[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M79GZFCH9PDS3BTC4HA6E16X":3,"skill-same:01M79GZFCH9PDS3BTC4HA6E16X":61},{"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},"01M79GZFCH9PDS3BTC4HA6E16X","generate-harness-dsl",null,"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`.","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\u002Fpackages\u002Fharness\u002Fskills\u002Fgenerate-harness-dsl\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: generate-harness-dsl\ndescription: 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`.\n---\n\n# Generate Harness DSL\n\nCreate a standalone Harness as Code v0.3 document and prove the execution\ncontract with the package compiler and resolver.\n\n## Workflow\n\n1. Identify the host, the capabilities it must actually expose, and the real\n   control owner. Use `session` for one host session. Use `state-machine` or\n   `program` only when a selected adapter explicitly implements that mode.\n2. Read [the DSL contract](references\u002Fdsl-contract.md). Start from\n   [the minimal example](..\u002F..\u002Fexamples\u002Fminimal.harness); open\n   [the standard example](..\u002F..\u002Fexamples\u002Fstandard-coding.harness) when callable\n   tools are required.\n3. Generate one self-contained document unless the user requests a fragment.\n   Include `language 0.3`, every referenced declaration, a concrete runtime,\n   and a named deployment. Standard tools may remain implicit.\n4. Run `scripts\u002Fvalidate.mjs`. Fix every compiler or resolution error and rerun.\n   A compile-only state machine is not an executable Qoder or Pi deployment.\n5. Return the DSL or saved file plus the harness id, deployment id, runtime,\n   resolution status, and any execution boundary the selected adapter cannot\n   satisfy.\n\n## Authoring Rules\n\n- State only falsifiable requirements. Do not add permission, setting,\n  degradation, binding, input\u002Foutput-name, or runtime-execution syntax; v0.3\n  intentionally has none.\n- Match the requirement verb to its capability: `use skill`, `require tool`,\n  or `connect mcp`.\n- Only the standard tool ids in the contract may be undeclared. Every custom\n  tool declares a stable `contract` id that the adapter exposure must match.\n- Qoder and Pi descriptors run `session` workflows only. A session workflow\n  names exactly the one agent role declared by each harness that uses it.\n- State-machine outcomes are typed on agents. Every route emitter, outcome,\n  destination, entry, and stop must exist, and every agent must be reachable.\n- A `program \u003Clanguage> \u003Centry>` workflow resolves only when the adapter lists\n  the same language in `programmaticLanguages`.\n- Keep credentials out of source. Prefer `env.VARIABLE` for MCP endpoints, but\n  remember that declaring an endpoint does not connect it; the adapter must do\n  that.\n- Do not invoke host SDKs, install integrations, or claim native enforcement\n  while generating or validating DSL.\n\n## Validate\n\nFrom this skill directory, run:\n\n```sh\nnode scripts\u002Fvalidate.mjs \u002Fpath\u002Fto\u002Fworkflow.harness [harness-id ...]\n```\n\nThe command prints JSON and exits non-zero when compilation or any selected\nnamed deployment fails resolution. A successful exit is required before\ncalling generated DSL executable.\n\nWhen editing this skill, build the package first so `dist\u002F` reflects the current\ncompiler:\n\n```sh\nnpm run harness:build\n```\n","# Generate Harness DSL\n\nCreate a standalone Harness as Code v0.3 document and prove the execution\ncontract with the package compiler and resolver.\n\n## Workflow\n\n1. Identify the host, the capabilities it must actually expose, and the real\n   control owner. Use `session` for one host session. Use `state-machine` or\n   `program` only when a selected adapter explicitly implements that mode.\n2. Read [the DSL contract](references\u002Fdsl-contract.md). Start from\n   [the minimal example](..\u002F..\u002Fexamples\u002Fminimal.harness); open\n   [the standard example](..\u002F..\u002Fexamples\u002Fstandard-coding.harness) when callable\n   tools are required.\n3. Generate one self-contained document unless the user requests a fragment.\n   Include `language 0.3`, every referenced declaration, a concrete runtime,\n   and a named deployment. Standard tools may remain implicit.\n4. Run `scripts\u002Fvalidate.mjs`. Fix every compiler or resolution error and rerun.\n   A compile-only state machine is not an executable Qoder or Pi deployment.\n5. Return the DSL or saved file plus the harness id, deployment id, runtime,\n   resolution status, and any execution boundary the selected adapter cannot\n   satisfy.\n\n## Authoring Rules\n\n- State only falsifiable requirements. Do not add permission, setting,\n  degradation, binding, input\u002Foutput-name, or runtime-execution syntax; v0.3\n  intentionally has none.\n- Match the requirement verb to its capability: `use skill`, `require tool`,\n  or `connect mcp`.\n- Only the standard tool ids in the contract may be undeclared. Every custom\n  tool declares a stable `contract` id that the adapter exposure must match.\n- Qoder and Pi descriptors run `session` workflows only. A session workflow\n  names exactly the one agent role declared by each harness that uses it.\n- State-machine outcomes are typed on agents. Every route emitter, outcome,\n  destination, entry, and stop must exist, and every agent must be reachable.\n- A `program \u003Clanguage> \u003Centry>` workflow resolves only when the adapter lists\n  the same language in `programmaticLanguages`.\n- Keep credentials out of source. Prefer `env.VARIABLE` for MCP endpoints, but\n  remember that declaring an endpoint does not connect it; the adapter must do\n  that.\n- Do not invoke host SDKs, install integrations, or claim native enforcement\n  while generating or validating DSL.\n\n## Validate\n\nFrom this skill directory, run:\n\n```sh\nnode scripts\u002Fvalidate.mjs \u002Fpath\u002Fto\u002Fworkflow.harness [harness-id ...]\n```\n\nThe command prints JSON and exits non-zero when compilation or any selected\nnamed deployment fails resolution. A successful exit is required before\ncalling generated DSL executable.\n\nWhen editing this skill, build the package first so `dist\u002F` reflects the current\ncompiler:\n\n```sh\nnpm run harness:build\n```\n",{"name":5,"description":7},"main","c6240a808923630db9d6397ced789eab509f0f66","packages\u002Fharness\u002Fskills\u002Fgenerate-harness-dsl",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 generate-harness-dsl",{"tool":37,"command":38},"bunx","bunx skills add QoderAI\u002Fbetter-harness --skill generate-harness-dsl",{"tool":40,"command":41},"pnpm","pnpm dlx skills add QoderAI\u002Fbetter-harness --skill generate-harness-dsl","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FQoderAI\u002Fbetter-harness\u002Fblob\u002Fmain\u002Fpackages\u002Fharness\u002Fskills\u002Fgenerate-harness-dsl\u002FSKILL.md",true,[45,51,55],{"path":46,"resourceType":47,"resourceTypeDesc":48,"sizeBytes":49,"sourceHtmlUrl":50},"agents\u002Fopenai.yaml","REFERENCE","参考文档",237,"https:\u002F\u002Fgithub.com\u002FQoderAI\u002Fbetter-harness\u002Fblob\u002Fmain\u002Fpackages\u002Fharness\u002Fskills\u002Fgenerate-harness-dsl\u002Fagents\u002Fopenai.yaml",{"path":52,"resourceType":47,"resourceTypeDesc":48,"sizeBytes":53,"sourceHtmlUrl":54},"references\u002Fdsl-contract.md",4588,"https:\u002F\u002Fgithub.com\u002FQoderAI\u002Fbetter-harness\u002Fblob\u002Fmain\u002Fpackages\u002Fharness\u002Fskills\u002Fgenerate-harness-dsl\u002Freferences\u002Fdsl-contract.md",{"path":56,"resourceType":57,"resourceTypeDesc":58,"sizeBytes":59,"sourceHtmlUrl":60},"scripts\u002Fvalidate.mjs","SCRIPT","脚本",3029,"https:\u002F\u002Fgithub.com\u002FQoderAI\u002Fbetter-harness\u002Fblob\u002Fmain\u002Fpackages\u002Fharness\u002Fskills\u002Fgenerate-harness-dsl\u002Fscripts\u002Fvalidate.mjs",[62,69,76,83,90,97],{"skillNo":63,"name":64,"nameZh":6,"description":65,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":9,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":66,"categories":67,"keywords":68,"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":70,"name":71,"nameZh":6,"description":72,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":9,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":73,"categories":74,"keywords":75,"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":77,"name":78,"nameZh":6,"description":79,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":9,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":80,"categories":81,"keywords":82,"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":84,"name":85,"nameZh":6,"description":86,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":9,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":87,"categories":88,"keywords":89,"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":91,"name":92,"nameZh":6,"description":93,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":9,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":94,"categories":95,"keywords":96,"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",[],[],{"skillNo":98,"name":99,"nameZh":6,"description":100,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":9,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":101,"categories":102,"keywords":103,"publishedAt":18},"01M79GZ63WWFKM9V2VMBEGXQ7X","reproduce-frontend-bug","Build a bounded, replayable browser or UI bug reproduction from GitHub Issues, Jira, Aone, user-provided exports, screenshots, videos, comments, or attachments. Use for browser, WebView, IDE or desktop UI, interaction, responsive, rendering, accessibility, or visual defects that need evidence-preserving reproduction before diagnosis or repair; do not use for ordinary implementation or backend-only failures.","https:\u002F\u002Fgithub.com\u002FQoderAI\u002Fbetter-harness\u002Fblob\u002Fmain\u002Fcase-studies\u002Fagent-customize\u002Fbug-diagnosis-skills\u002Freproduce-frontend-bug\u002FSKILL.md",[],[]]