[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M79GYJ51KTENYA70TY8QFC9P":3,"skill-same:01M79GYJ51KTENYA70TY8QFC9P":51},{"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},"01M79GYJ51KTENYA70TY8QFC9P","harness-skill-creator",null,"Use when bootstrapping or tightening the smallest harness-oriented skill from an existing repository, workflow, evaluation corpus, or harness-analysis chain. Trigger for meta skills, reusable harness workflows, Qoder\u002FCodex plugin skill sets, skill blueprints, and harness-analysis-like skills that need evidence-backed references, validation gates, and qodercli forward-tests.","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\u002Fharness-skill-creator\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: harness-skill-creator\ndescription: Use when bootstrapping or tightening the smallest harness-oriented skill from an existing repository, workflow, evaluation corpus, or harness-analysis chain. Trigger for meta skills, reusable harness workflows, Qoder\u002FCodex plugin skill sets, skill blueprints, and harness-analysis-like skills that need evidence-backed references, validation gates, and qodercli forward-tests.\n---\n\n# Harness Skill Creator\n\nCreate the smallest skill that makes another agent repeat one harness job with\nevidence, validation, and clear ownership.\n\n## Workflow\n\n1. Resolve source, target, and host: canonical `skills\u002F\u003Cname>\u002F`, `.agents\u002Fskills\u002F` wrapper, or both.\n2. Inspect the source chain before designing: entry `SKILL.md`, first-hop\n   references, scripts, validators, templates, specs, tests, plugin manifests,\n   and any real smoke evidence.\n3. Load `references\u002Fbootstrap-patterns.md` after the first inventory. Use it to\n   extract patterns, not product-specific rules.\n4. Draft the minimum viable skill map:\n   - skill name and trigger sentence\n   - one job the skill owns\n   - files to create under `skills\u002F\u003Cskill-name>\u002F`, usually `SKILL.md` plus one reference\n   - evidence boundary and validation commands\n   - forward-test prompt and pass\u002Ffail gates\n5. Initialize new canonical skills with the system `skill-creator` helper when\n   available. Add `scripts\u002F` only for stable repeated automation; keep ad-hoc\n   evaluation prompts out of runtime scripts.\n6. Write the `SKILL.md` as a router. Put trigger conditions in frontmatter\n   `description`, keep the body short, and route detailed rules to first-hop\n   references.\n7. Validate locally, then forward-test. Treat qodercli output as model evidence;\n   local validators and file inspection decide pass\u002Ffail.\n\n## Design Gates\n\n- Prefer one skill over a stage tree until the target process proves multiple\n  reusable stages.\n- Copy ownership shape, not product names, branch policy, private commands, or\n  source-specific team routing.\n- Keep `.agents\u002Fskills\u002F` as a wrapper or mirror when the workflow is shared by\n  the plugin; canonical judgment belongs under root `skills\u002F`.\n- Do not add install, network, server, migration, or dependency-changing\n  commands unless the user requested them and source evidence supports them.\n- Prefer portable Node\u002FPython validators or target-owned commands. Do not default generated validation gates to Unix-only `grep`\u002F`find` checks.\n- In attachment-only or no-tools forward-tests, never emit tool-call markup, shell probes, or inspection plans; return the skill map with `status: \"insufficient-evidence\"` when needed.\n- Forward-test `files` is a string array of `skills\u002F\u003Cskill-name>\u002F...` paths, not objects.\n- If the generated skill cannot pass `quick_validate.py \u003Cskill-dir>`, do not\n  describe it as usable.\n- After any forward-test, verify git status or file inventory for every repo the\n  model was allowed to read or write.\n\n## Validation\n\nRun the narrowest useful gates for the created skill:\n\n```bash\npython3 \u003Cskill-creator-root>\u002Fscripts\u002Fquick_validate.py \u003Cskill-dir>\nqodercli --cwd \u003Cneutral-dir> --plugin-dir \u003Charness-root> -p \"\u003Cforward-test prompt>\"\nqodercli plugin validate \u003Charness-root>\n```\n\nReject missing frontmatter, stale placeholders, broken links, unsupported\ncommands, source-only assumptions, pseudo tool calls, or broad reports.\n","# Harness Skill Creator\n\nCreate the smallest skill that makes another agent repeat one harness job with\nevidence, validation, and clear ownership.\n\n## Workflow\n\n1. Resolve source, target, and host: canonical `skills\u002F\u003Cname>\u002F`, `.agents\u002Fskills\u002F` wrapper, or both.\n2. Inspect the source chain before designing: entry `SKILL.md`, first-hop\n   references, scripts, validators, templates, specs, tests, plugin manifests,\n   and any real smoke evidence.\n3. Load `references\u002Fbootstrap-patterns.md` after the first inventory. Use it to\n   extract patterns, not product-specific rules.\n4. Draft the minimum viable skill map:\n   - skill name and trigger sentence\n   - one job the skill owns\n   - files to create under `skills\u002F\u003Cskill-name>\u002F`, usually `SKILL.md` plus one reference\n   - evidence boundary and validation commands\n   - forward-test prompt and pass\u002Ffail gates\n5. Initialize new canonical skills with the system `skill-creator` helper when\n   available. Add `scripts\u002F` only for stable repeated automation; keep ad-hoc\n   evaluation prompts out of runtime scripts.\n6. Write the `SKILL.md` as a router. Put trigger conditions in frontmatter\n   `description`, keep the body short, and route detailed rules to first-hop\n   references.\n7. Validate locally, then forward-test. Treat qodercli output as model evidence;\n   local validators and file inspection decide pass\u002Ffail.\n\n## Design Gates\n\n- Prefer one skill over a stage tree until the target process proves multiple\n  reusable stages.\n- Copy ownership shape, not product names, branch policy, private commands, or\n  source-specific team routing.\n- Keep `.agents\u002Fskills\u002F` as a wrapper or mirror when the workflow is shared by\n  the plugin; canonical judgment belongs under root `skills\u002F`.\n- Do not add install, network, server, migration, or dependency-changing\n  commands unless the user requested them and source evidence supports them.\n- Prefer portable Node\u002FPython validators or target-owned commands. Do not default generated validation gates to Unix-only `grep`\u002F`find` checks.\n- In attachment-only or no-tools forward-tests, never emit tool-call markup, shell probes, or inspection plans; return the skill map with `status: \"insufficient-evidence\"` when needed.\n- Forward-test `files` is a string array of `skills\u002F\u003Cskill-name>\u002F...` paths, not objects.\n- If the generated skill cannot pass `quick_validate.py \u003Cskill-dir>`, do not\n  describe it as usable.\n- After any forward-test, verify git status or file inventory for every repo the\n  model was allowed to read or write.\n\n## Validation\n\nRun the narrowest useful gates for the created skill:\n\n```bash\npython3 \u003Cskill-creator-root>\u002Fscripts\u002Fquick_validate.py \u003Cskill-dir>\nqodercli --cwd \u003Cneutral-dir> --plugin-dir \u003Charness-root> -p \"\u003Cforward-test prompt>\"\nqodercli plugin validate \u003Charness-root>\n```\n\nReject missing frontmatter, stale placeholders, broken links, unsupported\ncommands, source-only assumptions, pseudo tool calls, or broad reports.\n",{"name":5,"description":7},"main","c6240a808923630db9d6397ced789eab509f0f66",".agents\u002Fskills\u002Fharness-skill-creator",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 harness-skill-creator",{"tool":37,"command":38},"bunx","bunx skills add QoderAI\u002Fbetter-harness --skill harness-skill-creator",{"tool":40,"command":41},"pnpm","pnpm dlx skills add QoderAI\u002Fbetter-harness --skill harness-skill-creator","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FQoderAI\u002Fbetter-harness\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fharness-skill-creator\u002FSKILL.md",true,[45],{"path":46,"resourceType":47,"resourceTypeDesc":48,"sizeBytes":49,"sourceHtmlUrl":50},"references\u002Fbootstrap-patterns.md","REFERENCE","参考文档",3605,"https:\u002F\u002Fgithub.com\u002FQoderAI\u002Fbetter-harness\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fharness-skill-creator\u002Freferences\u002Fbootstrap-patterns.md",[52,59,66,73,80,87],{"skillNo":53,"name":54,"nameZh":6,"description":55,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":9,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":56,"categories":57,"keywords":58,"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":60,"name":61,"nameZh":6,"description":62,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":9,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":63,"categories":64,"keywords":65,"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":67,"name":68,"nameZh":6,"description":69,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":9,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":70,"categories":71,"keywords":72,"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":74,"name":75,"nameZh":6,"description":76,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":9,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":77,"categories":78,"keywords":79,"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":81,"name":82,"nameZh":6,"description":83,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":9,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":84,"categories":85,"keywords":86,"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":88,"name":89,"nameZh":6,"description":90,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":9,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":91,"categories":92,"keywords":93,"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",[],[]]