[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7921M0M69QRCEWP6H28TY5Q":3,"skill-same:01M7921M0M69QRCEWP6H28TY5Q":66},{"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":26,"commitSha":27,"skillDirectory":28,"forksCount":29,"repositoryHtmlUrl":30,"repositoryHomepageUrl":6,"ownerHtmlUrl":31,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":32,"install":33,"resources":45},"01M7921M0M69QRCEWP6H28TY5Q","openpilot",null,"Guides development, route\u002Flog analysis, car-porting, runtime services, simulator, and visual-debug workflows for comma.ai openpilot.","VectorSpaceLab\u002FAREX-Skill","VectorSpaceLab","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F180637102?v=4","01M7538C5WPSJGWF7KHR4EFZ9F","01M7538C6R2GFP53NPXTCZNBRT",351,"MIT","https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fopenpilot\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: openpilot\ndescription: \"Guides development, route\u002Flog analysis, car-porting, runtime\n  services, simulator, and visual-debug workflows for comma.ai openpilot.\"\ndisable-model-invocation: true\nmetadata:\n  disco-role: operating\nlicense: MIT\n---\n\n# openpilot Repo Skill\n\nUse this operating skill when a task involves the comma.ai **openpilot** repository, package, developer tooling, route logs, car ports, controls, runtime services, simulator, or visualization\u002Fdebug tools. openpilot is an open source driver-assistance\u002Frobotics system with Python, C\u002FC++, Cython, Cap'n Proto, SCons, uv, and several submodule packages such as opendbc and msgq.\n\nRead [references\u002Frepo-provenance.md](references\u002Frepo-provenance.md) before treating this skill as current for a checkout. Read [references\u002Ftroubleshooting.md](references\u002Ftroubleshooting.md) first when installs, imports, native extensions, submodules, or hardware assumptions fail.\n\n## First decisions\n\n1. **Is the task about editing or validating the repo?** Use [development-and-testing](sub-skills\u002Fdevelopment-and-testing\u002FSKILL.md).\n2. **Is the task about route IDs, rlogs\u002Fqlogs, message filtering, alerts, or LogReader?** Use [route-log-analysis](sub-skills\u002Froute-log-analysis\u002FSKILL.md).\n3. **Is the task about a car port, fingerprint, DBC\u002Fopendbc interface, controller behavior, process replay, or maneuver report?** Use [car-ports-and-controls](sub-skills\u002Fcar-ports-and-controls\u002FSKILL.md).\n4. **Is the task about cereal\u002Fmsgq, Params, manager processes, loggerd\u002Fuploader\u002Fdeleter, service timing, or hardware abstraction?** Use [core-services-and-runtime](sub-skills\u002Fcore-services-and-runtime\u002FSKILL.md).\n5. **Is the task about replay, Cabana, PlotJuggler\u002FJotPluggler, simulator, joystick, UI, camera streams, or CTF-style tool exploration?** Use [simulator-and-visual-tools](sub-skills\u002Fsimulator-and-visual-tools\u002FSKILL.md).\n\n## Safe baseline setup for a target checkout\n\nIn a target openpilot checkout, prefer the repository's uv\u002FSCons workflow and Python 3.12 line:\n\n```bash\n# Inspect before mutating anything\npython3 --version\ngit submodule status\n\n# Typical developer setup from a fresh checkout\nuv sync --frozen --extra tools --extra testing\nscons -u openpilot\u002Fcommon\u002Flibparams_c.so msgq_repo\u002Fmsgq\u002Fipc_pyx.so msgq_repo\u002Fmsgq\u002Fvisionipc\u002Fvisionipc_pyx.so\n```\n\nUse the bundled [scripts\u002Fopenpilot_skill_doctor.py](scripts\u002Fopenpilot_skill_doctor.py) or the development sub-skill's [scripts\u002Fopenpilot_dev_check.py](sub-skills\u002Fdevelopment-and-testing\u002Fscripts\u002Fopenpilot_dev_check.py) to inspect a checkout without running mutable setup commands.\n\n## Important constraints\n\n- openpilot metadata requires Python `>=3.12.3,\u003C3.13`.\n- Empty submodule directories are a common cause of install\u002Fimport failure. Required submodules include `msgq_repo`, `opendbc_repo`, `panda`, `rednose_repo`, `teleoprtc_repo`, and `tinygrad_repo`.\n- Many imports need native outputs from SCons, especially `openpilot\u002Fcommon\u002Flibparams_c.so`, `msgq_repo\u002Fmsgq\u002Fipc_pyx.so`, and `msgq_repo\u002Fmsgq\u002Fvisionipc\u002Fvisionipc_pyx.so`.\n- A CPU developer host can validate package imports, route\u002Flog parsing, unit-test collection, car docs, and many controller tests. It cannot validate in-car safety, Panda USB, AGNOS, camera\u002Fencoder power, GUI, simulator, or authenticated remote-route behavior by itself.\n- Treat live car\u002Fdevice commands, joystick control, `op switch`, updater\u002Fstart\u002Fstop flows, and Params writes as state-mutating. Do not run them unless the user explicitly asks and prerequisites are clear.\n\n## Sub-skill map\n\n| Need | Read |\n| --- | --- |\n| Setup, build, lint, tests, docs, CI-like checks | [development-and-testing\u002FSKILL.md](sub-skills\u002Fdevelopment-and-testing\u002FSKILL.md) |\n| Route\u002Fsegment formats, LogReader, qlog\u002Frlog summaries, filtering | [route-log-analysis\u002FSKILL.md](sub-skills\u002Froute-log-analysis\u002FSKILL.md) |\n| Car porting, fingerprints, controls, process replay, maneuvers | [car-ports-and-controls\u002FSKILL.md](sub-skills\u002Fcar-ports-and-controls\u002FSKILL.md) |\n| cereal\u002Fmsgq, Params, manager, loggerd, service diagnostics | [core-services-and-runtime\u002FSKILL.md](sub-skills\u002Fcore-services-and-runtime\u002FSKILL.md) |\n| Replay, Cabana, PlotJuggler, simulator, joystick, UI flags | [simulator-and-visual-tools\u002FSKILL.md](sub-skills\u002Fsimulator-and-visual-tools\u002FSKILL.md) |\n\n## Repo-level references and scripts\n\n- [references\u002Frepo-provenance.md](references\u002Frepo-provenance.md) records the source snapshot and refresh baseline.\n- [references\u002Frepo-routing-metadata.json](references\u002Frepo-routing-metadata.json) is structured router metadata for managed imports.\n- [references\u002Ftroubleshooting.md](references\u002Ftroubleshooting.md) covers cross-cutting failures and escalation rules.\n- [scripts\u002Fopenpilot_skill_doctor.py](scripts\u002Fopenpilot_skill_doctor.py) checks a target checkout's structure and import\u002Fbuild prerequisites without mutating it.\n\n## Verification posture\n\nCPU import\u002Fbuild preparation was verified for the selected developer workflows. Hardware, remote-route network, GUI, and simulator capabilities are documented as optional or unverified unless the user provides the required device, route access, display, or dependency stack.\n","# openpilot Repo Skill\n\nUse this operating skill when a task involves the comma.ai **openpilot** repository, package, developer tooling, route logs, car ports, controls, runtime services, simulator, or visualization\u002Fdebug tools. openpilot is an open source driver-assistance\u002Frobotics system with Python, C\u002FC++, Cython, Cap'n Proto, SCons, uv, and several submodule packages such as opendbc and msgq.\n\nRead [references\u002Frepo-provenance.md](references\u002Frepo-provenance.md) before treating this skill as current for a checkout. Read [references\u002Ftroubleshooting.md](references\u002Ftroubleshooting.md) first when installs, imports, native extensions, submodules, or hardware assumptions fail.\n\n## First decisions\n\n1. **Is the task about editing or validating the repo?** Use [development-and-testing](sub-skills\u002Fdevelopment-and-testing\u002FSKILL.md).\n2. **Is the task about route IDs, rlogs\u002Fqlogs, message filtering, alerts, or LogReader?** Use [route-log-analysis](sub-skills\u002Froute-log-analysis\u002FSKILL.md).\n3. **Is the task about a car port, fingerprint, DBC\u002Fopendbc interface, controller behavior, process replay, or maneuver report?** Use [car-ports-and-controls](sub-skills\u002Fcar-ports-and-controls\u002FSKILL.md).\n4. **Is the task about cereal\u002Fmsgq, Params, manager processes, loggerd\u002Fuploader\u002Fdeleter, service timing, or hardware abstraction?** Use [core-services-and-runtime](sub-skills\u002Fcore-services-and-runtime\u002FSKILL.md).\n5. **Is the task about replay, Cabana, PlotJuggler\u002FJotPluggler, simulator, joystick, UI, camera streams, or CTF-style tool exploration?** Use [simulator-and-visual-tools](sub-skills\u002Fsimulator-and-visual-tools\u002FSKILL.md).\n\n## Safe baseline setup for a target checkout\n\nIn a target openpilot checkout, prefer the repository's uv\u002FSCons workflow and Python 3.12 line:\n\n```bash\n# Inspect before mutating anything\npython3 --version\ngit submodule status\n\n# Typical developer setup from a fresh checkout\nuv sync --frozen --extra tools --extra testing\nscons -u openpilot\u002Fcommon\u002Flibparams_c.so msgq_repo\u002Fmsgq\u002Fipc_pyx.so msgq_repo\u002Fmsgq\u002Fvisionipc\u002Fvisionipc_pyx.so\n```\n\nUse the bundled [scripts\u002Fopenpilot_skill_doctor.py](scripts\u002Fopenpilot_skill_doctor.py) or the development sub-skill's [scripts\u002Fopenpilot_dev_check.py](sub-skills\u002Fdevelopment-and-testing\u002Fscripts\u002Fopenpilot_dev_check.py) to inspect a checkout without running mutable setup commands.\n\n## Important constraints\n\n- openpilot metadata requires Python `>=3.12.3,\u003C3.13`.\n- Empty submodule directories are a common cause of install\u002Fimport failure. Required submodules include `msgq_repo`, `opendbc_repo`, `panda`, `rednose_repo`, `teleoprtc_repo`, and `tinygrad_repo`.\n- Many imports need native outputs from SCons, especially `openpilot\u002Fcommon\u002Flibparams_c.so`, `msgq_repo\u002Fmsgq\u002Fipc_pyx.so`, and `msgq_repo\u002Fmsgq\u002Fvisionipc\u002Fvisionipc_pyx.so`.\n- A CPU developer host can validate package imports, route\u002Flog parsing, unit-test collection, car docs, and many controller tests. It cannot validate in-car safety, Panda USB, AGNOS, camera\u002Fencoder power, GUI, simulator, or authenticated remote-route behavior by itself.\n- Treat live car\u002Fdevice commands, joystick control, `op switch`, updater\u002Fstart\u002Fstop flows, and Params writes as state-mutating. Do not run them unless the user explicitly asks and prerequisites are clear.\n\n## Sub-skill map\n\n| Need | Read |\n| --- | --- |\n| Setup, build, lint, tests, docs, CI-like checks | [development-and-testing\u002FSKILL.md](sub-skills\u002Fdevelopment-and-testing\u002FSKILL.md) |\n| Route\u002Fsegment formats, LogReader, qlog\u002Frlog summaries, filtering | [route-log-analysis\u002FSKILL.md](sub-skills\u002Froute-log-analysis\u002FSKILL.md) |\n| Car porting, fingerprints, controls, process replay, maneuvers | [car-ports-and-controls\u002FSKILL.md](sub-skills\u002Fcar-ports-and-controls\u002FSKILL.md) |\n| cereal\u002Fmsgq, Params, manager, loggerd, service diagnostics | [core-services-and-runtime\u002FSKILL.md](sub-skills\u002Fcore-services-and-runtime\u002FSKILL.md) |\n| Replay, Cabana, PlotJuggler, simulator, joystick, UI flags | [simulator-and-visual-tools\u002FSKILL.md](sub-skills\u002Fsimulator-and-visual-tools\u002FSKILL.md) |\n\n## Repo-level references and scripts\n\n- [references\u002Frepo-provenance.md](references\u002Frepo-provenance.md) records the source snapshot and refresh baseline.\n- [references\u002Frepo-routing-metadata.json](references\u002Frepo-routing-metadata.json) is structured router metadata for managed imports.\n- [references\u002Ftroubleshooting.md](references\u002Ftroubleshooting.md) covers cross-cutting failures and escalation rules.\n- [scripts\u002Fopenpilot_skill_doctor.py](scripts\u002Fopenpilot_skill_doctor.py) checks a target checkout's structure and import\u002Fbuild prerequisites without mutating it.\n\n## Verification posture\n\nCPU import\u002Fbuild preparation was verified for the selected developer workflows. Hardware, remote-route network, GUI, and simulator capabilities are documented as optional or unverified unless the user provides the required device, route access, display, or dependency stack.\n",{"name":5,"license":14,"metadata":23,"description":7,"disable-model-invocation":25},{"disco-role":24},"operating",true,"main","ac3fe1afa80fb9a09775ecfb2b6cc3ba850a2db6","skills\u002Frepositories\u002Frepo-skills\u002Fopenpilot",27,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill","https:\u002F\u002Fgithub.com\u002FVectorSpaceLab","2026-09-03 10:25:21",{"source":8,"skillName":5,"commands":34,"prompt":44,"zipAvailable":25},[35,38,41],{"tool":36,"command":37},"npx","npx skills add VectorSpaceLab\u002FAREX-Skill --skill openpilot",{"tool":39,"command":40},"bunx","bunx skills add VectorSpaceLab\u002FAREX-Skill --skill openpilot",{"tool":42,"command":43},"pnpm","pnpm dlx skills add VectorSpaceLab\u002FAREX-Skill --skill openpilot","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fopenpilot\u002FSKILL.md",[46,52,56,60],{"path":47,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":50,"sourceHtmlUrl":51},"references\u002Frepo-provenance.md","REFERENCE","参考文档",2513,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fopenpilot\u002Freferences\u002Frepo-provenance.md",{"path":53,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":54,"sourceHtmlUrl":55},"references\u002Frepo-routing-metadata.json",519,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fopenpilot\u002Freferences\u002Frepo-routing-metadata.json",{"path":57,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":58,"sourceHtmlUrl":59},"references\u002Ftroubleshooting.md",3718,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fopenpilot\u002Freferences\u002Ftroubleshooting.md",{"path":61,"resourceType":62,"resourceTypeDesc":63,"sizeBytes":64,"sourceHtmlUrl":65},"scripts\u002Fopenpilot_skill_doctor.py","SCRIPT","脚本",3155,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fopenpilot\u002Fscripts\u002Fopenpilot_skill_doctor.py",[67,75,82,89,96,103],{"skillNo":68,"name":69,"nameZh":6,"description":70,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":71,"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.","Apache-2.0","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":71,"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":71,"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":71,"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":71,"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":71,"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",[],[]]