[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6FJABP43ASHC5KR26XM04EW":3,"skill-same:01M6FJABP43ASHC5KR26XM04EW":56},{"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":30,"linkOnly":31,"markdownContent":32,"markdownBody":33,"frontMatter":34,"refName":35,"commitSha":36,"skillDirectory":37,"forksCount":38,"repositoryHtmlUrl":39,"repositoryHomepageUrl":6,"ownerHtmlUrl":40,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":41,"install":42,"resources":55},"01M6FJABP43ASHC5KR26XM04EW","ln-312-review-findings-worker",null,"Use when an evaluation coordinator needs normalized findings from target artifacts and research evidence.","boisenoise\u002Fskills-collections","boisenoise","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F193180?v=4","01M6CDBDQK6BDN55ZMA6B6PKBM","01M6CDBDVSJ3JPTBYN26FZ7TZK",12,"MIT","https:\u002F\u002Fgithub.com\u002Fboisenoise\u002Fskills-collections\u002Fblob\u002Fmain\u002Fskills\u002Flevn-ln-312-review-findings-worker\u002FSKILL.md",[],[18,19,20,21,22,23,24,25,26,27,28,29],"review","worker","review findings","ln 312 review findings worker","ln","research","artifacts","Evaluation","use","evidence","coordinator","when","2026-11-10 10:12:30",false,"---\nname: ln-312-review-findings-worker\ndescription: \"Use when an evaluation coordinator needs normalized findings from target artifacts and research evidence.\"\nlicense: MIT\n---\n\n> **Paths:** File paths (`shared\u002F`, `references\u002F`, `..\u002Fln-*`) are relative to skills repo root.\n\n**Type:** L3 Worker\n**Category:** 3XX Planning\n\n# Review Findings Worker\n\n## Mandatory Read\n\n**MANDATORY READ:** Load `shared\u002Freferences\u002Fevaluation_worker_runtime_contract.md`, `shared\u002Freferences\u002Fevaluation_summary_contract.md`\n**MANDATORY READ:** Load `..\u002Fln-310-multi-agent-validator\u002Freferences\u002Fphase2_research_audit.md`, `..\u002Fln-310-multi-agent-validator\u002Freferences\u002Fpenalty_points.md`\n**MANDATORY READ:** Load `..\u002Fln-310-multi-agent-validator\u002Freferences\u002Fpremortem_validation.md`, `..\u002Fln-310-multi-agent-validator\u002Freferences\u002Fcross_reference_validation.md`\n\n## Purpose\n\n- analyze the target artifact or diff\n- convert evidence into normalized findings\n- for `mode=story`: calculate penalty points across 30 criteria per `phase2_research_audit.md`\n- for `mode=plan_review`: evaluate criteria #5, #6, #21, #28 only (no penalty accumulation)\n- avoid narrative-only review output\n\n## Mode Gate\n\n- `mode=story`: full pipeline — pre-mortem, cross-reference, penalty points across 30 criteria, build fix plan\n- `mode=plan_review`: applicability check, stack detection, evaluate criteria #5 (standards), #6 (library versions), #21 (alternatives), #28 (library features) only, normalize findings without penalty accumulation\n\n## Runtime\n\nRuntime family:\n- `evaluation-worker-runtime`\n\nRequired manifest fields:\n- `identifier`\n- `phase_order`\n- `summary_kind=review-findings`\n- `operation=findings`\n\nRecommended `phase_order`:\n1. `PHASE_0_CONFIG`\n2. `PHASE_1_LOAD_TARGET`\n3. `PHASE_2_PREMORTEM` (mode=story, complexity >= Medium)\n4. `PHASE_3_CROSS_REFERENCE` (mode=story, multi-story Epic)\n5. `PHASE_4_CRITERIA_AUDIT`\n6. `PHASE_5_PENALTY_CALCULATION` (mode=story only)\n7. `PHASE_6_NORMALIZE_FINDINGS`\n8. `PHASE_7_WRITE_SUMMARY`\n9. `PHASE_8_SELF_CHECK`\n\n## Workflow\n\n### Phase 0: Config\n\nLoad runtime manifest, target identifiers, and any linked research artifact paths.\n\n### Phase 1: Load Target\n\nLoad only the target artifacts needed for the review scope.\n\n### Phase 2: Pre-mortem (mode=story)\n\nExecute pre-mortem analysis per `premortem_validation.md`:\n1. Skip for trivial Stories (1-2 tasks, no external deps, known tech).\n2. Execute for Stories with complexity >= Medium (3+ tasks, external deps, or unfamiliar tech).\n3. Tigers (evidence-based risks) feed Risk criterion #20 — add to risk table BEFORE penalty calc.\n4. Elephants (unstated assumptions) feed Assumptions criterion #24 — add with `[pre-mortem]` tag, Confidence=LOW.\n5. Paper Tigers (fears without evidence) — document and dismiss.\n6. Include pre-mortem table in audit report.\n\n### Phase 3: Cross-Reference (mode=story)\n\nExecute cross-reference analysis per `cross_reference_validation.md`:\n1. Skip if Epic has only 1 Story or all siblings Done\u002FCanceled.\n2. Load sibling Stories via `list_issues(project=Epic.id)`.\n3. Check AC overlap (#25): structured traceability first, keyword fallback advisory-only.\n4. Check task duplication (#26): structured match primary.\n5. Include cross-reference findings in audit report.\n\n### Phase 4: Criteria Audit\n\n1. `mode=story`: evaluate all 30 criteria against Story\u002FTasks per `phase2_research_audit.md` Auto-Fix Actions Reference.\n2. `mode=plan_review`: evaluate criteria #5, #6, #21, #28 only (standards + solution groups).\n3. Cross-check claims against provided research evidence when present.\n\n### Phase 5: Penalty Calculation (mode=story)\n\n1. Assign penalty points per violation using severity levels from `phase2_research_audit.md` (CRITICAL=10, HIGH=5, MEDIUM=3, LOW=1).\n2. Apply multiple-violation rules per `penalty_points.md` Calculation Rules.\n3. Calculate total penalty points.\n4. Build fix plan for each violation.\n5. Format penalty audit table per `penalty_points.md` Report Format.\n\n### Phase 6: Normalize Findings\n\nEach finding should prefer structured fields such as:\n- `id`\n- `severity`\n- `category`\n- `subject`\n- `evidence`\n- `recommendation`\n\n### Phase 7: Write Summary\n\nEmit `summary_kind=review-findings`.\n\nPayload must include:\n- `worker=ln-312`\n- `status`\n- `operation=findings`\n- `warnings`\n\nPrefer these fields when available:\n- `findings`\n- `metrics.penalty_total` (mode=story)\n- `metrics.criteria_violated` (list of criterion numbers)\n- `metrics.fix_plan` (array of {criterion, action, severity})\n- `metrics.premortem_summary` (when executed)\n- `metrics.cross_reference_summary` (when executed)\n\n### Phase 8: Self-Check\n\n1. Remove duplicates.\n2. Remove unsupported claims.\n3. Verify penalty calculation matches `penalty_points.md` rules (mode=story).\n4. Record `pass=true` only after summary write.\n\n## Definition of Done\n\n- [ ] Target artifact loaded\n- [ ] Pre-mortem executed or justified as skipped (mode=story)\n- [ ] Cross-reference executed or justified as skipped (mode=story)\n- [ ] Criteria audit completed (30 for story, #5\u002F#6\u002F#21\u002F#28 for others)\n- [ ] Penalty points calculated and fix plan built (mode=story)\n- [ ] Findings normalized\n- [ ] Unsupported claims removed\n- [ ] `review-findings` summary written\n- [ ] Self-check passed\n\n**Version:** 1.0.0\n**Last Updated:** 2026-04-10\n","> **Paths:** File paths (`shared\u002F`, `references\u002F`, `..\u002Fln-*`) are relative to skills repo root.\n\n**Type:** L3 Worker\n**Category:** 3XX Planning\n\n# Review Findings Worker\n\n## Mandatory Read\n\n**MANDATORY READ:** Load `shared\u002Freferences\u002Fevaluation_worker_runtime_contract.md`, `shared\u002Freferences\u002Fevaluation_summary_contract.md`\n**MANDATORY READ:** Load `..\u002Fln-310-multi-agent-validator\u002Freferences\u002Fphase2_research_audit.md`, `..\u002Fln-310-multi-agent-validator\u002Freferences\u002Fpenalty_points.md`\n**MANDATORY READ:** Load `..\u002Fln-310-multi-agent-validator\u002Freferences\u002Fpremortem_validation.md`, `..\u002Fln-310-multi-agent-validator\u002Freferences\u002Fcross_reference_validation.md`\n\n## Purpose\n\n- analyze the target artifact or diff\n- convert evidence into normalized findings\n- for `mode=story`: calculate penalty points across 30 criteria per `phase2_research_audit.md`\n- for `mode=plan_review`: evaluate criteria #5, #6, #21, #28 only (no penalty accumulation)\n- avoid narrative-only review output\n\n## Mode Gate\n\n- `mode=story`: full pipeline — pre-mortem, cross-reference, penalty points across 30 criteria, build fix plan\n- `mode=plan_review`: applicability check, stack detection, evaluate criteria #5 (standards), #6 (library versions), #21 (alternatives), #28 (library features) only, normalize findings without penalty accumulation\n\n## Runtime\n\nRuntime family:\n- `evaluation-worker-runtime`\n\nRequired manifest fields:\n- `identifier`\n- `phase_order`\n- `summary_kind=review-findings`\n- `operation=findings`\n\nRecommended `phase_order`:\n1. `PHASE_0_CONFIG`\n2. `PHASE_1_LOAD_TARGET`\n3. `PHASE_2_PREMORTEM` (mode=story, complexity >= Medium)\n4. `PHASE_3_CROSS_REFERENCE` (mode=story, multi-story Epic)\n5. `PHASE_4_CRITERIA_AUDIT`\n6. `PHASE_5_PENALTY_CALCULATION` (mode=story only)\n7. `PHASE_6_NORMALIZE_FINDINGS`\n8. `PHASE_7_WRITE_SUMMARY`\n9. `PHASE_8_SELF_CHECK`\n\n## Workflow\n\n### Phase 0: Config\n\nLoad runtime manifest, target identifiers, and any linked research artifact paths.\n\n### Phase 1: Load Target\n\nLoad only the target artifacts needed for the review scope.\n\n### Phase 2: Pre-mortem (mode=story)\n\nExecute pre-mortem analysis per `premortem_validation.md`:\n1. Skip for trivial Stories (1-2 tasks, no external deps, known tech).\n2. Execute for Stories with complexity >= Medium (3+ tasks, external deps, or unfamiliar tech).\n3. Tigers (evidence-based risks) feed Risk criterion #20 — add to risk table BEFORE penalty calc.\n4. Elephants (unstated assumptions) feed Assumptions criterion #24 — add with `[pre-mortem]` tag, Confidence=LOW.\n5. Paper Tigers (fears without evidence) — document and dismiss.\n6. Include pre-mortem table in audit report.\n\n### Phase 3: Cross-Reference (mode=story)\n\nExecute cross-reference analysis per `cross_reference_validation.md`:\n1. Skip if Epic has only 1 Story or all siblings Done\u002FCanceled.\n2. Load sibling Stories via `list_issues(project=Epic.id)`.\n3. Check AC overlap (#25): structured traceability first, keyword fallback advisory-only.\n4. Check task duplication (#26): structured match primary.\n5. Include cross-reference findings in audit report.\n\n### Phase 4: Criteria Audit\n\n1. `mode=story`: evaluate all 30 criteria against Story\u002FTasks per `phase2_research_audit.md` Auto-Fix Actions Reference.\n2. `mode=plan_review`: evaluate criteria #5, #6, #21, #28 only (standards + solution groups).\n3. Cross-check claims against provided research evidence when present.\n\n### Phase 5: Penalty Calculation (mode=story)\n\n1. Assign penalty points per violation using severity levels from `phase2_research_audit.md` (CRITICAL=10, HIGH=5, MEDIUM=3, LOW=1).\n2. Apply multiple-violation rules per `penalty_points.md` Calculation Rules.\n3. Calculate total penalty points.\n4. Build fix plan for each violation.\n5. Format penalty audit table per `penalty_points.md` Report Format.\n\n### Phase 6: Normalize Findings\n\nEach finding should prefer structured fields such as:\n- `id`\n- `severity`\n- `category`\n- `subject`\n- `evidence`\n- `recommendation`\n\n### Phase 7: Write Summary\n\nEmit `summary_kind=review-findings`.\n\nPayload must include:\n- `worker=ln-312`\n- `status`\n- `operation=findings`\n- `warnings`\n\nPrefer these fields when available:\n- `findings`\n- `metrics.penalty_total` (mode=story)\n- `metrics.criteria_violated` (list of criterion numbers)\n- `metrics.fix_plan` (array of {criterion, action, severity})\n- `metrics.premortem_summary` (when executed)\n- `metrics.cross_reference_summary` (when executed)\n\n### Phase 8: Self-Check\n\n1. Remove duplicates.\n2. Remove unsupported claims.\n3. Verify penalty calculation matches `penalty_points.md` rules (mode=story).\n4. Record `pass=true` only after summary write.\n\n## Definition of Done\n\n- [ ] Target artifact loaded\n- [ ] Pre-mortem executed or justified as skipped (mode=story)\n- [ ] Cross-reference executed or justified as skipped (mode=story)\n- [ ] Criteria audit completed (30 for story, #5\u002F#6\u002F#21\u002F#28 for others)\n- [ ] Penalty points calculated and fix plan built (mode=story)\n- [ ] Findings normalized\n- [ ] Unsupported claims removed\n- [ ] `review-findings` summary written\n- [ ] Self-check passed\n\n**Version:** 1.0.0\n**Last Updated:** 2026-04-10\n",{"name":5,"license":14,"description":7},"main","7bf2279c8a65758319526a721d5c4b75683aec9c","skills\u002Flevn-ln-312-review-findings-worker",3,"https:\u002F\u002Fgithub.com\u002Fboisenoise\u002Fskills-collections","https:\u002F\u002Fgithub.com\u002Fboisenoise","2026-11-11 14:20:43",{"source":8,"skillName":5,"commands":43,"prompt":53,"zipAvailable":54},[44,47,50],{"tool":45,"command":46},"npx","npx skills add boisenoise\u002Fskills-collections --skill ln-312-review-findings-worker",{"tool":48,"command":49},"bunx","bunx skills add boisenoise\u002Fskills-collections --skill ln-312-review-findings-worker",{"tool":51,"command":52},"pnpm","pnpm dlx skills add boisenoise\u002Fskills-collections --skill ln-312-review-findings-worker","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fboisenoise\u002Fskills-collections\u002Fblob\u002Fmain\u002Fskills\u002Flevn-ln-312-review-findings-worker\u002FSKILL.md",true,[],[57,86,113,138,157,179],{"skillNo":58,"name":59,"nameZh":6,"description":60,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":61,"licenseFileUrl":62,"sourceHtmlUrl":63,"categories":64,"keywords":65,"publishedAt":30},"01M6WNH92BHVFXHGPDZCPJ0AG0","web-access","Use Treg for public web or platform data only when existing search, browser and connected tools cannot cover the task, with explicit cost and data boundaries.","Apache-2.0","https:\u002F\u002Fgithub.com\u002Fboisenoise\u002Fskills-collections\u002Fblob\u002Fmain\u002Fskills\u002Fantigravity-web-access\u002FLICENSE","https:\u002F\u002Fgithub.com\u002Fboisenoise\u002Fskills-collections\u002Fblob\u002Fmain\u002Fskills\u002Fantigravity-web-access\u002FSKILL.md",[],[66,67,68,69,70,71,72,73,74,75,76,77,78,79,80,81,82,83,84,29,85],"web","access","web access","official","development","browser","search","data","Tools","read","fetch","only","youtube","free tools","platform","critical","free","cover","normal","2026",{"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":61,"licenseFileUrl":90,"sourceHtmlUrl":91,"categories":92,"keywords":98,"publishedAt":30},"01M6WNF9XAYAB2CZDDJBAKNM93","treg","Use the Treg CLI or MCP catalog to discover, price and call authorized external tools with team-scoped credentials and a user-approved budget.","https:\u002F\u002Fgithub.com\u002Fboisenoise\u002Fskills-collections\u002Fblob\u002Fmain\u002Fskills\u002Fantigravity-treg\u002FLICENSE","https:\u002F\u002Fgithub.com\u002Fboisenoise\u002Fskills-collections\u002Fblob\u002Fmain\u002Fskills\u002Fantigravity-treg\u002FSKILL.md",[93],{"categoryNo":94,"categoryName":95,"taxonomyType":96,"taxonomyTypeDesc":97},"01JBSEEDCAT000000000000023","Skill与智能体开发","SCENARIO","使用场景",[88,99,100,101,69,70,102,74,103,104,105,106,26,107,108,81,109,110,111,112,85],"MCP","cli","github","license","Budget","credentials","team","catalog","call","discover","external tools","with","scoped","blob",{"skillNo":114,"name":115,"nameZh":6,"description":116,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":61,"licenseFileUrl":117,"sourceHtmlUrl":118,"categories":119,"keywords":125,"publishedAt":30},"01M6WN93MEAZ4E41DYAHJRPHQT","recruit","Turn a job description into an evidence-linked candidate shortlist through Treg, with job-related ranking and optional authorized business contact enrichment.","https:\u002F\u002Fgithub.com\u002Fboisenoise\u002Fskills-collections\u002Fblob\u002Fmain\u002Fskills\u002Fantigravity-recruit\u002FLICENSE","https:\u002F\u002Fgithub.com\u002Fboisenoise\u002Fskills-collections\u002Fblob\u002Fmain\u002Fskills\u002Fantigravity-recruit\u002FSKILL.md",[120],{"categoryNo":121,"categoryName":122,"taxonomyType":123,"taxonomyTypeDesc":124},"01JBSEEDCAT000000000000038","人力资源","PROFESSION","适用职业",[115,101,69,102,126,127,128,129,27,130,81,131,132,133,110,134,135,136,137,112,88,85],"https","email","enrichment","business","phone","ranking","post","job description","for","person","candidate","reason",{"skillNo":139,"name":140,"nameZh":6,"description":141,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":61,"licenseFileUrl":142,"sourceHtmlUrl":143,"categories":144,"keywords":145,"publishedAt":30},"01M6WN8R5RXSMHM9B4D9FAFX42","rea-growth","Analyze a company’s public growth and content through Treg, distinguish observations from hypotheses, and produce an evidence-linked playbook within an approved budget.","https:\u002F\u002Fgithub.com\u002Fboisenoise\u002Fskills-collections\u002Fblob\u002Fmain\u002Fskills\u002Fantigravity-rea-growth\u002FLICENSE","https:\u002F\u002Fgithub.com\u002Fboisenoise\u002Fskills-collections\u002Fblob\u002Fmain\u002Fskills\u002Fantigravity-rea-growth\u002FSKILL.md",[],[146,147,148,101,69,102,149,150,126,151,103,152,153,154,27,81,155,156,112,88,85],"growth","rea","rea growth","produce","content","playbook","marketing","analyze","public","observations","company",{"skillNo":158,"name":159,"nameZh":6,"description":160,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":61,"licenseFileUrl":161,"sourceHtmlUrl":162,"categories":163,"keywords":164,"publishedAt":30},"01M6WN2EVE3RQRGWAKBT4S7YT2","make-ugc","Create original AI UGC-style product videos through Treg: research hooks, approve a licensed presenter and voice, generate clips, add captions and report costs.","https:\u002F\u002Fgithub.com\u002Fboisenoise\u002Fskills-collections\u002Fblob\u002Fmain\u002Fskills\u002Fantigravity-make-ugc\u002FLICENSE","https:\u002F\u002Fgithub.com\u002Fboisenoise\u002Fskills-collections\u002Fblob\u002Fmain\u002Fskills\u002Fantigravity-make-ugc\u002FSKILL.md",[],[165,166,101,23,69,167,102,168,169,170,171,172,81,173,174,175,176,177,178,112],"make","make ugc","create","Video","Captions","ads","short","hooks","head","style","niche","trending","talking-head","approve",{"skillNo":180,"name":181,"nameZh":6,"description":182,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":61,"licenseFileUrl":183,"sourceHtmlUrl":184,"categories":185,"keywords":186,"publishedAt":30},"01M6WN10ARAA63Y8K1YNGXJ2RM","lead-signals","Find and qualify public buying signals through Treg, rank fitting business accounts and optionally enrich authorized business contact information.","https:\u002F\u002Fgithub.com\u002Fboisenoise\u002Fskills-collections\u002Fblob\u002Fmain\u002Fskills\u002Fantigravity-lead-signals\u002FLICENSE","https:\u002F\u002Fgithub.com\u002Fboisenoise\u002Fskills-collections\u002Fblob\u002Fmain\u002Fskills\u002Fantigravity-lead-signals\u002FSKILL.md",[],[187,188,189,101,69,102,190,191,129,192,193,81,194,195,196,197,198,199,200,112],"signals","lead","lead signals","how","find","ready","as","how to","qualify","people","information","enrich","changes","funding"]