[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M794FY24KSQV8WNM0DDC4H5M":3,"skill-same:01M794FY24KSQV8WNM0DDC4H5M":61},{"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},"01M794FY24KSQV8WNM0DDC4H5M","ros1-operations",null,"Inspect ROS 1 Noetic-or-newer graphs and perform bounded ROSA node, topic, service, parameter, package, log, launch, and node actions with discovery-first safety.","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\u002Frosa\u002Fsub-skills\u002Fros1-operations\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: ros1-operations\ndescription: \"Inspect ROS 1 Noetic-or-newer graphs and perform bounded ROSA\n  node, topic, service, parameter, package, log, launch, and node actions with\n  discovery-first safety.\"\ndisable-model-invocation: true\nmetadata:\n  disco-role: operating\nlicense: Apache 2.0\n---\n\n# ROS 1 Operations\n\nUse this sub-skill when the task concerns ROS 1\u002FNoetic-or-newer, the ROS master,\n`rosnode`, `rostopic`, `rosservice`, `rosparam`, ROS package or launch files,\nROS logs, or ROS 1 middleware errors. It describes ROSA's package-level tools;\nit is not a shell-command recipe and must not be treated as a substitute for a\nsourced ROS installation.\n\n## Scope and prerequisites\n\n- ROSA must be constructed for ROS 1 (for example, the parent agent's\n  `ROSA(ros_version=1, ...)` path). See [agent-core](..\u002Fagent-core\u002FSKILL.md)\n  for constructor, provider, executor, and runtime setup.\n- A compatible ROS 1 Python environment must provide the imported ROS modules\n  (`rosgraph`, `rospy`, `rosnode`, `rosparam`, `rospkg`, `rosservice`,\n  `rostopic`, and `rosmsg`) and a reachable ROS master for live graph work.\n  Without those prerequisites, report the middleware\u002Fimport failure; do not\n  infer that the graph is empty.\n- Start with discovery. Never invent a node, topic, service, package, launch\n  file, parameter, or log path. Use the returned names in later calls.\n- Execute exactly one ROSA tool call at a time and wait for its result before\n  selecting the next call. Do not parallelize inspection or actions.\n- Treat `rosservice_call`, `rosparam_set`, `roslaunch`, and `rosnode_kill` as\n  potentially mutating. Explain the target and expected side effect and obtain\n  confirmation before an action when the user has not already given clear\n  authorization. `roslaunch` and `rosnode_kill` are especially high risk.\n\n## Operating procedure\n\n1. Classify the request as graph inspection, bounded observation, read-only\n   metadata lookup, or mutation.\n2. For an action request, first call `rosnode_list` and `rostopic_list` with\n   their defaults unless a specific, already-known non-root namespace is the\n   task. For a service action, also call `rosservice_list`. These calls establish\n   current availability; they do not prove a ROS master exists if they return an\n   error.\n3. Select only names present in the latest result. Before `rostopic_echo`,\n   `rosservice_call`, `rosparam_set`, `roslaunch`, or `rosnode_kill`, inspect\n   the selected entity or package with the corresponding info\u002Flist tool. For\n   services, inspect service metadata and the service type before constructing\n   arguments. For a launch, enumerate package launch files first.\n4. Apply narrow pattern, namespace, and blacklist filters when an unfiltered\n   list is too large. Use `rosgraph_get` for connected publisher-topic-\n   subscriber relationships, never as a general node\u002Ftopic list API.\n5. Bound observations: keep topic echo counts in the documented 1--100 range,\n   use a finite timeout, and avoid returning large message payloads. For logs,\n   discover directories\u002Ffiles before reading a bounded recent slice.\n6. After a mutation, report the exact tool result. Re-list or re-inspect when\n   the result needs confirmation; do not claim a launch, kill, parameter write,\n   or service effect from intent alone.\n\n## API and failure details\n\n- Read [api-reference.md](references\u002Fapi-reference.md) for exact tool inputs,\n  defaults, filtering semantics, and response shapes.\n- Read [workflows.md](references\u002Fworkflows.md) for entity discovery, graph,\n  service, parameter, package, launch, log, and sequential-action workflows.\n- Read [troubleshooting.md](references\u002Ftroubleshooting.md) for missing modules\n  or master, empty graphs, namespace\u002Fregex behavior, bounded output limits,\n  service arguments, launch risks, blacklist effects, and kill confirmation.\n\n## Boundaries and related skills\n\n- This skill covers ROS 1 APIs in `rosa.tools.ros1` plus the shared ROSA\n  `read_log` behavior needed to consume discovered logs. It does not cover ROS\n  2 CLI-backed APIs; route ROS 2 requests to\n  [ros2-operations](..\u002Fros2-operations\u002FSKILL.md).\n- It does not cover generic ROSA construction, model\u002Fprovider setup, executor\n  lifecycle, or package installation; route those to\n  [agent-core](..\u002Fagent-core\u002FSKILL.md).\n- It does not teach custom tool registration, prompt customization, or general\n  blacklist injection; route those to\n  [tool-customization](..\u002Ftool-customization\u002FSKILL.md).\n- The parent router and shared prerequisites are in\n  [rosa](..\u002F..\u002FSKILL.md). No source checkout, demo script, Docker\u002FX11 setup, or\n  live ROS script is a runtime dependency of this sub-skill.\n","# ROS 1 Operations\n\nUse this sub-skill when the task concerns ROS 1\u002FNoetic-or-newer, the ROS master,\n`rosnode`, `rostopic`, `rosservice`, `rosparam`, ROS package or launch files,\nROS logs, or ROS 1 middleware errors. It describes ROSA's package-level tools;\nit is not a shell-command recipe and must not be treated as a substitute for a\nsourced ROS installation.\n\n## Scope and prerequisites\n\n- ROSA must be constructed for ROS 1 (for example, the parent agent's\n  `ROSA(ros_version=1, ...)` path). See [agent-core](..\u002Fagent-core\u002FSKILL.md)\n  for constructor, provider, executor, and runtime setup.\n- A compatible ROS 1 Python environment must provide the imported ROS modules\n  (`rosgraph`, `rospy`, `rosnode`, `rosparam`, `rospkg`, `rosservice`,\n  `rostopic`, and `rosmsg`) and a reachable ROS master for live graph work.\n  Without those prerequisites, report the middleware\u002Fimport failure; do not\n  infer that the graph is empty.\n- Start with discovery. Never invent a node, topic, service, package, launch\n  file, parameter, or log path. Use the returned names in later calls.\n- Execute exactly one ROSA tool call at a time and wait for its result before\n  selecting the next call. Do not parallelize inspection or actions.\n- Treat `rosservice_call`, `rosparam_set`, `roslaunch`, and `rosnode_kill` as\n  potentially mutating. Explain the target and expected side effect and obtain\n  confirmation before an action when the user has not already given clear\n  authorization. `roslaunch` and `rosnode_kill` are especially high risk.\n\n## Operating procedure\n\n1. Classify the request as graph inspection, bounded observation, read-only\n   metadata lookup, or mutation.\n2. For an action request, first call `rosnode_list` and `rostopic_list` with\n   their defaults unless a specific, already-known non-root namespace is the\n   task. For a service action, also call `rosservice_list`. These calls establish\n   current availability; they do not prove a ROS master exists if they return an\n   error.\n3. Select only names present in the latest result. Before `rostopic_echo`,\n   `rosservice_call`, `rosparam_set`, `roslaunch`, or `rosnode_kill`, inspect\n   the selected entity or package with the corresponding info\u002Flist tool. For\n   services, inspect service metadata and the service type before constructing\n   arguments. For a launch, enumerate package launch files first.\n4. Apply narrow pattern, namespace, and blacklist filters when an unfiltered\n   list is too large. Use `rosgraph_get` for connected publisher-topic-\n   subscriber relationships, never as a general node\u002Ftopic list API.\n5. Bound observations: keep topic echo counts in the documented 1--100 range,\n   use a finite timeout, and avoid returning large message payloads. For logs,\n   discover directories\u002Ffiles before reading a bounded recent slice.\n6. After a mutation, report the exact tool result. Re-list or re-inspect when\n   the result needs confirmation; do not claim a launch, kill, parameter write,\n   or service effect from intent alone.\n\n## API and failure details\n\n- Read [api-reference.md](references\u002Fapi-reference.md) for exact tool inputs,\n  defaults, filtering semantics, and response shapes.\n- Read [workflows.md](references\u002Fworkflows.md) for entity discovery, graph,\n  service, parameter, package, launch, log, and sequential-action workflows.\n- Read [troubleshooting.md](references\u002Ftroubleshooting.md) for missing modules\n  or master, empty graphs, namespace\u002Fregex behavior, bounded output limits,\n  service arguments, launch risks, blacklist effects, and kill confirmation.\n\n## Boundaries and related skills\n\n- This skill covers ROS 1 APIs in `rosa.tools.ros1` plus the shared ROSA\n  `read_log` behavior needed to consume discovered logs. It does not cover ROS\n  2 CLI-backed APIs; route ROS 2 requests to\n  [ros2-operations](..\u002Fros2-operations\u002FSKILL.md).\n- It does not cover generic ROSA construction, model\u002Fprovider setup, executor\n  lifecycle, or package installation; route those to\n  [agent-core](..\u002Fagent-core\u002FSKILL.md).\n- It does not teach custom tool registration, prompt customization, or general\n  blacklist injection; route those to\n  [tool-customization](..\u002Ftool-customization\u002FSKILL.md).\n- The parent router and shared prerequisites are in\n  [rosa](..\u002F..\u002FSKILL.md). No source checkout, demo script, Docker\u002FX11 setup, or\n  live ROS script is a runtime dependency of this sub-skill.\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\u002Frosa\u002Fsub-skills\u002Fros1-operations",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 ros1-operations",{"tool":40,"command":41},"bunx","bunx skills add VectorSpaceLab\u002FAREX-Skill --skill ros1-operations",{"tool":43,"command":44},"pnpm","pnpm dlx skills add VectorSpaceLab\u002FAREX-Skill --skill ros1-operations","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Frosa\u002Fsub-skills\u002Fros1-operations\u002FSKILL.md",[47,53,57],{"path":48,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":51,"sourceHtmlUrl":52},"references\u002Fapi-reference.md","REFERENCE","参考文档",14661,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Frosa\u002Fsub-skills\u002Fros1-operations\u002Freferences\u002Fapi-reference.md",{"path":54,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":55,"sourceHtmlUrl":56},"references\u002Ftroubleshooting.md",9622,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Frosa\u002Fsub-skills\u002Fros1-operations\u002Freferences\u002Ftroubleshooting.md",{"path":58,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":59,"sourceHtmlUrl":60},"references\u002Fworkflows.md",8179,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Frosa\u002Fsub-skills\u002Fros1-operations\u002Freferences\u002Fworkflows.md",[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":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":66,"categories":67,"keywords":68,"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":70,"name":71,"nameZh":6,"description":72,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":73,"categories":74,"keywords":75,"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":77,"name":78,"nameZh":6,"description":79,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":80,"categories":81,"keywords":82,"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":84,"name":85,"nameZh":6,"description":86,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":87,"categories":88,"keywords":89,"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":91,"name":92,"nameZh":6,"description":93,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":94,"categories":95,"keywords":96,"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":98,"name":99,"nameZh":6,"description":100,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":101,"categories":102,"keywords":103,"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",[],[]]