[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M75P1K5DP54K4D9V9TMX5BKM":3,"skill-same:01M75P1K5DP54K4D9V9TMX5BKM":48},{"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":26,"commitSha":27,"skillDirectory":28,"forksCount":29,"repositoryHtmlUrl":30,"repositoryHomepageUrl":6,"ownerHtmlUrl":31,"ownerBlogUrl":32,"ownerDescription":6,"updatedAt":33,"install":34,"resources":47},"01M75P1K5DP54K4D9V9TMX5BKM","plan-validation",null,"Use when deciding whether a phase can advance, whether work is complete, or what evidence “done” requires. Defines acceptance evaluation, validation-gate promotion, invalid completion signals, and the closing retro that hands lessons to learn.","pixeloven\u002Fcrew","pixeloven","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F5751260?v=4","01M75P0048G371B0AWRKQ7FJN8","PixelOven","01M75P0051RK1ZEY0SA9HCMX2Z",1,"MIT","https:\u002F\u002Fgithub.com\u002Fpixeloven\u002Fcrew\u002Fblob\u002Fmain\u002Fskills\u002Fplan-validation\u002FSKILL.md",[],[],"2026-11-12 13:55:43",false,"---\nname: plan-validation\ndescription: Use when deciding whether a phase can advance, whether work is complete, or what evidence “done” requires. Defines acceptance evaluation, validation-gate promotion, invalid completion signals, and the closing retro that hands lessons to learn.\ntier: concept\nrequires: []\n---\n\n## What a validation gate is\n\nA validation gate is a boolean condition that must be true before the next phase begins. It is stated explicitly in the plan:\n\n```markdown\n### Validation Gate (Phase 1 → Phase 2)\n- All unit tests pass (`uv run pytest`)\n- No ruff errors (`uv run ruff check`)\n- PR opened and review requested\n```\n\nGates are checkable — not \"looks good\" but \"exit code 0\" or \"PR state is OPEN.\"\n\n## Checking acceptance criteria\n\nFor each task in the completed phase:\n\n1. Re-read the task's acceptance criteria verbatim\n2. Run or verify each criterion against the actual artifact (code, manifest, PR, vault note)\n3. Record: met \u002F not met \u002F not checkable\n\nIf any criterion is \"not met\": the task is incomplete. Either re-run the task or raise a delta.\n\nIf any criterion is \"not checkable\": surface it as an open question before advancing. A criterion that can't be verified is a criterion that doesn't exist.\n\n## Promotion checklist\n\nBefore advancing to the next phase:\n- [ ] All tasks in current phase have acceptance criteria marked met\n- [ ] Validation gate conditions are all satisfied\n- [ ] No unresolved deltas from this phase\n- [ ] Every decision this phase raised has a closing record (key, the human's words or the evidence that made it moot, date)\n- [ ] Every loop-back this phase opened met its written exit or was escalated, and the plan has used no more than its budget of two (per `plan-execution`)\n- [ ] Artifacts from this phase are in a state the next phase can consume (merged PRs, published vault notes, applied manifests)\n- [ ] No protected seams were crossed without human sign-off\n\n## What does NOT count as validation\n\n- \"The agent said it was done\" — verify independently\n- \"The code looks correct\" — run the tool that checks it\n- \"No errors were mentioned\" — check exit codes, not absence of error messages\n- \"It worked before\" — check the current state, not prior history\n- \"The decisions were listed\" — a phase is not complete while a decision it raised has no closing record\n- \"Another round fixed it\" — a loop-back counts only against the exit written before it started; a round that ends because nobody found more is not an exit\n\n## When criteria conflict\n\nIf acceptance criteria conflict with each other or with the plan's stated goal, surface it as a delta before attempting to satisfy them. Don't resolve ambiguity silently.\n\n## Recording gate promotion\n\nWhen a validation gate passes, record it in the plan:\n\n```markdown\n### Gate: Phase 1 → Phase 2\n**Promoted:** 2026-05-11\n**Verified by:** Lead\n**Evidence:** pytest exit 0 (run log in PR #251 CI), ruff exit 0, PR #251 opened\n```\n\nThis creates an audit trail. If Phase 3 fails, you can trace back to which gate last passed and when.\n\n## Retro: what the plan taught\n\nWhen a plan's last gate passes, run a retro before closing it, and after any\nreviewer pass: a review can overturn a finding the retro would otherwise keep.\n\n1. List the signals the plan raised: corrections from the operator, steps that\n   failed more than once, tool denials, reviewer findings the work had to fix,\n   and Doctor rows the work left `DEGRADED`. The plan's delta history, review\n   records and gate records hold most of them.\n2. Hand them to `learn` as its experience source. It drafts proposals into the\n   project's declared queue, or only reports them when no queue is declared, and\n   never applies one. Promotion stays the operator's.\n3. Record the outcome in the last gate record:\n\n```markdown\n**Retro:** 2026-05-14-lint-before-review (draft), 2026-05-14-test-target (needs-recurrence)\n```\n\nor `**Retro:** no lessons` when nothing would change the next session.\n\nThe retro never holds a gate. Work that met its criteria is done, and its\nlessons wait in the queue for review. Under a supervising host whose task\ncontract defines knowledge capture, follow it instead, per the reporting\ncontract.\n","## What a validation gate is\n\nA validation gate is a boolean condition that must be true before the next phase begins. It is stated explicitly in the plan:\n\n```markdown\n### Validation Gate (Phase 1 → Phase 2)\n- All unit tests pass (`uv run pytest`)\n- No ruff errors (`uv run ruff check`)\n- PR opened and review requested\n```\n\nGates are checkable — not \"looks good\" but \"exit code 0\" or \"PR state is OPEN.\"\n\n## Checking acceptance criteria\n\nFor each task in the completed phase:\n\n1. Re-read the task's acceptance criteria verbatim\n2. Run or verify each criterion against the actual artifact (code, manifest, PR, vault note)\n3. Record: met \u002F not met \u002F not checkable\n\nIf any criterion is \"not met\": the task is incomplete. Either re-run the task or raise a delta.\n\nIf any criterion is \"not checkable\": surface it as an open question before advancing. A criterion that can't be verified is a criterion that doesn't exist.\n\n## Promotion checklist\n\nBefore advancing to the next phase:\n- [ ] All tasks in current phase have acceptance criteria marked met\n- [ ] Validation gate conditions are all satisfied\n- [ ] No unresolved deltas from this phase\n- [ ] Every decision this phase raised has a closing record (key, the human's words or the evidence that made it moot, date)\n- [ ] Every loop-back this phase opened met its written exit or was escalated, and the plan has used no more than its budget of two (per `plan-execution`)\n- [ ] Artifacts from this phase are in a state the next phase can consume (merged PRs, published vault notes, applied manifests)\n- [ ] No protected seams were crossed without human sign-off\n\n## What does NOT count as validation\n\n- \"The agent said it was done\" — verify independently\n- \"The code looks correct\" — run the tool that checks it\n- \"No errors were mentioned\" — check exit codes, not absence of error messages\n- \"It worked before\" — check the current state, not prior history\n- \"The decisions were listed\" — a phase is not complete while a decision it raised has no closing record\n- \"Another round fixed it\" — a loop-back counts only against the exit written before it started; a round that ends because nobody found more is not an exit\n\n## When criteria conflict\n\nIf acceptance criteria conflict with each other or with the plan's stated goal, surface it as a delta before attempting to satisfy them. Don't resolve ambiguity silently.\n\n## Recording gate promotion\n\nWhen a validation gate passes, record it in the plan:\n\n```markdown\n### Gate: Phase 1 → Phase 2\n**Promoted:** 2026-05-11\n**Verified by:** Lead\n**Evidence:** pytest exit 0 (run log in PR #251 CI), ruff exit 0, PR #251 opened\n```\n\nThis creates an audit trail. If Phase 3 fails, you can trace back to which gate last passed and when.\n\n## Retro: what the plan taught\n\nWhen a plan's last gate passes, run a retro before closing it, and after any\nreviewer pass: a review can overturn a finding the retro would otherwise keep.\n\n1. List the signals the plan raised: corrections from the operator, steps that\n   failed more than once, tool denials, reviewer findings the work had to fix,\n   and Doctor rows the work left `DEGRADED`. The plan's delta history, review\n   records and gate records hold most of them.\n2. Hand them to `learn` as its experience source. It drafts proposals into the\n   project's declared queue, or only reports them when no queue is declared, and\n   never applies one. Promotion stays the operator's.\n3. Record the outcome in the last gate record:\n\n```markdown\n**Retro:** 2026-05-14-lint-before-review (draft), 2026-05-14-test-target (needs-recurrence)\n```\n\nor `**Retro:** no lessons` when nothing would change the next session.\n\nThe retro never holds a gate. Work that met its criteria is done, and its\nlessons wait in the queue for review. Under a supervising host whose task\ncontract defines knowledge capture, follow it instead, per the reporting\ncontract.\n",{"name":5,"tier":24,"requires":25,"description":7},"concept",[],"main","686d42537f9efddb1aeece969b1a4fee2e4d1a88","skills\u002Fplan-validation",0,"https:\u002F\u002Fgithub.com\u002Fpixeloven\u002Fcrew","https:\u002F\u002Fgithub.com\u002Fpixeloven","www.pixeloven.com","2026-11-07 09:18:41",{"source":8,"skillName":5,"commands":35,"prompt":45,"zipAvailable":46},[36,39,42],{"tool":37,"command":38},"npx","npx skills add pixeloven\u002Fcrew --skill plan-validation",{"tool":40,"command":41},"bunx","bunx skills add pixeloven\u002Fcrew --skill plan-validation",{"tool":43,"command":44},"pnpm","pnpm dlx skills add pixeloven\u002Fcrew --skill plan-validation","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fpixeloven\u002Fcrew\u002Fblob\u002Fmain\u002Fskills\u002Fplan-validation\u002FSKILL.md",true,[],[49,56,63,70,76,82],{"skillNo":50,"name":51,"nameZh":6,"description":52,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":53,"categories":54,"keywords":55,"publishedAt":19},"01M75P2X72QCY4H2H6C7D3KQ1Z","orchard-gh-runs","Use when reading a failed GitHub Actions run with the gh CLI in this project, before re-running it or reporting a CI failure, so the failing step's log is read instead of the whole run.","https:\u002F\u002Fgithub.com\u002Fpixeloven\u002Fcrew\u002Fblob\u002Fmain\u002Ftests\u002Ffixtures\u002Fproposals\u002Forchard\u002F.agents\u002Fskills\u002Forchard-gh-runs\u002FSKILL.md",[],[],{"skillNo":57,"name":58,"nameZh":6,"description":59,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":60,"categories":61,"keywords":62,"publishedAt":19},"01M75P2T76B22B314Q3W25GDCK","orchard-gh","Hand-edited after promotion; the learned marker was dropped, so Doctor and check_skills --local can no longer see it.","https:\u002F\u002Fgithub.com\u002Fpixeloven\u002Fcrew\u002Fblob\u002Fmain\u002Ftests\u002Ffixtures\u002Fproposals\u002Finvalid\u002F.agents\u002Fskills\u002Forchard-gh\u002FSKILL.md",[],[],{"skillNo":64,"name":65,"nameZh":6,"description":66,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":67,"categories":68,"keywords":69,"publishedAt":19},"01M75P2Q410WX0H3ZZ61R210F4","demo-topology","Use when exercising the inventory contract fixture so that this fixture description comfortably clears the schema-v2 minimum length.","https:\u002F\u002Fgithub.com\u002Fpixeloven\u002Fcrew\u002Fblob\u002Fmain\u002Ftests\u002Ffixtures\u002Finventory\u002Fproject\u002F.agents\u002Fskills\u002Fdemo-topology\u002FSKILL.md",[],[],{"skillNo":71,"name":72,"nameZh":6,"description":66,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":73,"categories":74,"keywords":75,"publishedAt":19},"01M75P2KTWZ94KNSKHPGFB6Y6J","helper-jq","https:\u002F\u002Fgithub.com\u002Fpixeloven\u002Fcrew\u002Fblob\u002Fmain\u002Ftests\u002Ffixtures\u002Finventory\u002Fhome\u002F.codex\u002Fplugins\u002Fcache\u002Facme\u002Fhelper\u002F2.0.0\u002Fskills\u002Fhelper-jq\u002FSKILL.md",[],[],{"skillNo":77,"name":78,"nameZh":6,"description":66,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":79,"categories":80,"keywords":81,"publishedAt":19},"01M75P2GT2CXZR4EZE2DS9GTS7","user-notes","https:\u002F\u002Fgithub.com\u002Fpixeloven\u002Fcrew\u002Fblob\u002Fmain\u002Ftests\u002Ffixtures\u002Finventory\u002Fhome\u002F.claude\u002Fskills\u002Fuser-notes\u002FSKILL.md",[],[],{"skillNo":83,"name":84,"nameZh":6,"description":66,"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},"01M75P2D61GDSH9NFNEBV4HDBS","toolkit-gh","https:\u002F\u002Fgithub.com\u002Fpixeloven\u002Fcrew\u002Fblob\u002Fmain\u002Ftests\u002Ffixtures\u002Finventory\u002Fhome\u002F.claude\u002Fplugins\u002Fcache\u002Facme\u002Ftoolkit\u002F1.2.0\u002Fskills\u002Ftoolkit-gh\u002FSKILL.md",[],[]]