills\u002Fwindows-vm\u002FSKILL.md",[],[],{"skillNo":80,"name":81,"nameZh":6,"description":82,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":83,"categories":84,"keywords":85,"publishedAt":18},"01M7C1YD87SCNEJ2C9B8HFR2NQ","verify-completion","Use when about to claim work is complete, fixed, or passing, before committing or creating MRs - requires running verification commands and confirming output before making any success claims; evidence before assertions always","https:\u002F\u002Fgithub.com\u002Fzak-keown\u002Fmoe\u002Fblob\u002Fmain\u002Fplugins\u002Fmoe\u002Fskills\u002Fverify-completion\u002FSKILL.md",[],[],{"skillNo":87,"name":88,"nameZh":6,"description":89,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":90,"categories":91,"keywords":92,"publishedAt":18},"01M7C1YARDEHT0TJ9BRG30ZCF4","using-moe","Use when starting any conversation - establishes how to find and use skills, requiring skill invocation before ANY response including clarifying questions","https:\u002F\u002Fgithub.com\u002Fzak-keown\u002Fmoe\u002Fblob\u002Fmain\u002Fplugins\u002Fmoe\u002Fskills\u002Fusing-moe\u002FSKILL.md",[],[]]