[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7C0YAKKW9CVRA5ATNCSW9HT":3,"skill-same:01M7C0YAKKW9CVRA5ATNCSW9HT":60},{"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},"01M7C0YAKKW9CVRA5ATNCSW9HT","run-iteration",null,"Use when executing the next pending iteration from an iterate roadmap — picks the iteration, decomposes into code and evidence tasks, runs sentinel corpus baseline, dispatches implement-tasks, runs impacted + sentinel scenarios, and updates artifacts.","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\u002F.claude-plugin\u002Fskills\u002Frun-iteration\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: run-iteration\ndescription: Use when executing the next pending iteration from an iterate roadmap — picks the iteration, decomposes into code and evidence tasks, runs sentinel corpus baseline, dispatches implement-tasks, runs impacted + sentinel scenarios, and updates artifacts.\n---\n\n# Running an Iteration\n\n## Overview\n\nDrives one iteration: picks the next pending, runs sentinel corpus baseline, runs pre-iteration scope review via PAR, decomposes into code and evidence tasks, dispatches `implement-tasks`, runs impacted + sentinel scenarios at wrap-up, and updates the roadmap and iteration log.\n\n## When to Use\n\nInvoked by `iterate` inside the main loop. Each invocation runs exactly one iteration. After return, the orchestrator invokes `audit-progress`.\n\n## Script Location\n\nAll scripts referenced below live in this skill's `scripts\u002F` directory, next to this SKILL.md file.\n\n## Iteration Process\n\n### 1. Pick next iteration\n\nRead `docs\u002Fmoe\u002Fiterations\u002Froadmap.md`, find the first iteration with status `pending`.\n\n### 2. Load scope context\n\nRead the per-epic files in `docs\u002Fmoe\u002Fiterations\u002Frequirements\u002F` to load the full story cards for each committed story ID. Only read the epic files that contain stories for this iteration — not all of them. Also:\n- Load the next 3 pending iterations from the roadmap for look-ahead\n- Read `docs\u002Fmoe\u002Fiterations\u002Fbehavior-scenarios.md` to identify impacted scenarios\n- Read `docs\u002Fmoe\u002Fiterations\u002Fbehavior-corpus.md` to identify sentinel scenarios\n\n### 3. Run sentinel corpus baseline\n\nBefore any code changes, run every scenario in the behavior corpus with run cadence `sentinel`:\n\n- If all sentinels pass: record baseline as clean, proceed\n- If any sentinel fails: the failure predates this iteration. Record it, create a gap story for it, but proceed with the iteration (the gap will be addressed in a follow-up)\n\nThis establishes whether regressions exist before the current iteration starts.\n\n### 4. Pre-iteration consistency audit\n\nBefore planning any work, verify that artifact state is consistent:\n\n1. **Citation check:** Resolve [skills\u002Frun-iteration\u002Fscripts\u002Fcheck_citations.mjs](scripts\u002Fcheck_citations.mjs) relative to this loaded document, then invoke it as `node \"\u003Cresolved-check_citations.mjs>\" docs\u002Fmoe\u002Fiterations\u002Froadmap.md docs\u002Fmoe\u002Fiterations\u002Frequirements\u002F`. If citations fail, stop and fix the roadmap.\n2. **Status reconciliation:** For each story in this iteration's scope, verify:\n   - Stories listed in the roadmap iteration are not already marked `done:ITER-XXXX` in the requirements index (unless code\u002Ftests actually exist for them)\n   - Stories marked `done` in the requirements index actually have corresponding code and tests\n   - No story appears in multiple pending iterations\n3. **Epic counter validation:** Spot-check that epic progress counters match the actual count of `done` stories.\n\nIf any inconsistencies are found, reconcile before proceeding. Do not trust any single artifact blindly — cross-check.\n\n### 5. Pre-iteration scope review (PAR)\n\nFollowing [skills\u002F_shared\u002Fparallel-adversarial-review.md](..\u002F_shared\u002Fparallel-adversarial-review.md), resolved relative to this loaded document:\n\n1. Build the scope reviewer prompt using `scope-reviewer-prompt.md`\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 scope reviewers in parallel\n4. Aggregate findings: same issue from both = high confidence, unique = still actionable, severity disagreement = take worst\n5. If REVISE recommended: adjust iteration scope and re-review. Loop until APPROVE.\n\n### 6. Decompose into code tasks AND evidence tasks\n\nBreak the iteration scope into TDD-sized tasks. Each task = failing test → implementation → passing test → commit.\n\n**Evidence tasks:** In addition to code tasks, identify:\n- Which existing scenarios are impacted by this iteration's changes\n- Which new scenarios must be added (from the story proof obligations)\n- Which scenario harnesses need to be extended\n- Which behavior corpus entries need updated execution commands\n\nEvidence tasks are first-class — they produce scenario updates, test harness extensions, and corpus index entries. They are NOT afterthoughts. Interleave evidence tasks with code tasks: after implementing a feature, the next task should be extending or adding the scenario that proves it.\n\n**Cross-iteration dependencies:** Some stories reference subsystems that don't exist yet. For these, implement the thinnest abstraction boundary that satisfies the story's ACs without coupling to the future implementation. Prefer a single clean interface over a decomposed hierarchy — the real implementation will define its own internal structure when it arrives. Document the dependency with a TODO comment citing the future iteration. Do NOT defer the story silently or force premature integration.\n\n### 7. Dispatch implement-tasks\n\nPass the task list (code + evidence tasks) and iteration context to `implement-tasks`. Wait for completion.\n\n### 8. Post-iteration scenario runs\n\nAfter all tasks complete, run:\n\n1. **Impacted scenarios:** every scenario in the behavior corpus whose owning stories were touched by this iteration\n2. **Sentinel scenarios:** every scenario with run cadence `sentinel`\n\nIf any impacted or sentinel scenario fails that passed at baseline (step 3), this iteration introduced a regression. Create a fix task and re-dispatch to `implement-tasks`.\n\n### 9. Resolve cross-iteration TODOs\n\nGrep the codebase for `TODO(ITER-\u003Ccurrent>)` markers — these are interface stubs that earlier iterations created expecting THIS iteration to provide the real implementation.\n\nFor each marker found:\n1. Verify the real implementation now exists (not still a stub\u002FNoOp)\n2. If resolved: remove the TODO comment\n3. If NOT resolved: the iteration is incomplete — add a fix task and re-dispatch\n\nThis step is a hard gate. An iteration that leaves its own TODO markers in the code is not done.\n\n### 10. Wrap up\n\n- Verify all iteration stories' ACs pass (sanity check before audit)\n- Verify all proof obligations for observable ACs have corresponding scenario evidence\n- Verify no `TODO(ITER-\u003Ccurrent>)` markers remain in the codebase (step 9)\n- Mark stories `done:ITER-NNNN` in the relevant epic files under `requirements\u002F`\n- Update scenario automation status and execution commands in `behavior-scenarios.md`\n- Update the behavior corpus index in `behavior-corpus.md`\n- Update iteration status in `roadmap.md` to `done`\n- Append entry to `docs\u002Fmoe\u002Fiterations\u002Fiteration-log.md` — include:\n  - Stories delivered\n  - Scenarios added or updated\n  - Sentinel corpus results\n- Validate: resolve [skills\u002Frun-iteration\u002Fscripts\u002Fvalidate_iteration_log.mjs](scripts\u002Fvalidate_iteration_log.mjs) relative to this loaded document, then invoke it as `node \"\u003Cresolved-validate_iteration_log.mjs>\" docs\u002Fmoe\u002Fiterations\u002Fiteration-log.md`\n- After each task commit, update the progress snapshot with `moe jig progress update --phase ... --task ... --iterations ... --event ...`. If `moe-jig` is not on PATH, overwrite `docs\u002Fmoe\u002Fiterations\u002Fprogress.md` manually.\n- Return control to orchestrator (do NOT invoke `audit-progress` — that's the orchestrator's job)\n\n## Quick Reference\n\n| Step | Tool\u002FSkill | Purpose |\n|---|---|---|\n| Sentinel baseline | Run sentinel scenarios | Establish pre-iteration regression state |\n| Citation check | `scripts\u002Fcheck_citations.mjs` | Mechanical: cited stories exist |\n| Scope review | PAR + `scope-reviewer-prompt.md` | Semantic: scope, scenarios, splitting, boxing-in |\n| Task execution | `implement-tasks` | TDD code + evidence implementation |\n| Post-iteration runs | Run impacted + sentinel scenarios | Catch regressions |\n| TODO resolution | `grep -rn 'TODO(ITER-\u003Ccurrent>)'` | Cross-iteration stubs resolved |\n| Wrap up | `scripts\u002Fvalidate_iteration_log.mjs` | Artifact validation |\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\u002Fbehavior-evidence-formats.md](..\u002F_shared\u002Fbehavior-evidence-formats.md) — scenario and proof obligation formats; resolve relative to this loaded document\n- `scope-reviewer-prompt.md` — scope reviewer prompt template\n- [check_citations.mjs](.\u002Fscripts\u002Fcheck_citations.mjs) — mechanical citation check\n","# Running an Iteration\n\n## Overview\n\nDrives one iteration: picks the next pending, runs sentinel corpus baseline, runs pre-iteration scope review via PAR, decomposes into code and evidence tasks, dispatches `implement-tasks`, runs impacted + sentinel scenarios at wrap-up, and updates the roadmap and iteration log.\n\n## When to Use\n\nInvoked by `iterate` inside the main loop. Each invocation runs exactly one iteration. After return, the orchestrator invokes `audit-progress`.\n\n## Script Location\n\nAll scripts referenced below live in this skill's `scripts\u002F` directory, next to this SKILL.md file.\n\n## Iteration Process\n\n### 1. Pick next iteration\n\nRead `docs\u002Fmoe\u002Fiterations\u002Froadmap.md`, find the first iteration with status `pending`.\n\n### 2. Load scope context\n\nRead the per-epic files in `docs\u002Fmoe\u002Fiterations\u002Frequirements\u002F` to load the full story cards for each committed story ID. Only read the epic files that contain stories for this iteration — not all of them. Also:\n- Load the next 3 pending iterations from the roadmap for look-ahead\n- Read `docs\u002Fmoe\u002Fiterations\u002Fbehavior-scenarios.md` to identify impacted scenarios\n- Read `docs\u002Fmoe\u002Fiterations\u002Fbehavior-corpus.md` to identify sentinel scenarios\n\n### 3. Run sentinel corpus baseline\n\nBefore any code changes, run every scenario in the behavior corpus with run cadence `sentinel`:\n\n- If all sentinels pass: record baseline as clean, proceed\n- If any sentinel fails: the failure predates this iteration. Record it, create a gap story for it, but proceed with the iteration (the gap will be addressed in a follow-up)\n\nThis establishes whether regressions exist before the current iteration starts.\n\n### 4. Pre-iteration consistency audit\n\nBefore planning any work, verify that artifact state is consistent:\n\n1. **Citation check:** Resolve [skills\u002Frun-iteration\u002Fscripts\u002Fcheck_citations.mjs](scripts\u002Fcheck_citations.mjs) relative to this loaded document, then invoke it as `node \"\u003Cresolved-check_citations.mjs>\" docs\u002Fmoe\u002Fiterations\u002Froadmap.md docs\u002Fmoe\u002Fiterations\u002Frequirements\u002F`. If citations fail, stop and fix the roadmap.\n2. **Status reconciliation:** For each story in this iteration's scope, verify:\n   - Stories listed in the roadmap iteration are not already marked `done:ITER-XXXX` in the requirements index (unless code\u002Ftests actually exist for them)\n   - Stories marked `done` in the requirements index actually have corresponding code and tests\n   - No story appears in multiple pending iterations\n3. **Epic counter validation:** Spot-check that epic progress counters match the actual count of `done` stories.\n\nIf any inconsistencies are found, reconcile before proceeding. Do not trust any single artifact blindly — cross-check.\n\n### 5. Pre-iteration scope review (PAR)\n\nFollowing [skills\u002F_shared\u002Fparallel-adversarial-review.md](..\u002F_shared\u002Fparallel-adversarial-review.md), resolved relative to this loaded document:\n\n1. Build the scope reviewer prompt using `scope-reviewer-prompt.md`\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 scope reviewers in parallel\n4. Aggregate findings: same issue from both = high confidence, unique = still actionable, severity disagreement = take worst\n5. If REVISE recommended: adjust iteration scope and re-review. Loop until APPROVE.\n\n### 6. Decompose into code tasks AND evidence tasks\n\nBreak the iteration scope into TDD-sized tasks. Each task = failing test → implementation → passing test → commit.\n\n**Evidence tasks:** In addition to code tasks, identify:\n- Which existing scenarios are impacted by this iteration's changes\n- Which new scenarios must be added (from the story proof obligations)\n- Which scenario harnesses need to be extended\n- Which behavior corpus entries need updated execution commands\n\nEvidence tasks are first-class — they produce scenario updates, test harness extensions, and corpus index entries. They are NOT afterthoughts. Interleave evidence tasks with code tasks: after implementing a feature, the next task should be extending or adding the scenario that proves it.\n\n**Cross-iteration dependencies:** Some stories reference subsystems that don't exist yet. For these, implement the thinnest abstraction boundary that satisfies the story's ACs without coupling to the future implementation. Prefer a single clean interface over a decomposed hierarchy — the real implementation will define its own internal structure when it arrives. Document the dependency with a TODO comment citing the future iteration. Do NOT defer the story silently or force premature integration.\n\n### 7. Dispatch implement-tasks\n\nPass the task list (code + evidence tasks) and iteration context to `implement-tasks`. Wait for completion.\n\n### 8. Post-iteration scenario runs\n\nAfter all tasks complete, run:\n\n1. **Impacted scenarios:** every scenario in the behavior corpus whose owning stories were touched by this iteration\n2. **Sentinel scenarios:** every scenario with run cadence `sentinel`\n\nIf any impacted or sentinel scenario fails that passed at baseline (step 3), this iteration introduced a regression. Create a fix task and re-dispatch to `implement-tasks`.\n\n### 9. Resolve cross-iteration TODOs\n\nGrep the codebase for `TODO(ITER-\u003Ccurrent>)` markers — these are interface stubs that earlier iterations created expecting THIS iteration to provide the real implementation.\n\nFor each marker found:\n1. Verify the real implementation now exists (not still a stub\u002FNoOp)\n2. If resolved: remove the TODO comment\n3. If NOT resolved: the iteration is incomplete — add a fix task and re-dispatch\n\nThis step is a hard gate. An iteration that leaves its own TODO markers in the code is not done.\n\n### 10. Wrap up\n\n- Verify all iteration stories' ACs pass (sanity check before audit)\n- Verify all proof obligations for observable ACs have corresponding scenario evidence\n- Verify no `TODO(ITER-\u003Ccurrent>)` markers remain in the codebase (step 9)\n- Mark stories `done:ITER-NNNN` in the relevant epic files under `requirements\u002F`\n- Update scenario automation status and execution commands in `behavior-scenarios.md`\n- Update the behavior corpus index in `behavior-corpus.md`\n- Update iteration status in `roadmap.md` to `done`\n- Append entry to `docs\u002Fmoe\u002Fiterations\u002Fiteration-log.md` — include:\n  - Stories delivered\n  - Scenarios added or updated\n  - Sentinel corpus results\n- Validate: resolve [skills\u002Frun-iteration\u002Fscripts\u002Fvalidate_iteration_log.mjs](scripts\u002Fvalidate_iteration_log.mjs) relative to this loaded document, then invoke it as `node \"\u003Cresolved-validate_iteration_log.mjs>\" docs\u002Fmoe\u002Fiterations\u002Fiteration-log.md`\n- After each task commit, update the progress snapshot with `moe jig progress update --phase ... --task ... --iterations ... --event ...`. If `moe-jig` is not on PATH, overwrite `docs\u002Fmoe\u002Fiterations\u002Fprogress.md` manually.\n- Return control to orchestrator (do NOT invoke `audit-progress` — that's the orchestrator's job)\n\n## Quick Reference\n\n| Step | Tool\u002FSkill | Purpose |\n|---|---|---|\n| Sentinel baseline | Run sentinel scenarios | Establish pre-iteration regression state |\n| Citation check | `scripts\u002Fcheck_citations.mjs` | Mechanical: cited stories exist |\n| Scope review | PAR + `scope-reviewer-prompt.md` | Semantic: scope, scenarios, splitting, boxing-in |\n| Task execution | `implement-tasks` | TDD code + evidence implementation |\n| Post-iteration runs | Run impacted + sentinel scenarios | Catch regressions |\n| TODO resolution | `grep -rn 'TODO(ITER-\u003Ccurrent>)'` | Cross-iteration stubs resolved |\n| Wrap up | `scripts\u002Fvalidate_iteration_log.mjs` | Artifact validation |\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\u002Fbehavior-evidence-formats.md](..\u002F_shared\u002Fbehavior-evidence-formats.md) — scenario and proof obligation formats; resolve relative to this loaded document\n- `scope-reviewer-prompt.md` — scope reviewer prompt template\n- [check_citations.mjs](.\u002Fscripts\u002Fcheck_citations.mjs) — mechanical citation check\n",{"name":5,"description":7},"main","728894f3f85fbd4e788f015ddfd72bb6155d5dd5","plugins\u002Fmoe\u002F.claude-plugin\u002Fskills\u002Frun-iteration",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 run-iteration",{"tool":36,"command":37},"bunx","bunx skills add zak-keown\u002Fmoe --skill run-iteration",{"tool":39,"command":40},"pnpm","pnpm dlx skills add zak-keown\u002Fmoe --skill run-iteration","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fzak-keown\u002Fmoe\u002Fblob\u002Fmain\u002Fplugins\u002Fmoe\u002F.claude-plugin\u002Fskills\u002Frun-iteration\u002FSKILL.md",true,[44,50,56],{"path":45,"resourceType":46,"resourceTypeDesc":47,"sizeBytes":48,"sourceHtmlUrl":49},"scope-reviewer-prompt.md","REFERENCE","参考文档",3409,"https:\u002F\u002Fgithub.com\u002Fzak-keown\u002Fmoe\u002Fblob\u002Fmain\u002Fplugins\u002Fmoe\u002F.claude-plugin\u002Fskills\u002Frun-iteration\u002Fscope-reviewer-prompt.md",{"path":51,"resourceType":52,"resourceTypeDesc":53,"sizeBytes":54,"sourceHtmlUrl":55},"scripts\u002Fcheck_citations.mjs","SCRIPT","脚本",4507,"https:\u002F\u002Fgithub.com\u002Fzak-keown\u002Fmoe\u002Fblob\u002Fmain\u002Fplugins\u002Fmoe\u002F.claude-plugin\u002Fskills\u002Frun-iteration\u002Fscripts\u002Fcheck_citations.mjs",{"path":57,"resourceType":52,"resourceTypeDesc":53,"sizeBytes":58,"sourceHtmlUrl":59},"scripts\u002Fvalidate_iteration_log.mjs",3583,"https:\u002F\u002Fgithub.com\u002Fzak-keown\u002Fmoe\u002Fblob\u002Fmain\u002Fplugins\u002Fmoe\u002F.claude-plugin\u002Fskills\u002Frun-iteration\u002Fscripts\u002Fvalidate_iteration_log.mjs",[61,68,75,82,89,96],{"skillNo":62,"name":63,"nameZh":6,"description":64,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":65,"categories":66,"keywords":67,"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":69,"name":70,"nameZh":6,"description":71,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":72,"categories":73,"keywords":74,"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":76,"name":77,"nameZh":6,"description":78,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":79,"categories":80,"keywords":81,"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":83,"name":84,"nameZh":6,"description":85,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":86,"categories":87,"keywords":88,"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":90,"name":91,"nameZh":6,"description":92,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":93,"categories":94,"keywords":95,"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":97,"name":98,"nameZh":6,"description":99,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":100,"categories":101,"keywords":102,"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",[],[]]