[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6JVV57C7PTRB6EQQ33NRCPE":3,"skill-same:01M6JVV57C7PTRB6EQQ33NRCPE":58},{"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":30,"linkOnly":31,"markdownContent":32,"markdownBody":33,"frontMatter":34,"refName":35,"commitSha":36,"skillDirectory":37,"forksCount":38,"repositoryHtmlUrl":39,"repositoryHomepageUrl":40,"ownerHtmlUrl":41,"ownerBlogUrl":42,"ownerDescription":6,"updatedAt":43,"install":44,"resources":57},"01M6JVV57C7PTRB6EQQ33NRCPE","evidence-gap-review",null,"Analyse specgraph verify output and identify what evidence is missing to advance specs to their next state.","45ck\u002Fskill-harness","45ck","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F98618920?v=4","01M6JVMEERB77XKFGN2RT770BP","Calvin","01M6JVMEK42E6WBBD4R3QE9Y4P",15,"MIT","https:\u002F\u002Fgithub.com\u002F45ck\u002Fskill-harness\u002Fblob\u002Fmain\u002Fpacks\u002Fspecgraph-skills\u002Fskills\u002Fevidence-gap-review\u002FSKILL.md",[],[19,20,21,22,23,24,25,26,27,28,29],"review","evidence","gap","evidence gap review","state","verify","advance","next","missing","output","verify output","2026-11-10 10:12:30",false,"---\nname: evidence-gap-review\ndescription: Analyse specgraph verify output and identify what evidence is missing to advance specs to their next state.\n---\n\nReview the output of `specgraph verify` (or `specgraph verify --json`) and produce an actionable gap report.\n\n## Procedure\n\n1. Run `specgraph verify` (or read the provided output).\n2. For each spec with status `WARN`, `FAIL`, or `INSUFFICIENT`:\n   - Identify the required evidence dimension(s) that are unmet.\n   - State the current evidence level and what level is needed.\n   - Suggest the lowest-effort action that would provide the required evidence.\n3. Group findings by effort: low (annotation), medium (test), high (architecture decision).\n\n## Evidence-gap action map\n\n| Required level | Unmet because | Recommended action |\n|----------------|---------------|--------------------|\n| E0 | No `@spec` annotation | Add `\u002F** @spec ID @implements Feature *\u002F` to the implementation file |\n| E1 | No closed Beads issue or structural artifact | Create a Beads issue with `--spec-id ID` and close it when done |\n| E2 | Not indexed in specgraph DB \u002F no linked artifact | Run `specgraph verify` to store claims, add cross-refs via `depends_on` |\n| E3 | No test annotation | Add `\u002F** @spec ID @verifies Feature *\u002F` to a test file |\n| E4 | No CI artifact | Configure `freshness.artifacts` in `.specgraph\u002Fconfig.json` |\n\n## Status meanings\n\n| Status | Meaning |\n|--------|---------|\n| `PASS` | All required evidence thresholds met |\n| `WARN` | Evidence exists but below required strength for this state |\n| `FAIL` | No evidence found for a required dimension |\n| `INSUFFICIENT` | Evidence found but strength is below required level (e.g. E0 found, E2 required) |\n| `SKIP` | Spec has no evidence requirements (draft\u002Fdeprecated) |\n| `WAIVED` | Requirement waived — check expiry |\n\n## Output format\n\nFor each gap, output:\n\n```\nSPEC-ID  [WARN|FAIL|INSUFFICIENT]  dimension=\u003Cname>  need=\u003CEx>  have=\u003CEy|none>\n  → Action: \u003Cone-line description>\n```\n\nThen a prioritised action list (most impactful first).\n\n## Useful drill-down commands\n\n```bash\nspecgraph verify                     # summary table for all specs\nspecgraph verify --json              # machine-readable output\nspecgraph verify --spec SPEC-ID      # single spec only\nspecgraph explain SPEC-ID            # full claim breakdown for one spec\nspecgraph find --spec SPEC-ID        # locate files that reference a spec\nspecgraph find --relation IMPLEMENTS # all IMPLEMENTS claims\nspecgraph find --strength 1          # E1 and above\nspecgraph waivers                    # list active waivers\n```\n\n## Rules\n\n1. Do not suggest adding waivers unless the requirement is genuinely unreachable.\n2. Prefer adding annotations over creating new files.\n3. If multiple specs share the same gap pattern, batch the fix into a single suggestion.\n4. Check `specgraph explain \u003CSPEC-ID>` for detailed claim breakdown when unsure what evidence exists.\n5. Config file is `.specgraph\u002Fconfig.json` (falls back to `.agent-docs\u002Fconfig.json`).\n","Review the output of `specgraph verify` (or `specgraph verify --json`) and produce an actionable gap report.\n\n## Procedure\n\n1. Run `specgraph verify` (or read the provided output).\n2. For each spec with status `WARN`, `FAIL`, or `INSUFFICIENT`:\n   - Identify the required evidence dimension(s) that are unmet.\n   - State the current evidence level and what level is needed.\n   - Suggest the lowest-effort action that would provide the required evidence.\n3. Group findings by effort: low (annotation), medium (test), high (architecture decision).\n\n## Evidence-gap action map\n\n| Required level | Unmet because | Recommended action |\n|----------------|---------------|--------------------|\n| E0 | No `@spec` annotation | Add `\u002F** @spec ID @implements Feature *\u002F` to the implementation file |\n| E1 | No closed Beads issue or structural artifact | Create a Beads issue with `--spec-id ID` and close it when done |\n| E2 | Not indexed in specgraph DB \u002F no linked artifact | Run `specgraph verify` to store claims, add cross-refs via `depends_on` |\n| E3 | No test annotation | Add `\u002F** @spec ID @verifies Feature *\u002F` to a test file |\n| E4 | No CI artifact | Configure `freshness.artifacts` in `.specgraph\u002Fconfig.json` |\n\n## Status meanings\n\n| Status | Meaning |\n|--------|---------|\n| `PASS` | All required evidence thresholds met |\n| `WARN` | Evidence exists but below required strength for this state |\n| `FAIL` | No evidence found for a required dimension |\n| `INSUFFICIENT` | Evidence found but strength is below required level (e.g. E0 found, E2 required) |\n| `SKIP` | Spec has no evidence requirements (draft\u002Fdeprecated) |\n| `WAIVED` | Requirement waived — check expiry |\n\n## Output format\n\nFor each gap, output:\n\n```\nSPEC-ID  [WARN|FAIL|INSUFFICIENT]  dimension=\u003Cname>  need=\u003CEx>  have=\u003CEy|none>\n  → Action: \u003Cone-line description>\n```\n\nThen a prioritised action list (most impactful first).\n\n## Useful drill-down commands\n\n```bash\nspecgraph verify                     # summary table for all specs\nspecgraph verify --json              # machine-readable output\nspecgraph verify --spec SPEC-ID      # single spec only\nspecgraph explain SPEC-ID            # full claim breakdown for one spec\nspecgraph find --spec SPEC-ID        # locate files that reference a spec\nspecgraph find --relation IMPLEMENTS # all IMPLEMENTS claims\nspecgraph find --strength 1          # E1 and above\nspecgraph waivers                    # list active waivers\n```\n\n## Rules\n\n1. Do not suggest adding waivers unless the requirement is genuinely unreachable.\n2. Prefer adding annotations over creating new files.\n3. If multiple specs share the same gap pattern, batch the fix into a single suggestion.\n4. Check `specgraph explain \u003CSPEC-ID>` for detailed claim breakdown when unsure what evidence exists.\n5. Config file is `.specgraph\u002Fconfig.json` (falls back to `.agent-docs\u002Fconfig.json`).\n",{"name":5,"description":7},"main","31fedf0ad5fb02ca599add38ef92ce9ebfdaf785","packs\u002Fspecgraph-skills\u002Fskills\u002Fevidence-gap-review",1,"https:\u002F\u002Fgithub.com\u002F45ck\u002Fskill-harness","https:\u002F\u002Fgithub.com\u002F45ck\u002Fskill-harness\u002Freleases\u002Ftag\u002Fv0.1.0","https:\u002F\u002Fgithub.com\u002F45ck","calvinkennedy.com","2026-06-23 16:42:42",{"source":8,"skillName":5,"commands":45,"prompt":55,"zipAvailable":56},[46,49,52],{"tool":47,"command":48},"npx","npx skills add 45ck\u002Fskill-harness --skill evidence-gap-review",{"tool":50,"command":51},"bunx","bunx skills add 45ck\u002Fskill-harness --skill evidence-gap-review",{"tool":53,"command":54},"pnpm","pnpm dlx skills add 45ck\u002Fskill-harness --skill evidence-gap-review","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002F45ck\u002Fskill-harness\u002Fblob\u002Fmain\u002Fpacks\u002Fspecgraph-skills\u002Fskills\u002Fevidence-gap-review\u002FSKILL.md",true,[],[59,77,87,109,122,142],{"skillNo":60,"name":61,"nameZh":6,"description":62,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":63,"categories":64,"keywords":70,"publishedAt":30},"01M6JVWQZDB2JC8FC6Q2KKH0HV","risky-skill","Synthetic risky skill for intake scanner coverage.","https:\u002F\u002Fgithub.com\u002F45ck\u002Fskill-harness\u002Fblob\u002Fmain\u002Ftests\u002Ffixtures\u002Fexternal-skill-intake\u002Frisky-script-pack\u002Fskills\u002Frisky-skill\u002FSKILL.md",[65],{"categoryNo":66,"categoryName":67,"taxonomyType":68,"taxonomyTypeDesc":69},"01JBSEEDCAT000000000000023","Skill与智能体开发","SCENARIO","使用场景",[71,72,73,74,75,76],"risky skill","for","synthetic","scanner","coverage","intake",{"skillNo":78,"name":79,"nameZh":6,"description":80,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":81,"categories":82,"keywords":84,"publishedAt":30},"01M6JVWKG4SGT1M3TVDDDS4PDD","fixture-skill","Synthetic skill for intake scanner coverage.","https:\u002F\u002Fgithub.com\u002F45ck\u002Fskill-harness\u002Fblob\u002Fmain\u002Ftests\u002Ffixtures\u002Fexternal-skill-intake\u002Fclean-cross-host-pack\u002Fskills\u002Ffixture-skill\u002FSKILL.md",[83],{"categoryNo":66,"categoryName":67,"taxonomyType":68,"taxonomyTypeDesc":69},[85,86,73,76,75,74,72],"fixture skill","fixture",{"skillNo":88,"name":89,"nameZh":6,"description":90,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":91,"categories":92,"keywords":94,"publishedAt":30},"01M6JVWE7C4FKEF3PGZVZ31FFG","third-party-skill-intake","Review third-party skill repos for format fit, provenance, and first-party adoption paths without treating them as direct harness dependencies.","https:\u002F\u002Fgithub.com\u002F45ck\u002Fskill-harness\u002Fblob\u002Fmain\u002Fplugins\u002Fskill-harness-helpers\u002Fskills\u002Fthird-party-skill-intake\u002FSKILL.md",[93],{"categoryNo":66,"categoryName":67,"taxonomyType":68,"taxonomyTypeDesc":69},[76,95,96,97,98,99,100,101,102,103,104,105,106,72,107,19,108],"party","third party skill intake","paths","adoption","first","provenance","format","direct","dependencies","third-party","as","fit","harness","repos",{"skillNo":110,"name":111,"nameZh":6,"description":112,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":113,"categories":114,"keywords":116,"publishedAt":30},"01M6JVW8YAFFNP0Q1XWXE1WH6G","loop","Handle \u002Floop-style requests for finding, adapting, drafting, and preparing bounded agent loops without treating external loop catalogs as authorization.","https:\u002F\u002Fgithub.com\u002F45ck\u002Fskill-harness\u002Fblob\u002Fmain\u002Fplugins\u002Fskill-harness-helpers\u002Fskills\u002Floop\u002FSKILL.md",[115],{"categoryNo":66,"categoryName":67,"taxonomyType":68,"taxonomyTypeDesc":69},[111,117,118,105,119,120,121,72],"bounded","authorization","style","loops","requests",{"skillNo":123,"name":124,"nameZh":6,"description":125,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":126,"categories":127,"keywords":128,"publishedAt":30},"01M6JVW3EWZ6DES0NQP7YMBZQS","beads-task-shaping","Convert analysis output into actionable Beads-ready work items with clear scope, priority, and acceptance checks.","https:\u002F\u002Fgithub.com\u002F45ck\u002Fskill-harness\u002Fblob\u002Fmain\u002Fplugins\u002Fskill-harness-helpers\u002Fskills\u002Fbeads-task-shaping\u002FSKILL.md",[],[129,130,131,132,133,134,135,136,137,138,139,140,28,141],"beads task shaping","task","shaping","beads","scope","acceptance","analysis","convert","work","ready","clear","actionable","with",{"skillNo":143,"name":144,"nameZh":6,"description":145,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":146,"categories":147,"keywords":149,"publishedAt":30},"01M6JVVYNGXYZTFT7YRCE6MME6","agent-selection","Select the best workflow agent for a task based on task shape, deliverables, and dependency packs.","https:\u002F\u002Fgithub.com\u002F45ck\u002Fskill-harness\u002Fblob\u002Fmain\u002Fplugins\u002Fskill-harness-helpers\u002Fskills\u002Fagent-selection\u002FSKILL.md",[148],{"categoryNo":66,"categoryName":67,"taxonomyType":68,"taxonomyTypeDesc":69},[150,151,152,153,154,130,155,72,156],"agent selection","selection","select","dependency","shape","deliverables","workflow"]