[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M78XT4MAP5848D4WWWYA73TG":3,"skill-same:01M78XT4MAP5848D4WWWYA73TG":74},{"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},"01M78XT4MAP5848D4WWWYA73TG","gym-pybullet-drones",null,"Use gym-pybullet-drones for PyBullet quadrotor simulation, PID\u002FMRAC control examples, Gymnasium PPO hover workflows, and Betaflight SITL preflight guidance.","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\u002Fgym-pybullet-drones\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: gym-pybullet-drones\ndescription: \"Use gym-pybullet-drones for PyBullet quadrotor simulation,\n  PID\u002FMRAC control examples, Gymnasium PPO hover workflows, and Betaflight SITL\n  preflight guidance.\"\ndisable-model-invocation: true\nmetadata:\n  disco-role: operating\nlicense: MIT\n---\n\n# gym-pybullet-drones\n\nUse this repo skill when a task mentions `gym-pybullet-drones`, PyBullet drone or Crazyflie simulation, Aviary environments, PID\u002Fvelocity\u002Fdownwash\u002FMRAC control, Gymnasium hover environments, PPO training\u002Fplayback, or Betaflight SITL integration.\n\nThis skill is self-contained operating guidance for package version `2.2.0`. The original repository examples, tests, and assets were used as evidence, but future agents should use the bundled references and scripts in this skill rather than reopening or executing files from the source checkout.\n\n## Start here\n\n1. Confirm the package is installed in the active Python environment. The repository metadata targets Python `3.12`.\n2. Run the bundled import check if installation or Gymnasium registration is uncertain:\n\n   ```bash\n   python scripts\u002Fcheck_imports.py\n   python scripts\u002Fcheck_imports.py --headless-smoke --env-id hover-aviary-v0\n   ```\n\n3. Pick the route below and read the nearest sub-skill before running workflow-specific helpers.\n4. Keep `gui=False` \u002F headless mode for automation, CI, containers, or remote servers. Enable GUI, plotting, recording, and full-duration training only after the relevant sub-skill's troubleshooting page says the host can support them.\n\n## Installation and import baseline\n\nFor a published install or a local checkout, use a clean Python 3.12 environment and install only the package\u002Fruntime dependencies needed for the selected workflow:\n\n```bash\npython -m pip install gym-pybullet-drones\n# or, for a local checkout you are maintaining:\npython -m pip install -e \u002Fpath\u002Fto\u002Fgym-pybullet-drones\npython -m pip check\n```\n\nMinimal package import check:\n\n```python\nimport gym_pybullet_drones  # registers Gymnasium env IDs\nfrom gym_pybullet_drones.envs import CtrlAviary, VelocityAviary, HoverAviary, MultiHoverAviary\nfrom gym_pybullet_drones.utils.enums import DroneModel, Physics, ObservationType, ActionType\n```\n\nThe package has no console-script entry points. Use Python imports or the bundled helper scripts below.\n\n## Route map\n\n| Task signal | Read \u002F run |\n| --- | --- |\n| PID trajectory tracking, `CtrlAviary`, `VelocityAviary`, velocity commands, downwash physics, MRAC, `Logger`, headless control examples | [control-simulation](sub-skills\u002Fcontrol-simulation\u002FSKILL.md); helper: `python sub-skills\u002Fcontrol-simulation\u002Fscripts\u002Frun_control_example.py --list` |\n| PPO training, short RL smoke tests, `HoverAviary`, `MultiHoverAviary`, `hover-aviary-v0`, `multihover-aviary-v0`, SB3 model save\u002Fload\u002Fplayback | [rl-workflows](sub-skills\u002Frl-workflows\u002FSKILL.md); helper: `python sub-skills\u002Frl-workflows\u002Fscripts\u002Frun_rl_workflow.py --help` |\n| Betaflight SITL, `BetaAviary`, external `betaflight_sitl\u002FbfN` layout, UDP port mapping, `clone_bfs.sh` consequences | [betaflight-sitl](sub-skills\u002Fbetaflight-sitl\u002FSKILL.md); helper: `python sub-skills\u002Fbetaflight-sitl\u002Fscripts\u002Fcheck_betaflight_layout.py --help` |\n| Package layout, registered env IDs, shared enums, dependency\u002Fbackend notes, logger conventions | [package overview](references\u002Fpackage-overview.md) |\n| Install\u002Fimport, GUI\u002FOpenGL, Gymnasium registration, video conversion, and cross-workflow failures | [troubleshooting](references\u002Ftroubleshooting.md) |\n| Staleness or refresh decision for another checkout | [repo provenance](references\u002Frepo-provenance.md) |\n\n## Quick chooser\n\n- If the user says \"run the PID example\", \"velocity control\", \"downwash\", or \"MRAC\", start with `control-simulation`.\n- If the user says \"train a hover policy\", \"play a saved PPO model\", or mentions `hover-aviary-v0` \u002F `multihover-aviary-v0`, start with `rl-workflows`.\n- If the user says \"Betaflight SITL\", \"BetaAviary\", or \"check the external drone layout\", start with `betaflight-sitl`.\n- If the user only needs to know whether the package is installed and registered correctly, run `scripts\u002Fcheck_imports.py` first.\n\n## Operating guardrails\n\n- Required backend for this skill is CPU \u002F generic Python. CUDA is not required for any selected repo-native workflow, even though Torch may use accelerator hardware if the user's environment provides it.\n- PyBullet GUI is optional and host-dependent. Prefer `gui=False` for all smoke checks and automated verification.\n- `BaseAviary` requires `pyb_freq % ctrl_freq == 0`; use the bundled runners to catch timing mistakes before PyBullet construction.\n- Control observations use a 20-value state vector; `Logger.log(...)` expects one 20-value state and one 12-value control vector per drone.\n- RL smoke training proves environment\u002Frollout\u002Fsave\u002Fload mechanics, not policy quality. Full PPO training is intentionally not the default.\n- Betaflight SITL is an external integration: the package expects prebuilt Betaflight SITL binaries in a local `betaflight_sitl\u002FbfN` layout. The bundled checker is safe; execution wrappers should be run only after those external prerequisites are staged.\n- If you need to convert headless PNG recordings into MP4, use the bundled [`scripts\u002Fffmpeg_png2mp4.sh`](scripts\u002Fffmpeg_png2mp4.sh) helper rather than the source repo asset script.\n","# gym-pybullet-drones\n\nUse this repo skill when a task mentions `gym-pybullet-drones`, PyBullet drone or Crazyflie simulation, Aviary environments, PID\u002Fvelocity\u002Fdownwash\u002FMRAC control, Gymnasium hover environments, PPO training\u002Fplayback, or Betaflight SITL integration.\n\nThis skill is self-contained operating guidance for package version `2.2.0`. The original repository examples, tests, and assets were used as evidence, but future agents should use the bundled references and scripts in this skill rather than reopening or executing files from the source checkout.\n\n## Start here\n\n1. Confirm the package is installed in the active Python environment. The repository metadata targets Python `3.12`.\n2. Run the bundled import check if installation or Gymnasium registration is uncertain:\n\n   ```bash\n   python scripts\u002Fcheck_imports.py\n   python scripts\u002Fcheck_imports.py --headless-smoke --env-id hover-aviary-v0\n   ```\n\n3. Pick the route below and read the nearest sub-skill before running workflow-specific helpers.\n4. Keep `gui=False` \u002F headless mode for automation, CI, containers, or remote servers. Enable GUI, plotting, recording, and full-duration training only after the relevant sub-skill's troubleshooting page says the host can support them.\n\n## Installation and import baseline\n\nFor a published install or a local checkout, use a clean Python 3.12 environment and install only the package\u002Fruntime dependencies needed for the selected workflow:\n\n```bash\npython -m pip install gym-pybullet-drones\n# or, for a local checkout you are maintaining:\npython -m pip install -e \u002Fpath\u002Fto\u002Fgym-pybullet-drones\npython -m pip check\n```\n\nMinimal package import check:\n\n```python\nimport gym_pybullet_drones  # registers Gymnasium env IDs\nfrom gym_pybullet_drones.envs import CtrlAviary, VelocityAviary, HoverAviary, MultiHoverAviary\nfrom gym_pybullet_drones.utils.enums import DroneModel, Physics, ObservationType, ActionType\n```\n\nThe package has no console-script entry points. Use Python imports or the bundled helper scripts below.\n\n## Route map\n\n| Task signal | Read \u002F run |\n| --- | --- |\n| PID trajectory tracking, `CtrlAviary`, `VelocityAviary`, velocity commands, downwash physics, MRAC, `Logger`, headless control examples | [control-simulation](sub-skills\u002Fcontrol-simulation\u002FSKILL.md); helper: `python sub-skills\u002Fcontrol-simulation\u002Fscripts\u002Frun_control_example.py --list` |\n| PPO training, short RL smoke tests, `HoverAviary`, `MultiHoverAviary`, `hover-aviary-v0`, `multihover-aviary-v0`, SB3 model save\u002Fload\u002Fplayback | [rl-workflows](sub-skills\u002Frl-workflows\u002FSKILL.md); helper: `python sub-skills\u002Frl-workflows\u002Fscripts\u002Frun_rl_workflow.py --help` |\n| Betaflight SITL, `BetaAviary`, external `betaflight_sitl\u002FbfN` layout, UDP port mapping, `clone_bfs.sh` consequences | [betaflight-sitl](sub-skills\u002Fbetaflight-sitl\u002FSKILL.md); helper: `python sub-skills\u002Fbetaflight-sitl\u002Fscripts\u002Fcheck_betaflight_layout.py --help` |\n| Package layout, registered env IDs, shared enums, dependency\u002Fbackend notes, logger conventions | [package overview](references\u002Fpackage-overview.md) |\n| Install\u002Fimport, GUI\u002FOpenGL, Gymnasium registration, video conversion, and cross-workflow failures | [troubleshooting](references\u002Ftroubleshooting.md) |\n| Staleness or refresh decision for another checkout | [repo provenance](references\u002Frepo-provenance.md) |\n\n## Quick chooser\n\n- If the user says \"run the PID example\", \"velocity control\", \"downwash\", or \"MRAC\", start with `control-simulation`.\n- If the user says \"train a hover policy\", \"play a saved PPO model\", or mentions `hover-aviary-v0` \u002F `multihover-aviary-v0`, start with `rl-workflows`.\n- If the user says \"Betaflight SITL\", \"BetaAviary\", or \"check the external drone layout\", start with `betaflight-sitl`.\n- If the user only needs to know whether the package is installed and registered correctly, run `scripts\u002Fcheck_imports.py` first.\n\n## Operating guardrails\n\n- Required backend for this skill is CPU \u002F generic Python. CUDA is not required for any selected repo-native workflow, even though Torch may use accelerator hardware if the user's environment provides it.\n- PyBullet GUI is optional and host-dependent. Prefer `gui=False` for all smoke checks and automated verification.\n- `BaseAviary` requires `pyb_freq % ctrl_freq == 0`; use the bundled runners to catch timing mistakes before PyBullet construction.\n- Control observations use a 20-value state vector; `Logger.log(...)` expects one 20-value state and one 12-value control vector per drone.\n- RL smoke training proves environment\u002Frollout\u002Fsave\u002Fload mechanics, not policy quality. Full PPO training is intentionally not the default.\n- Betaflight SITL is an external integration: the package expects prebuilt Betaflight SITL binaries in a local `betaflight_sitl\u002FbfN` layout. The bundled checker is safe; execution wrappers should be run only after those external prerequisites are staged.\n- If you need to convert headless PNG recordings into MP4, use the bundled [`scripts\u002Fffmpeg_png2mp4.sh`](scripts\u002Fffmpeg_png2mp4.sh) helper rather than the source repo asset script.\n",{"name":5,"license":14,"metadata":23,"description":7,"disable-model-invocation":25},{"disco-role":24},"operating",true,"main","ac3fe1afa80fb9a09775ecfb2b6cc3ba850a2db6","skills\u002Frepositories\u002Frepo-skills\u002Fgym-pybullet-drones",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 gym-pybullet-drones",{"tool":39,"command":40},"bunx","bunx skills add VectorSpaceLab\u002FAREX-Skill --skill gym-pybullet-drones",{"tool":42,"command":43},"pnpm","pnpm dlx skills add VectorSpaceLab\u002FAREX-Skill --skill gym-pybullet-drones","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fgym-pybullet-drones\u002FSKILL.md",[46,52,56,60,64,70],{"path":47,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":50,"sourceHtmlUrl":51},"references\u002Fpackage-overview.md","REFERENCE","参考文档",4558,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fgym-pybullet-drones\u002Freferences\u002Fpackage-overview.md",{"path":53,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":54,"sourceHtmlUrl":55},"references\u002Frepo-provenance.md",1968,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fgym-pybullet-drones\u002Freferences\u002Frepo-provenance.md",{"path":57,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":58,"sourceHtmlUrl":59},"references\u002Frepo-routing-metadata.json",438,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fgym-pybullet-drones\u002Freferences\u002Frepo-routing-metadata.json",{"path":61,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":62,"sourceHtmlUrl":63},"references\u002Ftroubleshooting.md",5815,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fgym-pybullet-drones\u002Freferences\u002Ftroubleshooting.md",{"path":65,"resourceType":66,"resourceTypeDesc":67,"sizeBytes":68,"sourceHtmlUrl":69},"scripts\u002Fcheck_imports.py","SCRIPT","脚本",3289,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fgym-pybullet-drones\u002Fscripts\u002Fcheck_imports.py",{"path":71,"resourceType":66,"resourceTypeDesc":67,"sizeBytes":72,"sourceHtmlUrl":73},"scripts\u002Fffmpeg_png2mp4.sh",2246,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fgym-pybullet-drones\u002Fscripts\u002Fffmpeg_png2mp4.sh",[75,83,90,97,104,111],{"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":79,"licenseFileUrl":6,"sourceHtmlUrl":80,"categories":81,"keywords":82,"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":84,"name":85,"nameZh":6,"description":86,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":79,"licenseFileUrl":6,"sourceHtmlUrl":87,"categories":88,"keywords":89,"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":91,"name":92,"nameZh":6,"description":93,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":79,"licenseFileUrl":6,"sourceHtmlUrl":94,"categories":95,"keywords":96,"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":98,"name":99,"nameZh":6,"description":100,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":79,"licenseFileUrl":6,"sourceHtmlUrl":101,"categories":102,"keywords":103,"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":105,"name":106,"nameZh":6,"description":107,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":79,"licenseFileUrl":6,"sourceHtmlUrl":108,"categories":109,"keywords":110,"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":112,"name":113,"nameZh":6,"description":114,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":79,"licenseFileUrl":6,"sourceHtmlUrl":115,"categories":116,"keywords":117,"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",[],[]]