[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6DHASZYRB1ZZWVNQ6CN8FN3":3,"skill-same:01M6DHASZYRB1ZZWVNQ6CN8FN3":82},{"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":27,"linkOnly":28,"markdownContent":29,"markdownBody":30,"frontMatter":31,"refName":32,"commitSha":33,"skillDirectory":34,"forksCount":13,"repositoryHtmlUrl":35,"repositoryHomepageUrl":6,"ownerHtmlUrl":36,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":37,"install":38,"resources":51},"01M6DHASZYRB1ZZWVNQ6CN8FN3","verify",null,"Verification and auditing. Validate acceptance scenarios, run multi-perspective audits, check type-check\u002Fbuild evidence, and gate phase\u002Fsprint completion.","JAuto-Corp\u002Fjustinventit","JAuto-Corp","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F254009312?v=4","01M6DH85D43FJAXD8RPBY6A91C","01M6DH85M60CDJBZ9W2CAFCPXE",0,"MIT","https:\u002F\u002Fgithub.com\u002FJAuto-Corp\u002Fjustinventit\u002Fblob\u002Fmain\u002Ftemplate\u002F.claude\u002Fskills\u002Forchestrators\u002Fverify\u002FSKILL.md",[],[5,18,19,20,21,22,23,24,25,26],"validate","run","acceptance","verification","check","evidence","gate","build","type","2026-11-10 10:12:30",false,"---\nname: verify\ndescription: \"Verification and auditing. Validate acceptance scenarios, run multi-perspective audits, check type-check\u002Fbuild evidence, and gate phase\u002Fsprint completion.\"\n---\n\n# Verification\n\nProve work does what the SPEC said, then gate the phase\u002Fsprint. `\u002Fverify:complete` is the exit gate `\u002Fwork:done` calls — it PRODUCES the evidence the stop hooks look for (`checks\u002F03-scenario-evidence`, `04-tdd-cycle`, `05-progress-evidence`) when you signal `[PHASE_COMPLETE]`. The other commands are lighter, on-demand audits over a chosen surface.\n\n> Audit validates code *looks* correct. Scenario evidence validates code *works*. A phase needs both. Walk the SPEC line-by-line — never aggregate a \"looks done\" verdict.\n\n## Commands\n\n| Command | Purpose | Workflow |\n|-|-|-|\n| `\u002Fverify:complete` | Full phase validation — the exit gate | `complete.md` |\n| `\u002Fverify:phase` | Light audit of the current phase | `phase.md` |\n| `\u002Fverify:sprint` | Audit an entire sprint before merge | `sprint.md` |\n| `\u002Fverify:file` | Audit specific file(s) + their callers | `file.md` |\n| `\u002Fverify:feature` | Audit a named feature across the codebase | `feature.md` |\n| `\u002Fverify:audit` | Deploy a multi-perspective audit (the engine) | `audit.md` |\n| `\u002Fverify:recent` | Audit the last few commits | `recent.md` |\n\n## Shared foundations\n\n**State chain** (read in order — see `CLAUDE.md` § Session State Management): `docs\u002FCURRENT_WORK.md` → `context\u002FWORKING.md` → phase `SPEC.md` \u002F `SCENARIOS.md` \u002F `PROGRESS.md`.\n\n**Configured commands**: reference the project's type-check and build commands abstractly — read `type_check_command` \u002F `build_command` from `.copier-answers.yml`, or `CLAUDE.md` § Essential Commands. Never hardcode a stack's tooling.\n\n**Multi-perspective audit**: every audit command deploys parallel Explore agents (see the `patterns` skill § Multi-Explorer Pattern) — one per perspective that applies to the changed surface, each returning a bounded (\u003C2000 char) summary. Explorers cannot load skills; after they report, YOU invoke the project's matching best-practices skill(s) (`.claude\u002Fskills\u002Fdomain\u002F`) and cross-reference their findings. The perspective menu and report template live in `audit.md`.\n\n**Coherence rule**: verify code state first (git log, file reads), then update docs\u002Fissues — never record from memory alone.\n\n**Friction**: when verification exposes a bad skill\u002Fhook\u002Fworkflow step, emit the matching `[FRICTION:*]` signal (see `patterns` skill § Friction Signals); the stop hook logs it.\n\n---\n\n## \u002Fverify:complete\n\nExit gate for phase completion. Confirm every acceptance scenario has a recorded passing run, walk the SPEC line-by-line into a met\u002Fpartial\u002Fnot-met verdict table, run a multi-perspective audit, cross-reference best-practices skills, pass the configured type-check + build, update the state chain, and align docs ↔ issues. Any `partial`\u002F`not-met` row blocks. Only on a clean pass do you check off `PROGRESS.md` and signal `[PHASE_COMPLETE]` — the moment the stop-hook evidence checks fire. Full workflow: `complete.md`.\n\n## \u002Fverify:phase\n\nLighter than `complete` — a targeted audit of the current phase's changed surface for pattern alignment and coherence, ending in a `WORKING.md` phase-transition marker. Use before moving on; use `\u002Fverify:complete` for official completion. Full workflow: `phase.md`.\n\n## \u002Fverify:sprint\n\nFull validation before marking a sprint complete and merging. Aggregate scenario coverage across the sprint's phases, run a cross-phase audit, confirm each phase passed its exit gate, and block the merge on any unmet criteria. Full workflow: `sprint.md`.\n\n## \u002Fverify:file\n\nTargeted audit of specific file(s). Read the target and its immediate dependencies, find its callers, deploy explorers scoped to the file's role, cross-reference the matching best-practices skill, and assess caller impact. Full workflow: `file.md`.\n\n## \u002Fverify:feature\n\nAudit a named feature across its full implementation. Discover every participating file, deploy explorers scoped to them, check completeness across every layer the feature touches, and report gaps. Full workflow: `feature.md`.\n\n## \u002Fverify:audit\n\nThe multi-perspective audit engine the other commands call. Scope the surface, deploy the subset of perspectives that applies, consolidate bounded explorer findings, and cross-reference best-practices skills. Full workflow: `audit.md`.\n\n## \u002Fverify:recent\n\nQuick audit of the last few commits before a PR or handoff. Read the recent diffs, categorize the changed files, deploy the applicable perspectives, and report CLEAN \u002F ISSUES. Full workflow: `recent.md`.\n","# Verification\n\nProve work does what the SPEC said, then gate the phase\u002Fsprint. `\u002Fverify:complete` is the exit gate `\u002Fwork:done` calls — it PRODUCES the evidence the stop hooks look for (`checks\u002F03-scenario-evidence`, `04-tdd-cycle`, `05-progress-evidence`) when you signal `[PHASE_COMPLETE]`. The other commands are lighter, on-demand audits over a chosen surface.\n\n> Audit validates code *looks* correct. Scenario evidence validates code *works*. A phase needs both. Walk the SPEC line-by-line — never aggregate a \"looks done\" verdict.\n\n## Commands\n\n| Command | Purpose | Workflow |\n|-|-|-|\n| `\u002Fverify:complete` | Full phase validation — the exit gate | `complete.md` |\n| `\u002Fverify:phase` | Light audit of the current phase | `phase.md` |\n| `\u002Fverify:sprint` | Audit an entire sprint before merge | `sprint.md` |\n| `\u002Fverify:file` | Audit specific file(s) + their callers | `file.md` |\n| `\u002Fverify:feature` | Audit a named feature across the codebase | `feature.md` |\n| `\u002Fverify:audit` | Deploy a multi-perspective audit (the engine) | `audit.md` |\n| `\u002Fverify:recent` | Audit the last few commits | `recent.md` |\n\n## Shared foundations\n\n**State chain** (read in order — see `CLAUDE.md` § Session State Management): `docs\u002FCURRENT_WORK.md` → `context\u002FWORKING.md` → phase `SPEC.md` \u002F `SCENARIOS.md` \u002F `PROGRESS.md`.\n\n**Configured commands**: reference the project's type-check and build commands abstractly — read `type_check_command` \u002F `build_command` from `.copier-answers.yml`, or `CLAUDE.md` § Essential Commands. Never hardcode a stack's tooling.\n\n**Multi-perspective audit**: every audit command deploys parallel Explore agents (see the `patterns` skill § Multi-Explorer Pattern) — one per perspective that applies to the changed surface, each returning a bounded (\u003C2000 char) summary. Explorers cannot load skills; after they report, YOU invoke the project's matching best-practices skill(s) (`.claude\u002Fskills\u002Fdomain\u002F`) and cross-reference their findings. The perspective menu and report template live in `audit.md`.\n\n**Coherence rule**: verify code state first (git log, file reads), then update docs\u002Fissues — never record from memory alone.\n\n**Friction**: when verification exposes a bad skill\u002Fhook\u002Fworkflow step, emit the matching `[FRICTION:*]` signal (see `patterns` skill § Friction Signals); the stop hook logs it.\n\n---\n\n## \u002Fverify:complete\n\nExit gate for phase completion. Confirm every acceptance scenario has a recorded passing run, walk the SPEC line-by-line into a met\u002Fpartial\u002Fnot-met verdict table, run a multi-perspective audit, cross-reference best-practices skills, pass the configured type-check + build, update the state chain, and align docs ↔ issues. Any `partial`\u002F`not-met` row blocks. Only on a clean pass do you check off `PROGRESS.md` and signal `[PHASE_COMPLETE]` — the moment the stop-hook evidence checks fire. Full workflow: `complete.md`.\n\n## \u002Fverify:phase\n\nLighter than `complete` — a targeted audit of the current phase's changed surface for pattern alignment and coherence, ending in a `WORKING.md` phase-transition marker. Use before moving on; use `\u002Fverify:complete` for official completion. Full workflow: `phase.md`.\n\n## \u002Fverify:sprint\n\nFull validation before marking a sprint complete and merging. Aggregate scenario coverage across the sprint's phases, run a cross-phase audit, confirm each phase passed its exit gate, and block the merge on any unmet criteria. Full workflow: `sprint.md`.\n\n## \u002Fverify:file\n\nTargeted audit of specific file(s). Read the target and its immediate dependencies, find its callers, deploy explorers scoped to the file's role, cross-reference the matching best-practices skill, and assess caller impact. Full workflow: `file.md`.\n\n## \u002Fverify:feature\n\nAudit a named feature across its full implementation. Discover every participating file, deploy explorers scoped to them, check completeness across every layer the feature touches, and report gaps. Full workflow: `feature.md`.\n\n## \u002Fverify:audit\n\nThe multi-perspective audit engine the other commands call. Scope the surface, deploy the subset of perspectives that applies, consolidate bounded explorer findings, and cross-reference best-practices skills. Full workflow: `audit.md`.\n\n## \u002Fverify:recent\n\nQuick audit of the last few commits before a PR or handoff. Read the recent diffs, categorize the changed files, deploy the applicable perspectives, and report CLEAN \u002F ISSUES. Full workflow: `recent.md`.\n",{"name":5,"description":7},"main","07fef474a459f2562dbae35a3baf6470c8ae530d","template\u002F.claude\u002Fskills\u002Forchestrators\u002Fverify","https:\u002F\u002Fgithub.com\u002FJAuto-Corp\u002Fjustinventit","https:\u002F\u002Fgithub.com\u002FJAuto-Corp","2026-11-10 13:45:22",{"source":8,"skillName":5,"commands":39,"prompt":49,"zipAvailable":50},[40,43,46],{"tool":41,"command":42},"npx","npx skills add JAuto-Corp\u002Fjustinventit --skill verify",{"tool":44,"command":45},"bunx","bunx skills add JAuto-Corp\u002Fjustinventit --skill verify",{"tool":47,"command":48},"pnpm","pnpm dlx skills add JAuto-Corp\u002Fjustinventit --skill verify","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FJAuto-Corp\u002Fjustinventit\u002Fblob\u002Fmain\u002Ftemplate\u002F.claude\u002Fskills\u002Forchestrators\u002Fverify\u002FSKILL.md",true,[52,58,62,66,70,74,78],{"path":53,"resourceType":54,"resourceTypeDesc":55,"sizeBytes":56,"sourceHtmlUrl":57},"audit.md","REFERENCE","参考文档",2548,"https:\u002F\u002Fgithub.com\u002FJAuto-Corp\u002Fjustinventit\u002Fblob\u002Fmain\u002Ftemplate\u002F.claude\u002Fskills\u002Forchestrators\u002Fverify\u002Faudit.md",{"path":59,"resourceType":54,"resourceTypeDesc":55,"sizeBytes":60,"sourceHtmlUrl":61},"complete.md",3843,"https:\u002F\u002Fgithub.com\u002FJAuto-Corp\u002Fjustinventit\u002Fblob\u002Fmain\u002Ftemplate\u002F.claude\u002Fskills\u002Forchestrators\u002Fverify\u002Fcomplete.md",{"path":63,"resourceType":54,"resourceTypeDesc":55,"sizeBytes":64,"sourceHtmlUrl":65},"feature.md",1449,"https:\u002F\u002Fgithub.com\u002FJAuto-Corp\u002Fjustinventit\u002Fblob\u002Fmain\u002Ftemplate\u002F.claude\u002Fskills\u002Forchestrators\u002Fverify\u002Ffeature.md",{"path":67,"resourceType":54,"resourceTypeDesc":55,"sizeBytes":68,"sourceHtmlUrl":69},"file.md",1400,"https:\u002F\u002Fgithub.com\u002FJAuto-Corp\u002Fjustinventit\u002Fblob\u002Fmain\u002Ftemplate\u002F.claude\u002Fskills\u002Forchestrators\u002Fverify\u002Ffile.md",{"path":71,"resourceType":54,"resourceTypeDesc":55,"sizeBytes":72,"sourceHtmlUrl":73},"phase.md",1351,"https:\u002F\u002Fgithub.com\u002FJAuto-Corp\u002Fjustinventit\u002Fblob\u002Fmain\u002Ftemplate\u002F.claude\u002Fskills\u002Forchestrators\u002Fverify\u002Fphase.md",{"path":75,"resourceType":54,"resourceTypeDesc":55,"sizeBytes":76,"sourceHtmlUrl":77},"recent.md",1291,"https:\u002F\u002Fgithub.com\u002FJAuto-Corp\u002Fjustinventit\u002Fblob\u002Fmain\u002Ftemplate\u002F.claude\u002Fskills\u002Forchestrators\u002Fverify\u002Frecent.md",{"path":79,"resourceType":54,"resourceTypeDesc":55,"sizeBytes":80,"sourceHtmlUrl":81},"sprint.md",1917,"https:\u002F\u002Fgithub.com\u002FJAuto-Corp\u002Fjustinventit\u002Fblob\u002Fmain\u002Ftemplate\u002F.claude\u002Fskills\u002Forchestrators\u002Fverify\u002Fsprint.md",[83,110,134,156,176,198],{"skillNo":84,"name":85,"nameZh":6,"description":86,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":87,"sourceHtmlUrl":88,"categories":89,"keywords":90,"publishedAt":27},"01M6DHBJE2P291DTXAW6DE6ZSR","ponytail","Forces the laziest solution that actually works, simplest, shortest, most minimal. Channels a senior dev who has seen everything: question whether the task needs to exist at all (YAGNI), reach for the standard library before custom code, native platform features before dependencies, one line before fifty. Supports intensity levels: lite, full (default), ultra. Use on ANY coding task: writing, adding, refactoring, fixing, reviewing, or designing code, and choosing libraries or dependencies. Also use whenever the user says \"ponytail\", \"be lazy\", \"lazy mode\", \"simplest solution\", \"minimal solution\", \"yagni\", \"do less\", or \"shortest path\", or complains about over-engineering, bloat, boilerplate, or unnecessary dependencies. Do NOT use for non-coding requests (general knowledge, prose, translation, summaries, recipes).","https:\u002F\u002Fgithub.com\u002FJAuto-Corp\u002Fjustinventit\u002Fblob\u002Fmain\u002Ftemplate\u002F.claude\u002Fskills\u002Fponytail\u002FLICENSE.txt","https:\u002F\u002Fgithub.com\u002FJAuto-Corp\u002Fjustinventit\u002Fblob\u002Fmain\u002Ftemplate\u002F.claude\u002Fskills\u002Fponytail\u002FSKILL.md",[],[85,91,92,93,94,95,96,97,98,99,100,101,102,103,104,105,106,107,108,109],"use","line","recipes","platform","dependencies","task","do","translation","default","general","minimal","yagni","question","refactoring","knowledge","dev","code","libraries","writing",{"skillNo":111,"name":112,"nameZh":6,"description":113,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":114,"categories":115,"keywords":126,"publishedAt":27},"01M6DHB61PAWVGHF53A89MJ6SM","workflow\u002Fskill","Patterns for adding or editing a skill — frontmatter contract, router + sub-file split, line budgets.","https:\u002F\u002Fgithub.com\u002FJAuto-Corp\u002Fjustinventit\u002Fblob\u002Fmain\u002Ftemplate\u002F.claude\u002Fskills\u002Forchestrators\u002Fworkflow\u002Fskill.md",[116,121],{"categoryNo":117,"categoryName":118,"taxonomyType":119,"taxonomyTypeDesc":120},"01JBSEEDCAT000000000000023","Skill与智能体开发","SCENARIO","使用场景",{"categoryNo":122,"categoryName":123,"taxonomyType":124,"taxonomyTypeDesc":125},"01JBSEEDCAT000000000000037","律师与法务","PROFESSION","适用职业",[127,128,129,130,131,132,92,133],"workflow","workflow skill","editing","file","patterns","router","contract",{"skillNo":135,"name":127,"nameZh":6,"description":136,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":137,"categories":138,"keywords":140,"publishedAt":27},"01M6DHB1GD89RW71ZYZJZJH4ZG","Meta-skill for editing the framework itself — skills, hooks, commands, rules, CLAUDE.md. Use before changing anything under .claude\u002F or the routing docs, so the change keeps the system's shape (lazy-load, forge markers, hook auto-discovery, harness).","https:\u002F\u002Fgithub.com\u002FJAuto-Corp\u002Fjustinventit\u002Fblob\u002Fmain\u002Ftemplate\u002F.claude\u002Fskills\u002Forchestrators\u002Fworkflow\u002FSKILL.md",[139],{"categoryNo":117,"categoryName":118,"taxonomyType":119,"taxonomyTypeDesc":120},[127,91,141,142,143,144,145,129,146,147,148,149,150,151,152,153,154,155],"commands","meta-skill","shape","hooks","auto","Rules","system","discovery","Meta","forge","harness","framework","routing","change","docs",{"skillNo":157,"name":158,"nameZh":6,"description":159,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":160,"categories":161,"keywords":162,"publishedAt":27},"01M6DHAX1NCV3HXK4M1RMBWGAV","work","Work lifecycle orchestration: start, continue, pause, handoff, done, plus epic\u002Fsprint planning. Context gathering + goal-focused state-chain transitions.","https:\u002F\u002Fgithub.com\u002FJAuto-Corp\u002Fjustinventit\u002Fblob\u002Fmain\u002Ftemplate\u002F.claude\u002Fskills\u002Forchestrators\u002Fwork\u002FSKILL.md",[],[158,163,164,165,166,167,168,169,170,171,172,173,174,175],"transitions","handoff","sprint planning","done","goal","context","continue","lifecycle","start","state","planning","orchestration","chain",{"skillNo":177,"name":178,"nameZh":6,"description":179,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":180,"categories":181,"keywords":182,"publishedAt":27},"01M6DHAP9JN9X7ZSWCWYTWN1KT","team-lead","Coordinate an Agent Team for parallelizable work — implementation, audit, research, or testing. Teaches the mechanical constraints (WAIT pattern, file ownership, model tiers) and lets you design the team. For orchestration_tier=cluster \u002F multi-agent runs.","https:\u002F\u002Fgithub.com\u002FJAuto-Corp\u002Fjustinventit\u002Fblob\u002Fmain\u002Ftemplate\u002F.claude\u002Fskills\u002Forchestrators\u002Fteam-lead\u002FSKILL.md",[],[183,184,130,174,185,186,187,188,189,190,191,192,193,194,158,195,196,197],"team","team lead","research","design","testing","audit","wait","mechanical","pattern","agent team","coordinate","implementation","multi-agent","model","constraints",{"skillNo":199,"name":200,"nameZh":6,"description":201,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":202,"categories":203,"keywords":207,"publishedAt":27},"01M6DHAJTF40984VZYBZHFD52D","scope","Plan and design work before building. Invoke when starting an epic, scoping a sprint, or planning any Standard+ change: orient on what exists, equip the planning procedure + domain skills, then produce the SPEC\u002FSCENARIOS\u002FPROGRESS structure and converge it through an audit loop. Feeds \u002Fwork:epic-plan and the ATDD entry gate.","https:\u002F\u002Fgithub.com\u002FJAuto-Corp\u002Fjustinventit\u002Fblob\u002Fmain\u002Ftemplate\u002F.claude\u002Fskills\u002Forchestrators\u002Fscope\u002FSKILL.md",[204],{"categoryNo":205,"categoryName":206,"taxonomyType":119,"taxonomyTypeDesc":120},"01JBSEEDCAT000000000000015","视觉设计",[200,208,209,210,211,212,24,213,158,214,215,216,217,188,218,173,154,219,186],"before building","progress","orient","domain","structure","scoping","plan","loop","equip","feeds","produce","spec"]