[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M79GYVG3RCVT5N0RZ211XWJ6":3,"skill-same:01M79GYVG3RCVT5N0RZ211XWJ6":57},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":9,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":15,"categories":16,"keywords":17,"publishedAt":18,"linkOnly":19,"markdownContent":20,"markdownBody":21,"frontMatter":22,"refName":23,"commitSha":24,"skillDirectory":25,"forksCount":26,"repositoryHtmlUrl":27,"repositoryHomepageUrl":28,"ownerHtmlUrl":29,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":30,"install":31,"resources":44},"01M79GYVG3RCVT5N0RZ211XWJ6","triangulate-spec-review",null,"Review and improve architecture specs, ADRs, plugin or agent directory proposals, and other design documents by running multiple independent AI reviewers such as Claude, Qoder, Codex, or Cursor Agent against the same artifact, normalizing P1\u002FP2\u002FP3 findings, and iterating only on blocking or high-risk issues.","QoderAI\u002Fbetter-harness","QoderAI","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F219277434?v=4","01M79GY4YSX965EKC1H377AF4Q","01M79GY4ZYWF777EJFW8GED19N",2462,"MIT","https:\u002F\u002Fgithub.com\u002FQoderAI\u002Fbetter-harness\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Ftriangulate-spec-review\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: triangulate-spec-review\ndescription: Review and improve architecture specs, ADRs, plugin or agent directory proposals, and other design documents by running multiple independent AI reviewers such as Claude, Qoder, Codex, or Cursor Agent against the same artifact, normalizing P1\u002FP2\u002FP3 findings, and iterating only on blocking or high-risk issues.\n---\n\n# Triangulate Spec Review\n\nUse independent AI reviewers as an evaluation surface for specs. The lead agent\nowns synthesis, edits, validation, and the final recommendation.\n\n## Workflow\n\n1. Resolve the target spec path and the acceptance gate. If the user did not\n   name dimensions, default to `complexity`, `convenience`, and `evolution`.\n2. Read the target spec and nearby repo instructions. Do not pass your suspected\n   fixes or conclusions to reviewers.\n3. Use the same read-only prompt for every reviewer. Ask for structured\n   `P1`\u002F`P2`\u002F`P3` findings and a `p1_p2_clear` boolean.\n4. Run at least two reviewers; prefer three when available. Use\n   `scripts\u002Frun-triad-review.mjs` for repeatable local runs.\n5. Normalize findings. Treat reviewers as evidence, not authority:\n   fix convergent `P1`\u002F`P2` issues first, challenge weak or contradictory\n   findings, and leave `P3` as backlog unless it is cheap and clarifying.\n6. If the user asked for edits, patch only the owning spec or directly related\n   helper docs. Keep unrelated refactors out of the review loop.\n7. Run local validation such as `git diff --check`, relevant tests, and targeted\n   `rg` checks for renamed concepts or stale paths.\n8. Repeat the reviewer pass until every requested reviewer reports no `P1` or\n   `P2`, or until the user stops the loop.\n\n## Resources\n\n- Read `references\u002Freview-loop.md` for the prompt contract, severity rubric,\n  command matrix, and iteration patterns.\n- Run this skill's `scripts\u002Frun-triad-review.mjs --target \u003Cpath>` script,\n  resolved relative to the `triangulate-spec-review` skill directory, to execute\n  a read-only review round and write normalized JSON output.\n\n## Guardrails\n\n- Pass raw artifacts and task-local context to reviewers, not intended answers.\n- Keep every reviewer prompt materially identical unless a tool requires command\n  syntax changes.\n- Do not let reviewers edit files. The lead agent applies changes after\n  comparing findings.\n- Do not declare acceptance from an average score. Acceptance requires no\n  `P1`\u002F`P2` findings from the required review surface.\n","# Triangulate Spec Review\n\nUse independent AI reviewers as an evaluation surface for specs. The lead agent\nowns synthesis, edits, validation, and the final recommendation.\n\n## Workflow\n\n1. Resolve the target spec path and the acceptance gate. If the user did not\n   name dimensions, default to `complexity`, `convenience`, and `evolution`.\n2. Read the target spec and nearby repo instructions. Do not pass your suspected\n   fixes or conclusions to reviewers.\n3. Use the same read-only prompt for every reviewer. Ask for structured\n   `P1`\u002F`P2`\u002F`P3` findings and a `p1_p2_clear` boolean.\n4. Run at least two reviewers; prefer three when available. Use\n   `scripts\u002Frun-triad-review.mjs` for repeatable local runs.\n5. Normalize findings. Treat reviewers as evidence, not authority:\n   fix convergent `P1`\u002F`P2` issues first, challenge weak or contradictory\n   findings, and leave `P3` as backlog unless it is cheap and clarifying.\n6. If the user asked for edits, patch only the owning spec or directly related\n   helper docs. Keep unrelated refactors out of the review loop.\n7. Run local validation such as `git diff --check`, relevant tests, and targeted\n   `rg` checks for renamed concepts or stale paths.\n8. Repeat the reviewer pass until every requested reviewer reports no `P1` or\n   `P2`, or until the user stops the loop.\n\n## Resources\n\n- Read `references\u002Freview-loop.md` for the prompt contract, severity rubric,\n  command matrix, and iteration patterns.\n- Run this skill's `scripts\u002Frun-triad-review.mjs --target \u003Cpath>` script,\n  resolved relative to the `triangulate-spec-review` skill directory, to execute\n  a read-only review round and write normalized JSON output.\n\n## Guardrails\n\n- Pass raw artifacts and task-local context to reviewers, not intended answers.\n- Keep every reviewer prompt materially identical unless a tool requires command\n  syntax changes.\n- Do not let reviewers edit files. The lead agent applies changes after\n  comparing findings.\n- Do not declare acceptance from an average score. Acceptance requires no\n  `P1`\u002F`P2` findings from the required review surface.\n",{"name":5,"description":7},"main","c6240a808923630db9d6397ced789eab509f0f66",".agents\u002Fskills\u002Ftriangulate-spec-review",205,"https:\u002F\u002Fgithub.com\u002FQoderAI\u002Fbetter-harness","https:\u002F\u002Fqoderai.github.io\u002Fbetter-harness\u002F","https:\u002F\u002Fgithub.com\u002FQoderAI","2026-11-11 23:06:54",{"source":8,"skillName":5,"commands":32,"prompt":42,"zipAvailable":43},[33,36,39],{"tool":34,"command":35},"npx","npx skills add QoderAI\u002Fbetter-harness --skill triangulate-spec-review",{"tool":37,"command":38},"bunx","bunx skills add QoderAI\u002Fbetter-harness --skill triangulate-spec-review",{"tool":40,"command":41},"pnpm","pnpm dlx skills add QoderAI\u002Fbetter-harness --skill triangulate-spec-review","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FQoderAI\u002Fbetter-harness\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Ftriangulate-spec-review\u002FSKILL.md",true,[45,51],{"path":46,"resourceType":47,"resourceTypeDesc":48,"sizeBytes":49,"sourceHtmlUrl":50},"references\u002Freview-loop.md","REFERENCE","参考文档",2615,"https:\u002F\u002Fgithub.com\u002FQoderAI\u002Fbetter-harness\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Ftriangulate-spec-review\u002Freferences\u002Freview-loop.md",{"path":52,"resourceType":53,"resourceTypeDesc":54,"sizeBytes":55,"sourceHtmlUrl":56},"scripts\u002Frun-triad-review.mjs","SCRIPT","脚本",7399,"https:\u002F\u002Fgithub.com\u002FQoderAI\u002Fbetter-harness\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Ftriangulate-spec-review\u002Fscripts\u002Frun-triad-review.mjs",[58,65,72,79,86,93],{"skillNo":59,"name":60,"nameZh":6,"description":61,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":9,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":62,"categories":63,"keywords":64,"publishedAt":18},"01M79H048KTM9WH2SDF3B7JEND","verify","Verify one bounded change.","https:\u002F\u002Fgithub.com\u002FQoderAI\u002Fbetter-harness\u002Fblob\u002Fmain\u002Ftest\u002Ffixtures\u002Fharness-component-snapshot\u002Fproject\u002F.qoder\u002Fskills\u002Fverify\u002FSKILL.md",[],[],{"skillNo":66,"name":67,"nameZh":6,"description":68,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":9,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":69,"categories":70,"keywords":71,"publishedAt":18},"01M79H00NA32FVZMZ4Y4YZD8WQ","handoff","Prepare a bounded handoff.","https:\u002F\u002Fgithub.com\u002FQoderAI\u002Fbetter-harness\u002Fblob\u002Fmain\u002Ftest\u002Ffixtures\u002Fharness-component-snapshot\u002Fproject\u002F.agents\u002Fskills\u002Fhandoff\u002FSKILL.md",[],[],{"skillNo":73,"name":74,"nameZh":6,"description":75,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":9,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":76,"categories":77,"keywords":78,"publishedAt":18},"01M79GZTHYXQ0HD7QRQMDS9N2G","intent-correlation-analysis","Analyze a bounded IntentCorrelationPacketV1 and propose reviewable links among user inputs, execution slices, change units, commits, artifacts, and validation outcomes. Use when reconstructing why an observed coding-agent change exists or when Studio needs evidence-backed Intent correlation. Do not use for raw transcript summaries, deterministic file-operation collection, or autonomous confirmation of inferred Intent.","https:\u002F\u002Fgithub.com\u002FQoderAI\u002Fbetter-harness\u002Fblob\u002Fmain\u002Fskills\u002Fintent-correlation-analysis\u002FSKILL.md",[],[],{"skillNo":80,"name":81,"nameZh":6,"description":82,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":9,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":83,"categories":84,"keywords":85,"publishedAt":18},"01M79GZMG7TP1PN05085KG0FGF","better-harness","Use when \u002Fbetter-harness reviews the outer coding-agent Harness for lifecycle controls, repeated work, project feedback, agent assets, session outcomes, repair planning, durable reports, finding-bound fixes, or manual direct fixes. Invoke only via slash command.","https:\u002F\u002Fgithub.com\u002FQoderAI\u002Fbetter-harness\u002Fblob\u002Fmain\u002Fskills\u002Fbetter-harness\u002FSKILL.md",[],[],{"skillNo":87,"name":88,"nameZh":6,"description":89,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":9,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":90,"categories":91,"keywords":92,"publishedAt":18},"01M79GZFCH9PDS3BTC4HA6E16X","generate-harness-dsl","Generate, revise, or review complete Harness as Code `.harness` files when a coding-agent workflow, agent role, skill, tool contract, MCP connection, runtime, or deployment must be compiler-valid and resolvable with `@qoder-ai\u002Fharness`.","https:\u002F\u002Fgithub.com\u002FQoderAI\u002Fbetter-harness\u002Fblob\u002Fmain\u002Fpackages\u002Fharness\u002Fskills\u002Fgenerate-harness-dsl\u002FSKILL.md",[],[],{"skillNo":94,"name":95,"nameZh":6,"description":96,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":9,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":97,"categories":98,"keywords":99,"publishedAt":18},"01M79GZAV6TVS44HKQS4SPAX2M","memory-recap","Create evidence-linked work profiles, diagnose Coding Agent collaboration friction, and recommend concrete improvements from native memories or frozen exports. Use for memory recaps and agent-usage retrospectives, not memory maintenance or session-performance measurement.","https:\u002F\u002Fgithub.com\u002FQoderAI\u002Fbetter-harness\u002Fblob\u002Fmain\u002Fpackages\u002Fharness-studio\u002Fskills\u002Fmemory-recap\u002FSKILL.md",[],[]]