[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6C43WKVB9VY2YA38N2KN333":3,"skill-same:01M6C43WKVB9VY2YA38N2KN333":130},{"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":26,"linkOnly":27,"markdownContent":28,"markdownBody":29,"frontMatter":30,"refName":31,"commitSha":32,"skillDirectory":33,"forksCount":34,"repositoryHtmlUrl":35,"repositoryHomepageUrl":6,"ownerHtmlUrl":36,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":37,"install":38,"resources":51},"01M6C43WKVB9VY2YA38N2KN333","calibration-pipeline",null,"Calibration and review-pipeline tooling guidance. Use when running or maintaining calibration scripts, review aggregation, and related deterministic assets for issue #360. DO NOT USE FOR: changing orchestration ownership or agent review policy.","Grimblaz\u002Fagent-orchestra","Grimblaz","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F74755849?v=4","01M6C430M9XZDHGHPWQVTQ3KMA","01M6C430RJY3MMX0QAZ3X8DR3Y",3,"MIT","https:\u002F\u002Fgithub.com\u002FGrimblaz\u002Fagent-orchestra\u002Fblob\u002Fmain\u002Fskills\u002Fcalibration-pipeline\u002FSKILL.md",[],[18,19,20,21,22,23,24,25],"pipeline","calibration pipeline","review","policy","orchestration","aggregation","assets","use","2026-11-10 10:12:30",false,"---\nname: calibration-pipeline\ndescription: \"Calibration and review-pipeline tooling guidance. Use when running or maintaining calibration scripts, review aggregation, and related deterministic assets for issue #360. DO NOT USE FOR: changing orchestration ownership or agent review policy.\"\n---\n\n# Calibration Pipeline\n\nReusable entryway for deterministic tooling, committed assets, and pipeline-metrics reference material for the calibration pipeline introduced by issue #360.\n\n> **Survival**: `SMC-09` covers raw aggregate\u002Fprosecution-depth snapshots as `per-dispatch` until selected PR-body metrics are durable. `SMC-10` covers the `within-worktree` per-finding cache; `SMC-11` covers `within-worktree` cross-PR state. Script temp files are `per-process` scratch only.\n\n## When to Use\n\n- When running or maintaining calibration writers, aggregation scripts, or helper libraries under `scripts\u002F`\n- When updating committed calibration data or configuration under `assets\u002F`\n- When a workflow needs the canonical pipeline-metrics schema, verdict mapping, or findings-construction rules without re-reading Code-Conductor\n\n## Purpose\n\n- Describe the calibration and review-aggregation domain\n- Provide the stable home for pipeline scripts under `scripts\u002F`\n- Provide the stable home for committed pipeline data under `assets\u002F`\n- Metric segmentation (sustain-rate by confidence tier) needed to make pre\u002Fpost coverage-first `sustain_rate` readings comparable is deferred to umbrella #761 — see the `## Gotchas` entry below\n\n## Contents\n\n- `scripts\u002F` contains calibration writers, aggregation tools, improvement-issue helpers, and related shared helpers\n- `assets\u002F` contains committed pipeline configuration and data consumed by those scripts\n- `references\u002F` contains extracted pipeline-metrics contract material that other skills and agents can load directly\n- `schemas\u002Fphase-containment.schema.json` is the validation schema for `\u003C!-- phase-containment-{ID} -->` ledger entries; the ledger's warn-only enforcement surface is `.github\u002Fscripts\u002Fphase-containment-emission-check.ps1` (hub maintainers only — repo-relative, does not resolve from a consumer repo's CWD), which sweeps the code-review, post-review-observer, design-challenge, plan-stress-test and brief-review surfaces for upheld findings missing a paired ledger block and reports the gap; it never blocks a caller flow. \"Upheld\" is deliberately not \"judge-sustained\": the design-challenge and brief-review surfaces are prosecution-only and authorize counting without a judge, which is the whole point of issue #951. Issue surfaces are routed per issue, so a brief-declared issue is swept on brief-review and not on plan-stress-test\n\n## Composite References\n\n- [references\u002Fmetrics-schema.md](references\u002Fmetrics-schema.md): canonical `## Pipeline Metrics` block shape, top-level field semantics, and the `write-calibration-entry.ps1` invocation contract\n- [references\u002Fverdict-mapping.md](references\u002Fverdict-mapping.md): judge verdict to metrics-field mapping for main and post-fix review\n- [references\u002Ffindings-construction.md](references\u002Ffindings-construction.md): findings-array construction, backward compatibility, malformed-entry handling, and rework-cycle population rules\n- [references\u002Frelease-hygiene-credit-emission.md](references\u002Frelease-hygiene-credit-emission.md): v4 release-hygiene credit row construction (state-file reading, YAML examples) and CE Gate S2 synthetic-PR test protocol (issue #441 Step 7b)\n- [references\u002Freview-credit-emission.md](references\u002Freview-credit-emission.md): v4 review credit row construction via `Build-ReviewCreditRow` — adapter selection, RunIndex semantics, cross-tool handoff, and CE Gate S3 coverage (issue #441 Step 8b)\n- [references\u002Fconductor-credit-emission.md](references\u002Fconductor-credit-emission.md): Code-Conductor-owned credit-row emission procedures — Pipeline-Entry Credit Harvest (SMC-17), Deferred Port Credit Rows, `process-review` trigger-absent emission, and the Post-PR Credit Row (D10 category 3)\n- [references\u002Fconductor-metrics-protocol.md](references\u002Fconductor-metrics-protocol.md): emission timing and ownership boundary, Add-FCLCreditRow accumulator pattern, release-hygiene and review credit row pointers, and dispatch-cost samples — extracted from `agents\u002FCode-Conductor.agent.md` via D5 compression (issue #774)\n\n## Boundary\n\n- This skill owns deterministic tooling and static assets only\n- Review orchestration, judgment, and step execution stay with the owning agents and existing methodology skills\n\n## Gotchas\n\n| Trigger                        | Gotcha                                                        | Fix                                                                                 |\n| ------------------------------ | ------------------------------------------------------------- | ----------------------------------------------------------------------------------- |\n| Adding review pipeline helpers | Tooling and orchestration responsibilities get mixed together | Keep scripts and assets here, but leave routing and judgment with the owning agents |\n| Reading sustain_rate trends across the #784 coverage-first prosecution change (dated 2026-07-02) | Coverage-first prosecution reports more low-confidence findings that were previously silently omitted, mechanically lowering sustain_rate even though prosecutor quality is unchanged | Treat sustain-rate readings from before vs. after the coverage-first epoch as non-comparable; do not trigger prosecution-depth auto-tuning on a low-confidence-driven sustain-rate dip. Metric segmentation (sustain-rate by confidence tier) is deferred to umbrella #761. |\n","# Calibration Pipeline\n\nReusable entryway for deterministic tooling, committed assets, and pipeline-metrics reference material for the calibration pipeline introduced by issue #360.\n\n> **Survival**: `SMC-09` covers raw aggregate\u002Fprosecution-depth snapshots as `per-dispatch` until selected PR-body metrics are durable. `SMC-10` covers the `within-worktree` per-finding cache; `SMC-11` covers `within-worktree` cross-PR state. Script temp files are `per-process` scratch only.\n\n## When to Use\n\n- When running or maintaining calibration writers, aggregation scripts, or helper libraries under `scripts\u002F`\n- When updating committed calibration data or configuration under `assets\u002F`\n- When a workflow needs the canonical pipeline-metrics schema, verdict mapping, or findings-construction rules without re-reading Code-Conductor\n\n## Purpose\n\n- Describe the calibration and review-aggregation domain\n- Provide the stable home for pipeline scripts under `scripts\u002F`\n- Provide the stable home for committed pipeline data under `assets\u002F`\n- Metric segmentation (sustain-rate by confidence tier) needed to make pre\u002Fpost coverage-first `sustain_rate` readings comparable is deferred to umbrella #761 — see the `## Gotchas` entry below\n\n## Contents\n\n- `scripts\u002F` contains calibration writers, aggregation tools, improvement-issue helpers, and related shared helpers\n- `assets\u002F` contains committed pipeline configuration and data consumed by those scripts\n- `references\u002F` contains extracted pipeline-metrics contract material that other skills and agents can load directly\n- `schemas\u002Fphase-containment.schema.json` is the validation schema for `\u003C!-- phase-containment-{ID} -->` ledger entries; the ledger's warn-only enforcement surface is `.github\u002Fscripts\u002Fphase-containment-emission-check.ps1` (hub maintainers only — repo-relative, does not resolve from a consumer repo's CWD), which sweeps the code-review, post-review-observer, design-challenge, plan-stress-test and brief-review surfaces for upheld findings missing a paired ledger block and reports the gap; it never blocks a caller flow. \"Upheld\" is deliberately not \"judge-sustained\": the design-challenge and brief-review surfaces are prosecution-only and authorize counting without a judge, which is the whole point of issue #951. Issue surfaces are routed per issue, so a brief-declared issue is swept on brief-review and not on plan-stress-test\n\n## Composite References\n\n- [references\u002Fmetrics-schema.md](references\u002Fmetrics-schema.md): canonical `## Pipeline Metrics` block shape, top-level field semantics, and the `write-calibration-entry.ps1` invocation contract\n- [references\u002Fverdict-mapping.md](references\u002Fverdict-mapping.md): judge verdict to metrics-field mapping for main and post-fix review\n- [references\u002Ffindings-construction.md](references\u002Ffindings-construction.md): findings-array construction, backward compatibility, malformed-entry handling, and rework-cycle population rules\n- [references\u002Frelease-hygiene-credit-emission.md](references\u002Frelease-hygiene-credit-emission.md): v4 release-hygiene credit row construction (state-file reading, YAML examples) and CE Gate S2 synthetic-PR test protocol (issue #441 Step 7b)\n- [references\u002Freview-credit-emission.md](references\u002Freview-credit-emission.md): v4 review credit row construction via `Build-ReviewCreditRow` — adapter selection, RunIndex semantics, cross-tool handoff, and CE Gate S3 coverage (issue #441 Step 8b)\n- [references\u002Fconductor-credit-emission.md](references\u002Fconductor-credit-emission.md): Code-Conductor-owned credit-row emission procedures — Pipeline-Entry Credit Harvest (SMC-17), Deferred Port Credit Rows, `process-review` trigger-absent emission, and the Post-PR Credit Row (D10 category 3)\n- [references\u002Fconductor-metrics-protocol.md](references\u002Fconductor-metrics-protocol.md): emission timing and ownership boundary, Add-FCLCreditRow accumulator pattern, release-hygiene and review credit row pointers, and dispatch-cost samples — extracted from `agents\u002FCode-Conductor.agent.md` via D5 compression (issue #774)\n\n## Boundary\n\n- This skill owns deterministic tooling and static assets only\n- Review orchestration, judgment, and step execution stay with the owning agents and existing methodology skills\n\n## Gotchas\n\n| Trigger                        | Gotcha                                                        | Fix                                                                                 |\n| ------------------------------ | ------------------------------------------------------------- | ----------------------------------------------------------------------------------- |\n| Adding review pipeline helpers | Tooling and orchestration responsibilities get mixed together | Keep scripts and assets here, but leave routing and judgment with the owning agents |\n| Reading sustain_rate trends across the #784 coverage-first prosecution change (dated 2026-07-02) | Coverage-first prosecution reports more low-confidence findings that were previously silently omitted, mechanically lowering sustain_rate even though prosecutor quality is unchanged | Treat sustain-rate readings from before vs. after the coverage-first epoch as non-comparable; do not trigger prosecution-depth auto-tuning on a low-confidence-driven sustain-rate dip. Metric segmentation (sustain-rate by confidence tier) is deferred to umbrella #761. |\n",{"name":5,"description":7},"main","d5486aacc32c9ca1b07173cfd530f8fe75c29e58","skills\u002Fcalibration-pipeline",0,"https:\u002F\u002Fgithub.com\u002FGrimblaz\u002Fagent-orchestra","https:\u002F\u002Fgithub.com\u002FGrimblaz","2026-08-16 01:12:46",{"source":8,"skillName":5,"commands":39,"prompt":49,"zipAvailable":50},[40,43,46],{"tool":41,"command":42},"npx","npx skills add Grimblaz\u002Fagent-orchestra --skill calibration-pipeline",{"tool":44,"command":45},"bunx","bunx skills add Grimblaz\u002Fagent-orchestra --skill calibration-pipeline",{"tool":47,"command":48},"pnpm","pnpm dlx skills add Grimblaz\u002Fagent-orchestra --skill calibration-pipeline","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FGrimblaz\u002Fagent-orchestra\u002Fblob\u002Fmain\u002Fskills\u002Fcalibration-pipeline\u002FSKILL.md",true,[52,58,64,68,72,76,80,84,88,92,98,102,106,110,114,118,122,126],{"path":53,"resourceType":54,"resourceTypeDesc":55,"sizeBytes":56,"sourceHtmlUrl":57},"assets\u002Fguidance-complexity.json","ASSET","资产文件",120,"https:\u002F\u002Fgithub.com\u002FGrimblaz\u002Fagent-orchestra\u002Fblob\u002Fmain\u002Fskills\u002Fcalibration-pipeline\u002Fassets\u002Fguidance-complexity.json",{"path":59,"resourceType":60,"resourceTypeDesc":61,"sizeBytes":62,"sourceHtmlUrl":63},"references\u002Fconductor-credit-emission.md","REFERENCE","参考文档",4661,"https:\u002F\u002Fgithub.com\u002FGrimblaz\u002Fagent-orchestra\u002Fblob\u002Fmain\u002Fskills\u002Fcalibration-pipeline\u002Freferences\u002Fconductor-credit-emission.md",{"path":65,"resourceType":60,"resourceTypeDesc":61,"sizeBytes":66,"sourceHtmlUrl":67},"references\u002Fconductor-metrics-protocol.md",3844,"https:\u002F\u002Fgithub.com\u002FGrimblaz\u002Fagent-orchestra\u002Fblob\u002Fmain\u002Fskills\u002Fcalibration-pipeline\u002Freferences\u002Fconductor-metrics-protocol.md",{"path":69,"resourceType":60,"resourceTypeDesc":61,"sizeBytes":70,"sourceHtmlUrl":71},"references\u002Ffindings-construction.md",2672,"https:\u002F\u002Fgithub.com\u002FGrimblaz\u002Fagent-orchestra\u002Fblob\u002Fmain\u002Fskills\u002Fcalibration-pipeline\u002Freferences\u002Ffindings-construction.md",{"path":73,"resourceType":60,"resourceTypeDesc":61,"sizeBytes":74,"sourceHtmlUrl":75},"references\u002Fmetrics-schema.md",9145,"https:\u002F\u002Fgithub.com\u002FGrimblaz\u002Fagent-orchestra\u002Fblob\u002Fmain\u002Fskills\u002Fcalibration-pipeline\u002Freferences\u002Fmetrics-schema.md",{"path":77,"resourceType":60,"resourceTypeDesc":61,"sizeBytes":78,"sourceHtmlUrl":79},"references\u002Frelease-hygiene-credit-emission.md",4523,"https:\u002F\u002Fgithub.com\u002FGrimblaz\u002Fagent-orchestra\u002Fblob\u002Fmain\u002Fskills\u002Fcalibration-pipeline\u002Freferences\u002Frelease-hygiene-credit-emission.md",{"path":81,"resourceType":60,"resourceTypeDesc":61,"sizeBytes":82,"sourceHtmlUrl":83},"references\u002Freview-credit-emission.md",3442,"https:\u002F\u002Fgithub.com\u002FGrimblaz\u002Fagent-orchestra\u002Fblob\u002Fmain\u002Fskills\u002Fcalibration-pipeline\u002Freferences\u002Freview-credit-emission.md",{"path":85,"resourceType":60,"resourceTypeDesc":61,"sizeBytes":86,"sourceHtmlUrl":87},"references\u002Fverdict-mapping.md",819,"https:\u002F\u002Fgithub.com\u002FGrimblaz\u002Fagent-orchestra\u002Fblob\u002Fmain\u002Fskills\u002Fcalibration-pipeline\u002Freferences\u002Fverdict-mapping.md",{"path":89,"resourceType":60,"resourceTypeDesc":61,"sizeBytes":90,"sourceHtmlUrl":91},"schemas\u002Fphase-containment.schema.json",4587,"https:\u002F\u002Fgithub.com\u002FGrimblaz\u002Fagent-orchestra\u002Fblob\u002Fmain\u002Fskills\u002Fcalibration-pipeline\u002Fschemas\u002Fphase-containment.schema.json",{"path":93,"resourceType":94,"resourceTypeDesc":95,"sizeBytes":96,"sourceHtmlUrl":97},"scripts\u002Faggregate-review-scores-core.ps1","SCRIPT","脚本",76979,"https:\u002F\u002Fgithub.com\u002FGrimblaz\u002Fagent-orchestra\u002Fblob\u002Fmain\u002Fskills\u002Fcalibration-pipeline\u002Fscripts\u002Faggregate-review-scores-core.ps1",{"path":99,"resourceType":94,"resourceTypeDesc":95,"sizeBytes":100,"sourceHtmlUrl":101},"scripts\u002Faggregate-review-scores.ps1",4071,"https:\u002F\u002Fgithub.com\u002FGrimblaz\u002Fagent-orchestra\u002Fblob\u002Fmain\u002Fskills\u002Fcalibration-pipeline\u002Fscripts\u002Faggregate-review-scores.ps1",{"path":103,"resourceType":94,"resourceTypeDesc":95,"sizeBytes":104,"sourceHtmlUrl":105},"scripts\u002Fbackfill-calibration-core.ps1",8020,"https:\u002F\u002Fgithub.com\u002FGrimblaz\u002Fagent-orchestra\u002Fblob\u002Fmain\u002Fskills\u002Fcalibration-pipeline\u002Fscripts\u002Fbackfill-calibration-core.ps1",{"path":107,"resourceType":94,"resourceTypeDesc":95,"sizeBytes":108,"sourceHtmlUrl":109},"scripts\u002Fbackfill-calibration.ps1",484,"https:\u002F\u002Fgithub.com\u002FGrimblaz\u002Fagent-orchestra\u002Fblob\u002Fmain\u002Fskills\u002Fcalibration-pipeline\u002Fscripts\u002Fbackfill-calibration.ps1",{"path":111,"resourceType":94,"resourceTypeDesc":95,"sizeBytes":112,"sourceHtmlUrl":113},"scripts\u002Fcreate-improvement-issue-core.ps1",19933,"https:\u002F\u002Fgithub.com\u002FGrimblaz\u002Fagent-orchestra\u002Fblob\u002Fmain\u002Fskills\u002Fcalibration-pipeline\u002Fscripts\u002Fcreate-improvement-issue-core.ps1",{"path":115,"resourceType":94,"resourceTypeDesc":95,"sizeBytes":116,"sourceHtmlUrl":117},"scripts\u002Fcreate-improvement-issue.ps1",1291,"https:\u002F\u002Fgithub.com\u002FGrimblaz\u002Fagent-orchestra\u002Fblob\u002Fmain\u002Fskills\u002Fcalibration-pipeline\u002Fscripts\u002Fcreate-improvement-issue.ps1",{"path":119,"resourceType":94,"resourceTypeDesc":95,"sizeBytes":120,"sourceHtmlUrl":121},"scripts\u002Fpipeline-metrics-helpers.ps1",2729,"https:\u002F\u002Fgithub.com\u002FGrimblaz\u002Fagent-orchestra\u002Fblob\u002Fmain\u002Fskills\u002Fcalibration-pipeline\u002Fscripts\u002Fpipeline-metrics-helpers.ps1",{"path":123,"resourceType":94,"resourceTypeDesc":95,"sizeBytes":124,"sourceHtmlUrl":125},"scripts\u002Fwrite-calibration-entry-core.ps1",12016,"https:\u002F\u002Fgithub.com\u002FGrimblaz\u002Fagent-orchestra\u002Fblob\u002Fmain\u002Fskills\u002Fcalibration-pipeline\u002Fscripts\u002Fwrite-calibration-entry-core.ps1",{"path":127,"resourceType":94,"resourceTypeDesc":95,"sizeBytes":128,"sourceHtmlUrl":129},"scripts\u002Fwrite-calibration-entry.ps1",854,"https:\u002F\u002Fgithub.com\u002FGrimblaz\u002Fagent-orchestra\u002Fblob\u002Fmain\u002Fskills\u002Fcalibration-pipeline\u002Fscripts\u002Fwrite-calibration-entry.ps1",[131,165,189,204,232,253],{"skillNo":132,"name":133,"nameZh":6,"description":134,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":135,"categories":136,"keywords":145,"publishedAt":26},"01M6C48YMJVFHM7DVGG1WWW5RJ","webapp-testing","Playwright end-to-end testing guidance for web apps, with practical patterns and setup steps. Use when creating or improving browser-based E2E coverage, test stability, and CI execution. DO NOT USE FOR: React component tests (use ui-testing), canvas game interaction (use browser-canvas-testing), TDD workflow (use test-driven-development), debugging failures (use systematic-debugging), or randomized property tests (use property-based-testing).","https:\u002F\u002Fgithub.com\u002FGrimblaz\u002Fagent-orchestra\u002Fblob\u002Fmain\u002Fskills\u002Fwebapp-testing\u002FSKILL.md",[137,142],{"categoryNo":138,"categoryName":139,"taxonomyType":140,"taxonomyTypeDesc":141},"01JBSEEDCAT000000000000008","测试与质量","SCENARIO","使用场景",{"categoryNo":143,"categoryName":144,"taxonomyType":140,"taxonomyTypeDesc":141},"01JBSEEDCAT000000000000009","前端开发",[146,147,148,149,150,151,152,153,154,155,156,157,158,159,160,161,162,163,164,25],"testing","webapp testing","webapp","canvas","tdd","workflow","playwright","test","web","react","component","debugging","development","browser","ci","execution","e2e","game","coverage",{"skillNo":166,"name":167,"nameZh":6,"description":168,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":169,"categories":170,"keywords":171,"publishedAt":26},"01M6C48TNNP2KCSQXV8YK7SK49","verification-before-completion","Evidence-based verification checklist before marking work complete. Use before PRs, releases, marking tickets done, or any \"I'm finished\" declaration; also when naming a baseline commit for a differential suite claim, when designing a mutation campaign or red-run evidence, when making an absence claim, a universal claim, or a one-time demonstration offered as a standing guarantee, when attributing a measurement or claiming a sweep or verification loop is complete, and when stating what a check or a CI suite will do about a change. DO NOT USE FOR: post-merge cleanup or archival (use post-pr-review) or processing GitHub review comments (use code-review-intake).","https:\u002F\u002Fgithub.com\u002FGrimblaz\u002Fagent-orchestra\u002Fblob\u002Fmain\u002Fskills\u002Fverification-before-completion\u002FSKILL.md",[],[172,173,20,174,175,176,177,178,179,180,181,182,160,183,184,185,186,25,187,188],"verification","verification before completion","change","commit","merge","pr","cleanup","run","code","code-review","intake","loop","verification loop","work","check","evidence","campaign",{"skillNo":190,"name":191,"nameZh":6,"description":192,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":193,"categories":194,"keywords":195,"publishedAt":26},"01M6C48QZWNTP7JGKD32QZAKKX","validation-methodology","Reusable validation and review methodology for staged validation, failure triage, and prosecution-depth setup. Use when running validation ladders, triaging failures, or executing adversarial review passes. DO NOT USE FOR: CE Gate orchestration, specialist dispatch ownership, or step execution flow (keep those in Code-Conductor).","https:\u002F\u002Fgithub.com\u002FGrimblaz\u002Fagent-orchestra\u002Fblob\u002Fmain\u002Fskills\u002Fvalidation-methodology\u002FSKILL.md",[],[196,197,198,20,199,22,200,201,180,202,161,25,203],"validation","methodology","validation methodology","triage","setup","adversarial review","flow","dispatch",{"skillNo":205,"name":206,"nameZh":6,"description":207,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":208,"categories":209,"keywords":218,"publishedAt":26},"01M6C48MCAHG5Z79BJ369CRYRZ","upstream-onboarding","Shared opening-phase protocol for upstream agents (Experience-Owner, Solution-Designer, Issue-Planner) and Code-Conductor when invoked on an existing GitHub issue. Renders a scaled context brief and runs a standards check on inherited work at each phase boundary. Use when a user-invocable agent receives a request referencing an existing GitHub issue and must load solution-authoring and upstream-onboarding at the opening phase. DO NOT USE FOR: subagent dispatches (which already operate within an assessed session context); post-merge review (use post-pr-review); research or non-tree subagents.","https:\u002F\u002Fgithub.com\u002FGrimblaz\u002Fagent-orchestra\u002Fblob\u002Fmain\u002Fskills\u002Fupstream-onboarding\u002FSKILL.md",[210,213],{"categoryNo":211,"categoryName":212,"taxonomyType":140,"taxonomyTypeDesc":141},"01JBSEEDCAT000000000000023","Skill与智能体开发",{"categoryNo":214,"categoryName":215,"taxonomyType":216,"taxonomyTypeDesc":217},"01JBSEEDCAT000000000000038","人力资源","PROFESSION","适用职业",[219,220,20,221,222,176,223,177,180,224,225,226,227,228,229,185,186,230,231,25],"onboarding","upstream onboarding","github","research","standards check","protocol","brief","boundary","designer","subagent","planner","user","session",{"skillNo":233,"name":234,"nameZh":6,"description":235,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":236,"categories":237,"keywords":246,"publishedAt":26},"01M6C48GPVE120TGPMD1CS365H","ui-testing","Resilient React component testing strategies focusing on user behavior. Use when writing or reviewing component-level React tests, fixing flaky component tests, or establishing React testing patterns. DO NOT USE FOR: Playwright E2E tests (use webapp-testing), canvas game interaction (use browser-canvas-testing), TDD workflow (use test-driven-development), debugging failures (use systematic-debugging), UI component design (use frontend-design), or randomized property tests (use property-based-testing).","https:\u002F\u002Fgithub.com\u002FGrimblaz\u002Fagent-orchestra\u002Fblob\u002Fmain\u002Fskills\u002Fui-testing\u002FSKILL.md",[238,239,240,243],{"categoryNo":138,"categoryName":139,"taxonomyType":140,"taxonomyTypeDesc":141},{"categoryNo":143,"categoryName":144,"taxonomyType":140,"taxonomyTypeDesc":141},{"categoryNo":241,"categoryName":242,"taxonomyType":140,"taxonomyTypeDesc":141},"01JBSEEDCAT000000000000015","视觉设计",{"categoryNo":244,"categoryName":245,"taxonomyType":216,"taxonomyTypeDesc":217},"01JBSEEDCAT000000000000032","设计师",[146,247,248,249,250,251,149,151,152,153,155,156,157,158,159,252,162,163,25,148],"ui","ui testing","frontend","design","writing","testing patterns",{"skillNo":254,"name":255,"nameZh":6,"description":256,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":257,"categories":258,"keywords":261,"publishedAt":26},"01M6C48DRJ9XBDR2FW0W37DY53","ui-iteration","Reusable screenshot-driven UI polish workflow for iterative visual refinement. Use when improving layout, hierarchy, spacing, feedback, or Tailwind-based presentation through repeated review-and-adjust passes. DO NOT USE FOR: functional bug fixing, accessibility-only audits, or major redesign strategy work (use Code-Smith or frontend-design).","https:\u002F\u002Fgithub.com\u002FGrimblaz\u002Fagent-orchestra\u002Fblob\u002Fmain\u002Fskills\u002Fui-iteration\u002FSKILL.md",[259,260],{"categoryNo":143,"categoryName":144,"taxonomyType":140,"taxonomyTypeDesc":141},{"categoryNo":244,"categoryName":245,"taxonomyType":216,"taxonomyTypeDesc":217},[247,262,249,250,20,151,263,180,264,265,266,267,268,185,269,270,25,271],"ui iteration","accessibility","screenshot","Tailwind","polish","ui polish","feedback","redesign","strategy","only"]