[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M78XZ4YGCWC4ZGY3D73PJDBA":3,"skill-same:01M78XZ4YGCWC4ZGY3D73PJDBA":67},{"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":27,"commitSha":28,"skillDirectory":29,"forksCount":30,"repositoryHtmlUrl":31,"repositoryHomepageUrl":6,"ownerHtmlUrl":32,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":33,"install":34,"resources":46},"01M78XZ4YGCWC4ZGY3D73PJDBA","proxy-wrap",null,"Run the Headroom proxy, route LLM providers through it, and wrap or unwrap coding agents safely.","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\u002Fheadroom\u002Fsub-skills\u002Fproxy-wrap\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: proxy-wrap\ndescription: \"Run the Headroom proxy, route LLM providers through it, and wrap\n  or unwrap coding agents safely.\"\ndisable-model-invocation: true\nmetadata:\n  disco-role: operating\nlicense: Apache 2.0\n---\n\n# Headroom proxy and agent wrapping\n\nUse this sub-skill when the user needs a live Headroom proxy, provider routing, agent wrapping, or troubleshooting for requests that should pass through Headroom before reaching an LLM provider.\n\n## Route here for\n\n- `headroom proxy` foreground server flags, optimization modes, local endpoints, dashboard, health, metrics, and provider backends.\n- `headroom wrap ...` and `headroom unwrap ...` for Claude, Codex, Copilot, VS Code, Aider, OpenClaude, Vibe, Kimi, Grok, Cursor, Grok Build, Cline, Continue, Goose, OpenHands, OpenClaw, OpenCode, OMP, and ZCode.\n- Provider-specific base URL, auth, and model routing issues for Anthropic, OpenAI-compatible clients, Codex\u002FChatGPT backend, GitHub Copilot, Bedrock, Vertex, any-LLM, LiteLLM, and plugin integrations.\n- OpenClaw\u002FOpenCode plugin setup and proxy auto-detection.\n- Proxy cache-safety, WebSocket\u002FSSE behavior, and Prometheus metrics interpretation.\n\n## Route elsewhere\n\n- Durable deployment lifecycle with `headroom deploy` or `headroom install`: use `..\u002Fops\u002FSKILL.md`.\n- `headroom mcp`, `headroom memory`, `headroom learn`, and CCR tool registration: use `..\u002Fmemory\u002FSKILL.md`.\n- Direct `compress()` or TypeScript SDK application integration that does not need wrapping: use `..\u002Fsdk\u002FSKILL.md`.\n\n## Fast start\n\nForeground proxy:\n\n```bash\nheadroom proxy --host 127.0.0.1 --port 8787\n```\n\nClaude Code through a local proxy:\n\n```bash\nANTHROPIC_BASE_URL=http:\u002F\u002F127.0.0.1:8787 claude\n# or durable wrapper:\nheadroom wrap claude\n```\n\nOpenAI-compatible client through a local proxy:\n\n```bash\nexport OPENAI_BASE_URL=http:\u002F\u002F127.0.0.1:8787\u002Fv1\n```\n\nCheck a running proxy without sending model traffic:\n\n```bash\npython scripts\u002Fproxy_livez_check.py --url http:\u002F\u002F127.0.0.1:8787 --json\n```\n\n## References and helper\n\n- `references\u002Fproxy-reference.md` covers proxy flags, modes, endpoints, telemetry, and backend routing concepts.\n- `references\u002Fagent-routing.md` maps agent wrappers and provider-specific routing signals.\n- `references\u002Ftroubleshooting.md` covers common proxy, base URL, auth, cloud, plugin, and cache-safety failures.\n- `scripts\u002Fproxy_livez_check.py` is a safe loopback health checker for `\u002Flivez`, `\u002Fhealth`, and optional `\u002Fstats`.\n\n## Safety rules\n\n- Do not run long-lived proxies or durable wrappers unless the user wants that side effect; for diagnosis, use read-only health probes first.\n- Do not bind the proxy to non-loopback hosts without explicit user intent and network\u002Fsecurity context.\n- Do not put API keys, OAuth tokens, cloud credentials, or bearer tokens in shell examples.\n- Cloud backends such as Bedrock and Vertex require valid credentials and permissions; local help and synthetic tests do not prove live cloud access.\n","# Headroom proxy and agent wrapping\n\nUse this sub-skill when the user needs a live Headroom proxy, provider routing, agent wrapping, or troubleshooting for requests that should pass through Headroom before reaching an LLM provider.\n\n## Route here for\n\n- `headroom proxy` foreground server flags, optimization modes, local endpoints, dashboard, health, metrics, and provider backends.\n- `headroom wrap ...` and `headroom unwrap ...` for Claude, Codex, Copilot, VS Code, Aider, OpenClaude, Vibe, Kimi, Grok, Cursor, Grok Build, Cline, Continue, Goose, OpenHands, OpenClaw, OpenCode, OMP, and ZCode.\n- Provider-specific base URL, auth, and model routing issues for Anthropic, OpenAI-compatible clients, Codex\u002FChatGPT backend, GitHub Copilot, Bedrock, Vertex, any-LLM, LiteLLM, and plugin integrations.\n- OpenClaw\u002FOpenCode plugin setup and proxy auto-detection.\n- Proxy cache-safety, WebSocket\u002FSSE behavior, and Prometheus metrics interpretation.\n\n## Route elsewhere\n\n- Durable deployment lifecycle with `headroom deploy` or `headroom install`: use `..\u002Fops\u002FSKILL.md`.\n- `headroom mcp`, `headroom memory`, `headroom learn`, and CCR tool registration: use `..\u002Fmemory\u002FSKILL.md`.\n- Direct `compress()` or TypeScript SDK application integration that does not need wrapping: use `..\u002Fsdk\u002FSKILL.md`.\n\n## Fast start\n\nForeground proxy:\n\n```bash\nheadroom proxy --host 127.0.0.1 --port 8787\n```\n\nClaude Code through a local proxy:\n\n```bash\nANTHROPIC_BASE_URL=http:\u002F\u002F127.0.0.1:8787 claude\n# or durable wrapper:\nheadroom wrap claude\n```\n\nOpenAI-compatible client through a local proxy:\n\n```bash\nexport OPENAI_BASE_URL=http:\u002F\u002F127.0.0.1:8787\u002Fv1\n```\n\nCheck a running proxy without sending model traffic:\n\n```bash\npython scripts\u002Fproxy_livez_check.py --url http:\u002F\u002F127.0.0.1:8787 --json\n```\n\n## References and helper\n\n- `references\u002Fproxy-reference.md` covers proxy flags, modes, endpoints, telemetry, and backend routing concepts.\n- `references\u002Fagent-routing.md` maps agent wrappers and provider-specific routing signals.\n- `references\u002Ftroubleshooting.md` covers common proxy, base URL, auth, cloud, plugin, and cache-safety failures.\n- `scripts\u002Fproxy_livez_check.py` is a safe loopback health checker for `\u002Flivez`, `\u002Fhealth`, and optional `\u002Fstats`.\n\n## Safety rules\n\n- Do not run long-lived proxies or durable wrappers unless the user wants that side effect; for diagnosis, use read-only health probes first.\n- Do not bind the proxy to non-loopback hosts without explicit user intent and network\u002Fsecurity context.\n- Do not put API keys, OAuth tokens, cloud credentials, or bearer tokens in shell examples.\n- Cloud backends such as Bedrock and Vertex require valid credentials and permissions; local help and synthetic tests do not prove live cloud access.\n",{"name":5,"license":23,"metadata":24,"description":7,"disable-model-invocation":26},"Apache 2.0",{"disco-role":25},"operating",true,"main","ac3fe1afa80fb9a09775ecfb2b6cc3ba850a2db6","skills\u002Frepositories\u002Frepo-skills\u002Fheadroom\u002Fsub-skills\u002Fproxy-wrap",27,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill","https:\u002F\u002Fgithub.com\u002FVectorSpaceLab","2026-09-03 10:25:21",{"source":8,"skillName":5,"commands":35,"prompt":45,"zipAvailable":26},[36,39,42],{"tool":37,"command":38},"npx","npx skills add VectorSpaceLab\u002FAREX-Skill --skill proxy-wrap",{"tool":40,"command":41},"bunx","bunx skills add VectorSpaceLab\u002FAREX-Skill --skill proxy-wrap",{"tool":43,"command":44},"pnpm","pnpm dlx skills add VectorSpaceLab\u002FAREX-Skill --skill proxy-wrap","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fheadroom\u002Fsub-skills\u002Fproxy-wrap\u002FSKILL.md",[47,53,57,61],{"path":48,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":51,"sourceHtmlUrl":52},"references\u002Fagent-routing.md","REFERENCE","参考文档",2542,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fheadroom\u002Fsub-skills\u002Fproxy-wrap\u002Freferences\u002Fagent-routing.md",{"path":54,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":55,"sourceHtmlUrl":56},"references\u002Fproxy-reference.md",3000,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fheadroom\u002Fsub-skills\u002Fproxy-wrap\u002Freferences\u002Fproxy-reference.md",{"path":58,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":59,"sourceHtmlUrl":60},"references\u002Ftroubleshooting.md",3674,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fheadroom\u002Fsub-skills\u002Fproxy-wrap\u002Freferences\u002Ftroubleshooting.md",{"path":62,"resourceType":63,"resourceTypeDesc":64,"sizeBytes":65,"sourceHtmlUrl":66},"scripts\u002Fproxy_livez_check.py","SCRIPT","脚本",3355,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fheadroom\u002Fsub-skills\u002Fproxy-wrap\u002Fscripts\u002Fproxy_livez_check.py",[68,75,82,89,96,103],{"skillNo":69,"name":70,"nameZh":6,"description":71,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":72,"categories":73,"keywords":74,"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":76,"name":77,"nameZh":6,"description":78,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":79,"categories":80,"keywords":81,"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":83,"name":84,"nameZh":6,"description":85,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":86,"categories":87,"keywords":88,"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":90,"name":91,"nameZh":6,"description":92,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":93,"categories":94,"keywords":95,"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":97,"name":98,"nameZh":6,"description":99,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":100,"categories":101,"keywords":102,"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":104,"name":105,"nameZh":6,"description":106,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":107,"categories":108,"keywords":109,"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",[],[]]