[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M79GYQ3A484W1652KDRXQR2R":3,"skill-same:01M79GYQ3A484W1652KDRXQR2R":59},{"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},"01M79GYQ3A484W1652KDRXQR2R","skill-review",null,"Use when reviewing Codex, Qoder, or repo-local skills and their prompt chains for trigger quality, workflow clarity, progressive disclosure, duplicated instructions, template ownership, output readability, validation gaps, or whether a skill should be edited.","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\u002Fskill-review\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: skill-review\ndescription: Use when reviewing Codex, Qoder, or repo-local skills and their prompt chains for trigger quality, workflow clarity, progressive disclosure, duplicated instructions, template ownership, output readability, validation gaps, or whether a skill should be edited.\n---\n\n# Skill Review\n\nReview a skill as an execution contract, not as prose. Trace how an agent would\nenter, load, delegate, produce artifacts, and verify results; then report the\nsmallest changes that would improve that chain.\n\n## Review Workflow\n\n1. Resolve the target skill or prompt chain. If the user names a path, stay on\n   that path and its directly linked resources.\n2. Read repo instructions first: nearest `AGENTS.md`, plugin manifests, and the\n   target `SKILL.md` frontmatter\u002Fbody.\n3. Trace the chain from entrypoint to references, templates, scripts, detectors,\n   tests, generated artifacts, and validation commands. Build an ownership map:\n   what file owns workflow, output structure, runtime rules, style, and tests.\n4. Audit the contract before editing. Use [Audit Checklist](references\u002Faudit-checklist.md)\n   and [Reference Patterns](references\u002Freference-patterns.md) as lenses.\n5. If the user asked for changes, patch only the smallest owning files. Keep\n   generated helpers, smoke scripts, and local experiments outside `SKILL.md`\n   unless they are durable resources the skill must use.\n6. Validate with the lightest real gate available: skill validator, repo tests,\n   plugin validation, or a bounded agent smoke. State any gate that could not be\n   run.\n\nUse subagents only as an evaluation surface or for independent broad research.\nThe lead agent owns the review, final calibration, and file edits. Pass raw\nartifacts and task-local scope to subagents; do not pass the intended answer.\n\n## Review Lenses\n\n- [Audit Checklist](references\u002Faudit-checklist.md): trigger contract, progressive\n  disclosure, workflow\u002Fdelegation, template ownership, readability, evidence.\n- [Reference Patterns](references\u002Freference-patterns.md): reusable design lenses\n  such as Trigger\u002FProtocol split, Gate Function, and Output Contract Slots.\n- [Fast Inspection Commands](references\u002Finspection-commands.md): starting `rg`,\n  `wc`, and `git diff --check` probes adapted to the repo.\n\n## Finding Severity\n\n- **P0**: The skill points to missing, empty, contradictory, or invalid resources;\n  an agent can follow the instructions and fail.\n- **P1**: The skill works but wastes context, duplicates ownership, hides key\n  constraints, or produces unreadable output.\n- **P2**: Style, naming, wording, or organization issues that reduce scanability\n  without breaking the workflow.\n\n## Report Shape\n\nLead with findings, ordered by severity. Keep each finding concrete:\n\n```text\nP1 - \u003Cshort title>\nFile: \u003Cpath>:\u003Cline>\nWhy it matters: \u003Cexecution or output risk>\nEvidence: \u003Cquoted phrase, command result, or linked resource>\nFix: \u003Csmallest owning-file change>\nValidation: \u003Ccommand or smoke that should prove it>\n```\n\nAfter findings, add open questions only when they block a safe change. If the\nuser asked for edits, include changed files and validation results after the\nfindings. Default to the user's language.\n","# Skill Review\n\nReview a skill as an execution contract, not as prose. Trace how an agent would\nenter, load, delegate, produce artifacts, and verify results; then report the\nsmallest changes that would improve that chain.\n\n## Review Workflow\n\n1. Resolve the target skill or prompt chain. If the user names a path, stay on\n   that path and its directly linked resources.\n2. Read repo instructions first: nearest `AGENTS.md`, plugin manifests, and the\n   target `SKILL.md` frontmatter\u002Fbody.\n3. Trace the chain from entrypoint to references, templates, scripts, detectors,\n   tests, generated artifacts, and validation commands. Build an ownership map:\n   what file owns workflow, output structure, runtime rules, style, and tests.\n4. Audit the contract before editing. Use [Audit Checklist](references\u002Faudit-checklist.md)\n   and [Reference Patterns](references\u002Freference-patterns.md) as lenses.\n5. If the user asked for changes, patch only the smallest owning files. Keep\n   generated helpers, smoke scripts, and local experiments outside `SKILL.md`\n   unless they are durable resources the skill must use.\n6. Validate with the lightest real gate available: skill validator, repo tests,\n   plugin validation, or a bounded agent smoke. State any gate that could not be\n   run.\n\nUse subagents only as an evaluation surface or for independent broad research.\nThe lead agent owns the review, final calibration, and file edits. Pass raw\nartifacts and task-local scope to subagents; do not pass the intended answer.\n\n## Review Lenses\n\n- [Audit Checklist](references\u002Faudit-checklist.md): trigger contract, progressive\n  disclosure, workflow\u002Fdelegation, template ownership, readability, evidence.\n- [Reference Patterns](references\u002Freference-patterns.md): reusable design lenses\n  such as Trigger\u002FProtocol split, Gate Function, and Output Contract Slots.\n- [Fast Inspection Commands](references\u002Finspection-commands.md): starting `rg`,\n  `wc`, and `git diff --check` probes adapted to the repo.\n\n## Finding Severity\n\n- **P0**: The skill points to missing, empty, contradictory, or invalid resources;\n  an agent can follow the instructions and fail.\n- **P1**: The skill works but wastes context, duplicates ownership, hides key\n  constraints, or produces unreadable output.\n- **P2**: Style, naming, wording, or organization issues that reduce scanability\n  without breaking the workflow.\n\n## Report Shape\n\nLead with findings, ordered by severity. Keep each finding concrete:\n\n```text\nP1 - \u003Cshort title>\nFile: \u003Cpath>:\u003Cline>\nWhy it matters: \u003Cexecution or output risk>\nEvidence: \u003Cquoted phrase, command result, or linked resource>\nFix: \u003Csmallest owning-file change>\nValidation: \u003Ccommand or smoke that should prove it>\n```\n\nAfter findings, add open questions only when they block a safe change. If the\nuser asked for edits, include changed files and validation results after the\nfindings. Default to the user's language.\n",{"name":5,"description":7},"main","c6240a808923630db9d6397ced789eab509f0f66",".agents\u002Fskills\u002Fskill-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 skill-review",{"tool":37,"command":38},"bunx","bunx skills add QoderAI\u002Fbetter-harness --skill skill-review",{"tool":40,"command":41},"pnpm","pnpm dlx skills add QoderAI\u002Fbetter-harness --skill skill-review","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FQoderAI\u002Fbetter-harness\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fskill-review\u002FSKILL.md",true,[45,51,55],{"path":46,"resourceType":47,"resourceTypeDesc":48,"sizeBytes":49,"sourceHtmlUrl":50},"references\u002Faudit-checklist.md","REFERENCE","参考文档",2052,"https:\u002F\u002Fgithub.com\u002FQoderAI\u002Fbetter-harness\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fskill-review\u002Freferences\u002Faudit-checklist.md",{"path":52,"resourceType":47,"resourceTypeDesc":48,"sizeBytes":53,"sourceHtmlUrl":54},"references\u002Finspection-commands.md",341,"https:\u002F\u002Fgithub.com\u002FQoderAI\u002Fbetter-harness\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fskill-review\u002Freferences\u002Finspection-commands.md",{"path":56,"resourceType":47,"resourceTypeDesc":48,"sizeBytes":57,"sourceHtmlUrl":58},"references\u002Freference-patterns.md",3635,"https:\u002F\u002Fgithub.com\u002FQoderAI\u002Fbetter-harness\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fskill-review\u002Freferences\u002Freference-patterns.md",[60,67,74,81,88,95],{"skillNo":61,"name":62,"nameZh":6,"description":63,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":9,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":64,"categories":65,"keywords":66,"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":68,"name":69,"nameZh":6,"description":70,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":9,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":71,"categories":72,"keywords":73,"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":75,"name":76,"nameZh":6,"description":77,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":9,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":78,"categories":79,"keywords":80,"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":82,"name":83,"nameZh":6,"description":84,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":9,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":85,"categories":86,"keywords":87,"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":89,"name":90,"nameZh":6,"description":91,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":9,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":92,"categories":93,"keywords":94,"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":96,"name":97,"nameZh":6,"description":98,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":9,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":99,"categories":100,"keywords":101,"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",[],[]]