[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M78XMMWKCVFPQPQDR91VGRW5":3,"skill-same:01M78XMMWKCVFPQPQDR91VGRW5":63},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"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":33,"commitSha":34,"skillDirectory":35,"forksCount":36,"repositoryHtmlUrl":37,"repositoryHomepageUrl":6,"ownerHtmlUrl":38,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":39,"install":40,"resources":52},"01M78XMMWKCVFPQPQDR91VGRW5","scaffold",null,"Use this sub-skill when creating or enhancing an ADK project with agents-cli scaffold create, scaffold enhance, or scaffold upgrade, including template, deployment target, CI\u002FCD, session storage, and prototype-first decisions.","VectorSpaceLab\u002FAREX-Skill","VectorSpaceLab","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F180637102?v=4","01M7538C5WPSJGWF7KHR4EFZ9F","01M7538C6R2GFP53NPXTCZNBRT",351,"Apache-2.0","https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fgoogle-agents-cli\u002Fsub-skills\u002Fscaffold\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: scaffold\ndescription: \"Use this sub-skill when creating or enhancing an ADK project with\n  agents-cli scaffold create, scaffold enhance, or scaffold upgrade, including\n  template, deployment target, CI\u002FCD, session storage, and prototype-first\n  decisions.\"\nmetadata:\n  disco-role: operating\n  author: Google\n  license: Apache-2.0\n  version: 1.3.1\n  requires:\n    bins:\n      - agents-cli\n    install: \"uv tool install google-agents-cli\"\ndisable-model-invocation: true\nlicense: Apache 2.0\n---\n\n# Project Scaffolding\n\nUse this sub-skill inside the `google-agents-cli` repo skill. It is a router plus operating checklist; move into the bundled references for full command flags, schemas, and examples.\n\n## When to Use\n\n- The user wants to create a new project, enhance an existing project, or upgrade generated files.\n- The task asks about `agents-cli create`, `agents-cli scaffold create`, `enhance`, or `upgrade`.\n- You need to map prototype\u002Fdeployment\u002Fsession\u002FCI-CD choices to CLI flags.\n\n## Workflow\n\n1. Confirm project name\u002Fpath and whether prototype-first is desired.\n2. Map target architecture to `--deployment-target`, `--session-type`, and `--cicd-runner` flags.\n3. Run `scaffold create` only for a new directory; use `scaffold enhance` for an existing project.\n4. After scaffolding, load workflow\u002Fadk-code\u002Feval for implementation and validation.\n\n## Read These References\n\n- `references\u002Fscaffold-guide.md` — read for scaffold guide details.\n- `references\u002Fflags.md` — read for flags details.\n\n## Verification and Safety\n\nSafe checks: `agents-cli scaffold --help`; project creation\u002Fenhance mutates files and needs confirmation.\n\n## Boundaries\n\n- Does not write custom ADK business logic; use adk-code after project creation.\n- Does not deploy live resources; use deploy after scaffold files exist.\n\n## Related Sub-Skills\n\n- `..\u002Fworkflow\u002FSKILL.md` — lifecycle routing and approval gates.\n- `..\u002Fscaffold\u002FSKILL.md` — project creation\u002Fenhancement.\n- `..\u002Fadk-code\u002FSKILL.md` — ADK Python implementation patterns.\n- `..\u002Feval\u002FSKILL.md` — evaluation loops and metrics.\n- `..\u002Fdeploy\u002FSKILL.md` — deployment and infrastructure.\n- `..\u002Fpublish\u002FSKILL.md` — Gemini Enterprise registration.\n- `..\u002Fobservability\u002FSKILL.md` — logging, tracing, and analytics.\n","# Project Scaffolding\n\nUse this sub-skill inside the `google-agents-cli` repo skill. It is a router plus operating checklist; move into the bundled references for full command flags, schemas, and examples.\n\n## When to Use\n\n- The user wants to create a new project, enhance an existing project, or upgrade generated files.\n- The task asks about `agents-cli create`, `agents-cli scaffold create`, `enhance`, or `upgrade`.\n- You need to map prototype\u002Fdeployment\u002Fsession\u002FCI-CD choices to CLI flags.\n\n## Workflow\n\n1. Confirm project name\u002Fpath and whether prototype-first is desired.\n2. Map target architecture to `--deployment-target`, `--session-type`, and `--cicd-runner` flags.\n3. Run `scaffold create` only for a new directory; use `scaffold enhance` for an existing project.\n4. After scaffolding, load workflow\u002Fadk-code\u002Feval for implementation and validation.\n\n## Read These References\n\n- `references\u002Fscaffold-guide.md` — read for scaffold guide details.\n- `references\u002Fflags.md` — read for flags details.\n\n## Verification and Safety\n\nSafe checks: `agents-cli scaffold --help`; project creation\u002Fenhance mutates files and needs confirmation.\n\n## Boundaries\n\n- Does not write custom ADK business logic; use adk-code after project creation.\n- Does not deploy live resources; use deploy after scaffold files exist.\n\n## Related Sub-Skills\n\n- `..\u002Fworkflow\u002FSKILL.md` — lifecycle routing and approval gates.\n- `..\u002Fscaffold\u002FSKILL.md` — project creation\u002Fenhancement.\n- `..\u002Fadk-code\u002FSKILL.md` — ADK Python implementation patterns.\n- `..\u002Feval\u002FSKILL.md` — evaluation loops and metrics.\n- `..\u002Fdeploy\u002FSKILL.md` — deployment and infrastructure.\n- `..\u002Fpublish\u002FSKILL.md` — Gemini Enterprise registration.\n- `..\u002Fobservability\u002FSKILL.md` — logging, tracing, and analytics.\n",{"name":5,"license":23,"metadata":24,"description":7,"disable-model-invocation":32},"Apache 2.0",{"author":25,"license":14,"version":26,"requires":27,"disco-role":31},"Google","1.3.1",{"bins":28,"install":30},[29],"agents-cli","uv tool install google-agents-cli","operating",true,"main","ac3fe1afa80fb9a09775ecfb2b6cc3ba850a2db6","skills\u002Frepositories\u002Frepo-skills\u002Fgoogle-agents-cli\u002Fsub-skills\u002Fscaffold",27,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill","https:\u002F\u002Fgithub.com\u002FVectorSpaceLab","2026-09-03 10:25:21",{"source":8,"skillName":5,"commands":41,"prompt":51,"zipAvailable":32},[42,45,48],{"tool":43,"command":44},"npx","npx skills add VectorSpaceLab\u002FAREX-Skill --skill scaffold",{"tool":46,"command":47},"bunx","bunx skills add VectorSpaceLab\u002FAREX-Skill --skill scaffold",{"tool":49,"command":50},"pnpm","pnpm dlx skills add VectorSpaceLab\u002FAREX-Skill --skill scaffold","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fgoogle-agents-cli\u002Fsub-skills\u002Fscaffold\u002FSKILL.md",[53,59],{"path":54,"resourceType":55,"resourceTypeDesc":56,"sizeBytes":57,"sourceHtmlUrl":58},"references\u002Fflags.md","REFERENCE","参考文档",3289,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fgoogle-agents-cli\u002Fsub-skills\u002Fscaffold\u002Freferences\u002Fflags.md",{"path":60,"resourceType":55,"resourceTypeDesc":56,"sizeBytes":61,"sourceHtmlUrl":62},"references\u002Fscaffold-guide.md",10599,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fgoogle-agents-cli\u002Fsub-skills\u002Fscaffold\u002Freferences\u002Fscaffold-guide.md",[64,71,78,85,92,99],{"skillNo":65,"name":66,"nameZh":6,"description":67,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":68,"categories":69,"keywords":70,"publishedAt":18},"01M799NYSH1R3RVAHSM2D88Y84","passnet-triton-opt","Make a single PassNet Triton kernel fast AND numerically faithful: performance model (when a replacement can win at all), block\u002Fgrid\u002Fwarp tuning, autotune policy, launch overhead, and per-op numeric recipes to pass the dtype baseline tolerances. Use when a pass matches and is correct but speedup below expected, or when correctness fails by small numeric margins.","https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Ftask-oriented\u002FPassNet\u002Fskills\u002Fpassnet-triton-opt\u002FSKILL.md",[],[],{"skillNo":72,"name":73,"nameZh":6,"description":74,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":75,"categories":76,"keywords":77,"publishedAt":18},"01M799NS5APEC0N1FZ7XZVW6BN","passnet-solve","END-TO-END playbook for solving one PassNet sample: analyze the computation graphs, decide the optimization strategy (what to fuse, what to replace, what to leave alone), drive the iteration loop, and maximize the sample score. This is the ENTRY skill — invoke it first for any PassNet optimization task; it tells you when to use passnet-pattern-fusion, passnet-triton-opt and passnet-feedback.","https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Ftask-oriented\u002FPassNet\u002Fskills\u002Fpassnet-solve\u002FSKILL.md",[],[],{"skillNo":79,"name":80,"nameZh":6,"description":81,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":82,"categories":83,"keywords":84,"publishedAt":18},"01M799NNY9BKSM21V5R7QVTBJX","passnet-skill","PassNet GPU kernel optimization via compiler passes. Design and implement Triton-based optimization passes, create pass files under .\u002Fpass_dir\u002F, self-evaluate with pass_evaluator, and iterate to maximize GPU speedup.","https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Ftask-oriented\u002FPassNet\u002Fskills\u002Fpassnet-skill\u002FSKILL.md",[],[],{"skillNo":86,"name":87,"nameZh":6,"description":88,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":89,"categories":90,"keywords":91,"publishedAt":18},"01M799NHH6NP7Z1RK77KGXAN6S","passnet-pattern-fusion","Author PassNet pass files: write patterns that actually MATCH the FX graph, pick fusion regions (which ops to absorb into one Triton kernel), and structure multi-pass submissions with the mandatory shared-dispatch architecture. Use when creating or fixing pattern()\u002Freplacement_args()\u002Freplacement_func() files, when a pass \"failed to match\", or when deciding how to fuse multiple kernels\u002Fops.","https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Ftask-oriented\u002FPassNet\u002Fskills\u002Fpassnet-pattern-fusion\u002FSKILL.md",[],[],{"skillNo":93,"name":94,"nameZh":6,"description":95,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":96,"categories":97,"keywords":98,"publishedAt":18},"01M799ND2J4WNC2PGAZ0A06NDF","passnet-orchestrate","Round\u002Fbatch planning and decision support for PassNet graph optimization. Use for multi-sample triage, worker allocation, eval-budget policy, and post-eval keep\u002Frevert decisions. For solving one concrete sample end to end, use passnet-solve as the entry skill; consult this skill only when you need broader planning or a specific decision gate.","https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Ftask-oriented\u002FPassNet\u002Fskills\u002Fpassnet-orchestrate\u002FSKILL.md",[],[],{"skillNo":100,"name":101,"nameZh":6,"description":102,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":103,"categories":104,"keywords":105,"publishedAt":18},"01M799N8SBTMY02ZDG2AZF5ZWE","passnet-feedback","Fast, deterministic feedback for PassNet work: pre-flight pattern\u002Fmatch verification WITHOUT burning a GPU evaluation, per-node bottleneck analysis of a sample's graphs, and eval-log parsing into per-variant status + estimated score + failure classification. Use BEFORE every GPU evaluation (check_pattern), at the START of a sample (analyze_graph), and AFTER every evaluation (parse_eval_log).","https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Ftask-oriented\u002FPassNet\u002Fskills\u002Fpassnet-feedback\u002FSKILL.md",[],[]]