[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M79MM0759PXQCDF9EF79FFSM":3,"skill-same:01M79MM0759PXQCDF9EF79FFSM":52},{"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":19,"linkOnly":20,"markdownContent":21,"markdownBody":22,"frontMatter":23,"refName":24,"commitSha":25,"skillDirectory":26,"forksCount":14,"repositoryHtmlUrl":27,"repositoryHomepageUrl":28,"ownerHtmlUrl":29,"ownerBlogUrl":30,"ownerDescription":6,"updatedAt":31,"install":32,"resources":45},"01M79MM0759PXQCDF9EF79FFSM","add-coding-agent-integration",null,"Orchestrate a complete Braintrust coding-agent integration by delegating feasibility, daemon translation, event capture, setup, managed run, transcript import, verification, and shipping to the specialized repo-local skills. Use for end-to-end support for a new agent or a completeness audit of an existing integration; use the component skills directly for focused work.","braintrustdata\u002Fbraintrust-coding-agent-plugins","braintrustdata","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F128932779?v=4","01M77HXQSY5673JXZEA4HJ8P23","Braintrust","01M79MKJVWZJKG9XWZQMF17ASR",3,"Apache-2.0","https:\u002F\u002Fgithub.com\u002Fbraintrustdata\u002Fbraintrust-coding-agent-plugins\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fadd-coding-agent-integration\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: add-coding-agent-integration\ndescription: Orchestrate a complete Braintrust coding-agent integration by delegating feasibility, daemon translation, event capture, setup, managed run, transcript import, verification, and shipping to the specialized repo-local skills. Use for end-to-end support for a new agent or a completeness audit of an existing integration; use the component skills directly for focused work.\n---\n\n# Orchestrate a coding-agent integration\n\nCoordinate the integration; do not implement component details from this skill.\nInspect current source, keep a requirement-to-evidence inventory, and invoke the\nspecialized skill for every applicable workstream.\n\n## Delegate the work\n\n1. Use `audit-agent-tracing-support` to establish whether hooks, an in-process\n   plugin API, transcripts, or a combination can provide sufficient data.\n2. Use `add-coding-agent-translator` to establish the canonical source identity\n   and production daemon translator first.\n3. Use `add-coding-agent-capture` to forward live native events through command\n   hooks or an in-process plugin.\n4. Once the translator exists, delegate independently:\n   - persistent installation and configuration to `add-coding-agent-setup`;\n   - invocation-local launching to `add-coding-agent-run`;\n   - historical import and live transcript following to\n     `add-coding-agent-import`, when a viable transcript exists.\n5. Use `test-coding-agent-integration` to verify every implemented surface and\n   the combined end-to-end path.\n6. Use `ship-coding-agent-integration` only after verification evidence exists.\n\nAdd every applicable skill to the working plan and follow that skill when its\nworkstream begins. Do not copy its instructions into the plan or preload skills\nfor workstreams that are out of scope.\n\n## Maintain the shared contract\n\nKeep one stable source identity across the translator, capture adapter, setup,\nrun, import, status, tests, and documentation. Keep plugins and hooks thin,\nfail-open, credential-free forwarders; the daemon owns correlation, trace\nconstruction, recovery, routing, and delivery.\n\nTreat a missing capability as `blocked` or explicitly `not applicable` with\nevidence, never as silently complete. Do not call the integration complete\nuntil each applicable component skill has produced implementation and test\nevidence and the shipping skill has confirmed a releasable distribution path.\n\n## Hand off\n\nReport a compact matrix with one row per delegated skill: status, source\nevidence, test evidence, blockers or fidelity loss, and remaining release work.\n","# Orchestrate a coding-agent integration\n\nCoordinate the integration; do not implement component details from this skill.\nInspect current source, keep a requirement-to-evidence inventory, and invoke the\nspecialized skill for every applicable workstream.\n\n## Delegate the work\n\n1. Use `audit-agent-tracing-support` to establish whether hooks, an in-process\n   plugin API, transcripts, or a combination can provide sufficient data.\n2. Use `add-coding-agent-translator` to establish the canonical source identity\n   and production daemon translator first.\n3. Use `add-coding-agent-capture` to forward live native events through command\n   hooks or an in-process plugin.\n4. Once the translator exists, delegate independently:\n   - persistent installation and configuration to `add-coding-agent-setup`;\n   - invocation-local launching to `add-coding-agent-run`;\n   - historical import and live transcript following to\n     `add-coding-agent-import`, when a viable transcript exists.\n5. Use `test-coding-agent-integration` to verify every implemented surface and\n   the combined end-to-end path.\n6. Use `ship-coding-agent-integration` only after verification evidence exists.\n\nAdd every applicable skill to the working plan and follow that skill when its\nworkstream begins. Do not copy its instructions into the plan or preload skills\nfor workstreams that are out of scope.\n\n## Maintain the shared contract\n\nKeep one stable source identity across the translator, capture adapter, setup,\nrun, import, status, tests, and documentation. Keep plugins and hooks thin,\nfail-open, credential-free forwarders; the daemon owns correlation, trace\nconstruction, recovery, routing, and delivery.\n\nTreat a missing capability as `blocked` or explicitly `not applicable` with\nevidence, never as silently complete. Do not call the integration complete\nuntil each applicable component skill has produced implementation and test\nevidence and the shipping skill has confirmed a releasable distribution path.\n\n## Hand off\n\nReport a compact matrix with one row per delegated skill: status, source\nevidence, test evidence, blockers or fidelity loss, and remaining release work.\n",{"name":5,"description":7},"main","e168d549aa7679385d987077bc12ce5a45ddc861",".agents\u002Fskills\u002Fadd-coding-agent-integration","https:\u002F\u002Fgithub.com\u002Fbraintrustdata\u002Fbraintrust-coding-agent-plugins","https:\u002F\u002Fwww.braintrust.dev\u002F","https:\u002F\u002Fgithub.com\u002Fbraintrustdata","https:\u002F\u002Fbraintrust.dev","2026-11-14 04:41:44",{"source":8,"skillName":5,"commands":33,"prompt":43,"zipAvailable":44},[34,37,40],{"tool":35,"command":36},"npx","npx skills add braintrustdata\u002Fbraintrust-coding-agent-plugins --skill add-coding-agent-integration",{"tool":38,"command":39},"bunx","bunx skills add braintrustdata\u002Fbraintrust-coding-agent-plugins --skill add-coding-agent-integration",{"tool":41,"command":42},"pnpm","pnpm dlx skills add braintrustdata\u002Fbraintrust-coding-agent-plugins --skill add-coding-agent-integration","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fbraintrustdata\u002Fbraintrust-coding-agent-plugins\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fadd-coding-agent-integration\u002FSKILL.md",true,[46],{"path":47,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":50,"sourceHtmlUrl":51},"agents\u002Fopenai.yaml","REFERENCE","参考文档",234,"https:\u002F\u002Fgithub.com\u002Fbraintrustdata\u002Fbraintrust-coding-agent-plugins\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fadd-coding-agent-integration\u002Fagents\u002Fopenai.yaml",[53,60,67,74,81,88],{"skillNo":54,"name":55,"nameZh":6,"description":56,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":57,"categories":58,"keywords":59,"publishedAt":19},"01M79MN1PSBXVXNMZEH0Q5Y2WJ","troubleshoot-braintrust-mcp","Diagnose Braintrust MCP connection issues.","https:\u002F\u002Fgithub.com\u002Fbraintrustdata\u002Fbraintrust-coding-agent-plugins\u002Fblob\u002Fmain\u002Fsrc\u002Fskills\u002Ftroubleshoot-braintrust-mcp\u002FSKILL.md",[],[],{"skillNo":61,"name":62,"nameZh":6,"description":63,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":64,"categories":65,"keywords":66,"publishedAt":19},"01M79MMZ29PZNAMRGSGYCRK5M7","braintrust","Use Braintrust for LLM evaluation, logging, and observability.","https:\u002F\u002Fgithub.com\u002Fbraintrustdata\u002Fbraintrust-coding-agent-plugins\u002Fblob\u002Fmain\u002Fsrc\u002Fskills\u002Fbraintrust\u002FSKILL.md",[],[],{"skillNo":68,"name":69,"nameZh":6,"description":70,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":71,"categories":72,"keywords":73,"publishedAt":19},"01M79MMV2MH28HJFMMCHVJ62DE","test-coding-agent-integration","Test or audit a coding-agent tracing integration across translator fixtures, capture adapters, setup, managed run, transcript import, daemon recovery, real-agent execution, package installation, and CI. Use when adding verification, reviewing integration completeness, diagnosing coverage gaps, or proving that emitted events become correct Braintrust traces.","https:\u002F\u002Fgithub.com\u002Fbraintrustdata\u002Fbraintrust-coding-agent-plugins\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Ftest-coding-agent-integration\u002FSKILL.md",[],[],{"skillNo":75,"name":76,"nameZh":6,"description":77,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":78,"categories":79,"keywords":80,"publishedAt":19},"01M79MMPJQB0EPN3M7JBJA2B93","ship-coding-agent-integration","Package and release a coding-agent tracing integration through its marketplace, package registry, or distribution repository, including manifests, builds, validation, versioning, CI, documentation, publishing automation, and installed-artifact smoke tests. Use when preparing an integration for release or auditing whether it has a complete distribution path.","https:\u002F\u002Fgithub.com\u002Fbraintrustdata\u002Fbraintrust-coding-agent-plugins\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fship-coding-agent-integration\u002FSKILL.md",[],[],{"skillNo":82,"name":83,"nameZh":6,"description":84,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":85,"categories":86,"keywords":87,"publishedAt":19},"01M79MMHTVVV5CMYJE3C1K00XJ","audit-agent-tracing-support","Assess whether a coding agent's hooks\u002Fplugin API can support tracing (per docs\u002Ftrace-coding-agents-with-hooks.md), or whether a reliable fallback like session transcripts exists. Use when evaluating a new or existing coding agent (Claude Code, Codex, Cursor, Gemini CLI, Aider, etc.) for a Braintrust tracing plugin, or when someone asks \"can we trace agent X\" \u002F \"is agent X's hook API good enough\".","https:\u002F\u002Fgithub.com\u002Fbraintrustdata\u002Fbraintrust-coding-agent-plugins\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Faudit-agent-tracing-support\u002FSKILL.md",[],[],{"skillNo":89,"name":90,"nameZh":6,"description":91,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":92,"categories":93,"keywords":94,"publishedAt":19},"01M79MMDJKG3JXX2VQX6AZAQSB","add-coding-agent-translator","Implement or review a coding agent's daemon translator, including source registration, native event correlation, trace shape, deterministic recovery, routing metadata, and translator tests. Use when adding a new agent translator or changing how an existing agent's hooks or transcripts become Braintrust spans.","https:\u002F\u002Fgithub.com\u002Fbraintrustdata\u002Fbraintrust-coding-agent-plugins\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fadd-coding-agent-translator\u002FSKILL.md",[],[]]