[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7FBYYJBFE8ACYTAVFFF3NV9":3,"skill-same:01M7FBYYJBFE8ACYTAVFFF3NV9":66},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":16,"categories":17,"keywords":18,"publishedAt":19,"linkOnly":20,"markdownContent":21,"markdownBody":22,"frontMatter":23,"refName":27,"commitSha":28,"skillDirectory":29,"forksCount":30,"repositoryHtmlUrl":31,"repositoryHomepageUrl":6,"ownerHtmlUrl":32,"ownerBlogUrl":6,"ownerDescription":33,"updatedAt":34,"install":35,"resources":47},"01M7FBYYJBFE8ACYTAVFFF3NV9","rl-mpc-locomotion",null,"Guide quadruped locomotion workflows built from Python convex MPC, FSM and gait control, NVIDIA Isaac Gym simulation, Hydra\u002FRSL-RL training, learned MPC-weight policies, robot assets, and CUDA or solver troubleshooting.","lza6\u002FArmor-piercing-system-prompts","lza6","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F128880206?v=4","01M7EB3K7WPX5T28EJ2NVHE6EG","Chinese-tingfeng","01M7EB3K97E1KQ16QWKJMFNGX8",11,"MIT","https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F06-前端与设计\u002Frl-mpc-locomotion\u002FSKILL.md",[],[],"2026-11-16 10:05:34",false,"---\nname: rl-mpc-locomotion\ndescription: \"Guide quadruped locomotion workflows built from Python convex MPC,\n  FSM and gait control, NVIDIA Isaac Gym simulation, Hydra\u002FRSL-RL training,\n  learned MPC-weight policies, robot assets, and CUDA or solver\n  troubleshooting.\"\ndisable-model-invocation: true\nmetadata:\n  disco-role: operating\nlicense: MIT\n---\n\n# RL-MPC Locomotion\n\nUse this repo skill when a task involves the `rl_mpc_locomotion` package, its\n`MPC_Controller` and `RL_Environment` modules, quadruped torque control, Isaac\nGym locomotion simulation, or learned MPC-weight policies. This is a router,\nnot a replacement for the focused workflow references.\n\n## Gate before acting\n\n1. Read [repository provenance](references\u002Frepo-provenance.md) when checking\n   whether the guidance matches the source revision.\n2. Use [setup-and-diagnostics](sub-skills\u002Fsetup-and-diagnostics\u002FSKILL.md) first\n   for an isolated Python 3.8-era environment, pinned native inputs,\n   `mpc_osqp`, CUDA, Isaac Gym, asset, and checkpoint probes.\n3. Treat Isaac Gym Preview 4 as a required external backend for simulation,\n   RL training\u002Fevaluation, and the interactive launcher. The construction\n   evidence verified PyTorch 1.10\u002FCUDA 11.3, CUDA allocation, repository\n   imports, `rsl_rl`, and `mpc_osqp`, but did not verify Isaac Gym. Do not\n   substitute a CUDA tensor or CPU import for that gate.\n\n## Route by task\n\n- **MPC, gait, FSM, state estimation, robot model, torque arrays, or solver\n  binding:** read [mpc-control](sub-skills\u002Fmpc-control\u002FSKILL.md).\n- **Hydra training, evaluation, task YAML, observations\u002Factions\u002Frewards,\n  checkpoints, policy bridge, or TensorBoard:** read\n  [rl-training](sub-skills\u002Frl-training\u002FSKILL.md), then route low-level torque\n  questions to `mpc-control`.\n- **Isaac Gym setup, PhysX, URDF\u002Fassets, terrains, state tensors, effort\n  control, viewer lifecycle, or gamepad launcher:** read\n  [isaac-gym-simulation](sub-skills\u002Fisaac-gym-simulation\u002FSKILL.md).\n- **Installation order, submodules, PyTorch\u002FCUDA conflicts, compiled\n  extension, optional solver, missing config\u002Fasset, or backend diagnosis:**\n  read [setup-and-diagnostics](sub-skills\u002Fsetup-and-diagnostics\u002FSKILL.md).\n\nFor shared concepts and cross-route boundaries, read\n[the architecture overview](references\u002Farchitecture-overview.md). For a\ncross-cutting failure, read [troubleshooting](references\u002Ftroubleshooting.md).\n\n## Minimal public package check\n\nIn a current project copy, install the package after its documented native\ninputs are present:\n\n```bash\npython -m pip install -e .\npython -c \"import MPC_Controller, RL_Environment, mpc_osqp; print('MPC package imports passed')\"\n```\n\nRun the bundled checks from the generated skill root (or enter the setup\nsub-skill directory). Set `PROJECT_COPY` to the current user-supplied project\ncopy when validating its native layout\u002Fconfig\u002Fassets; it is not a path inside\nthis skill bundle. The checks are read-only unless `--build` is passed\nexplicitly to the extension checker:\n\n```bash\nPROJECT_COPY=\u002Fpath\u002Fto\u002Fcurrent\u002Fproject-copy\npython sub-skills\u002Fsetup-and-diagnostics\u002Fscripts\u002Fcheck_environment.py --pip-check\npython sub-skills\u002Fsetup-and-diagnostics\u002Fscripts\u002Fcheck_mpc_extension.py --repo-root \"$PROJECT_COPY\" --check-submodules --strict\npython sub-skills\u002Fsetup-and-diagnostics\u002Fscripts\u002Fvalidate_config.py --repo-root \"$PROJECT_COPY\" --all-tasks --strict\n```\n\nThe setup sub-skill documents the explicit project-root argument needed when\nchecking a particular checkout. These commands do not prove Isaac Gym or a\nstable gait.\n\n## Safety and handoff\n\nNever start a viewer, gamepad reader, training run, or policy deployment as an\ninstallation smoke test. Confirm robot\u002Ftask, device, checkpoint, run directory,\nbackend availability, and cleanup behavior first. The project supports\n`Aliengo`, `A1`, and `Go1` in the public runtime selection; the bundled Mini\nCheetah assets are not a launcher robot choice. Sim-to-real operation is outside\nthis repository's verified contract.\n","# RL-MPC Locomotion\n\nUse this repo skill when a task involves the `rl_mpc_locomotion` package, its\n`MPC_Controller` and `RL_Environment` modules, quadruped torque control, Isaac\nGym locomotion simulation, or learned MPC-weight policies. This is a router,\nnot a replacement for the focused workflow references.\n\n## Gate before acting\n\n1. Read [repository provenance](references\u002Frepo-provenance.md) when checking\n   whether the guidance matches the source revision.\n2. Use [setup-and-diagnostics](sub-skills\u002Fsetup-and-diagnostics\u002FSKILL.md) first\n   for an isolated Python 3.8-era environment, pinned native inputs,\n   `mpc_osqp`, CUDA, Isaac Gym, asset, and checkpoint probes.\n3. Treat Isaac Gym Preview 4 as a required external backend for simulation,\n   RL training\u002Fevaluation, and the interactive launcher. The construction\n   evidence verified PyTorch 1.10\u002FCUDA 11.3, CUDA allocation, repository\n   imports, `rsl_rl`, and `mpc_osqp`, but did not verify Isaac Gym. Do not\n   substitute a CUDA tensor or CPU import for that gate.\n\n## Route by task\n\n- **MPC, gait, FSM, state estimation, robot model, torque arrays, or solver\n  binding:** read [mpc-control](sub-skills\u002Fmpc-control\u002FSKILL.md).\n- **Hydra training, evaluation, task YAML, observations\u002Factions\u002Frewards,\n  checkpoints, policy bridge, or TensorBoard:** read\n  [rl-training](sub-skills\u002Frl-training\u002FSKILL.md), then route low-level torque\n  questions to `mpc-control`.\n- **Isaac Gym setup, PhysX, URDF\u002Fassets, terrains, state tensors, effort\n  control, viewer lifecycle, or gamepad launcher:** read\n  [isaac-gym-simulation](sub-skills\u002Fisaac-gym-simulation\u002FSKILL.md).\n- **Installation order, submodules, PyTorch\u002FCUDA conflicts, compiled\n  extension, optional solver, missing config\u002Fasset, or backend diagnosis:**\n  read [setup-and-diagnostics](sub-skills\u002Fsetup-and-diagnostics\u002FSKILL.md).\n\nFor shared concepts and cross-route boundaries, read\n[the architecture overview](references\u002Farchitecture-overview.md). For a\ncross-cutting failure, read [troubleshooting](references\u002Ftroubleshooting.md).\n\n## Minimal public package check\n\nIn a current project copy, install the package after its documented native\ninputs are present:\n\n```bash\npython -m pip install -e .\npython -c \"import MPC_Controller, RL_Environment, mpc_osqp; print('MPC package imports passed')\"\n```\n\nRun the bundled checks from the generated skill root (or enter the setup\nsub-skill directory). Set `PROJECT_COPY` to the current user-supplied project\ncopy when validating its native layout\u002Fconfig\u002Fassets; it is not a path inside\nthis skill bundle. The checks are read-only unless `--build` is passed\nexplicitly to the extension checker:\n\n```bash\nPROJECT_COPY=\u002Fpath\u002Fto\u002Fcurrent\u002Fproject-copy\npython sub-skills\u002Fsetup-and-diagnostics\u002Fscripts\u002Fcheck_environment.py --pip-check\npython sub-skills\u002Fsetup-and-diagnostics\u002Fscripts\u002Fcheck_mpc_extension.py --repo-root \"$PROJECT_COPY\" --check-submodules --strict\npython sub-skills\u002Fsetup-and-diagnostics\u002Fscripts\u002Fvalidate_config.py --repo-root \"$PROJECT_COPY\" --all-tasks --strict\n```\n\nThe setup sub-skill documents the explicit project-root argument needed when\nchecking a particular checkout. These commands do not prove Isaac Gym or a\nstable gait.\n\n## Safety and handoff\n\nNever start a viewer, gamepad reader, training run, or policy deployment as an\ninstallation smoke test. Confirm robot\u002Ftask, device, checkpoint, run directory,\nbackend availability, and cleanup behavior first. The project supports\n`Aliengo`, `A1`, and `Go1` in the public runtime selection; the bundled Mini\nCheetah assets are not a launcher robot choice. Sim-to-real operation is outside\nthis repository's verified contract.\n",{"name":5,"license":15,"metadata":24,"description":7,"disable-model-invocation":26},{"disco-role":25},"operating",true,"main","d69096e239f2a89aabc2cd078c47664a9d3b1e11","06-前端与设计\u002Frl-mpc-locomotion",3,"https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts","https:\u002F\u002Fgithub.com\u002Flza6","个人vx：Tf00798\r\n个人✈：@TFGY999","2026-10-08 14:29:22",{"source":8,"skillName":5,"commands":36,"prompt":46,"zipAvailable":26},[37,40,43],{"tool":38,"command":39},"npx","npx skills add lza6\u002FArmor-piercing-system-prompts --skill rl-mpc-locomotion",{"tool":41,"command":42},"bunx","bunx skills add lza6\u002FArmor-piercing-system-prompts --skill rl-mpc-locomotion",{"tool":44,"command":45},"pnpm","pnpm dlx skills add lza6\u002FArmor-piercing-system-prompts --skill rl-mpc-locomotion","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F06-前端与设计\u002Frl-mpc-locomotion\u002FSKILL.md",[48,54,58,62],{"path":49,"resourceType":50,"resourceTypeDesc":51,"sizeBytes":52,"sourceHtmlUrl":53},"references\u002Farchitecture-overview.md","REFERENCE","参考文档",2159,"https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F06-前端与设计\u002Frl-mpc-locomotion\u002Freferences\u002Farchitecture-overview.md",{"path":55,"resourceType":50,"resourceTypeDesc":51,"sizeBytes":56,"sourceHtmlUrl":57},"references\u002Frepo-provenance.md",2254,"https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F06-前端与设计\u002Frl-mpc-locomotion\u002Freferences\u002Frepo-provenance.md",{"path":59,"resourceType":50,"resourceTypeDesc":51,"sizeBytes":60,"sourceHtmlUrl":61},"references\u002Frepo-routing-metadata.json",535,"https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F06-前端与设计\u002Frl-mpc-locomotion\u002Freferences\u002Frepo-routing-metadata.json",{"path":63,"resourceType":50,"resourceTypeDesc":51,"sizeBytes":64,"sourceHtmlUrl":65},"references\u002Ftroubleshooting.md",3538,"https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F06-前端与设计\u002Frl-mpc-locomotion\u002Freferences\u002Ftroubleshooting.md",[67,74,79,86,93,100],{"skillNo":68,"name":69,"nameZh":6,"description":70,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":71,"categories":72,"keywords":73,"publishedAt":19},"01M7FFG485KY83TD6HSC4YPCMC","obsidian-clipper-template-creator","Guide for creating templates for the Obsidian Web Clipper. Use when you want to create a new clipping template, understand available variables, or format clipped content.","https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F07-后端与架构\u002Fobsidian-clipper-template-creator\u002FSKILL.md",[],[],{"skillNo":75,"name":69,"nameZh":6,"description":70,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":76,"categories":77,"keywords":78,"publishedAt":19},"01M7FFG0T6AZ0STEJPSB3CX84K","https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F07-后端与架构\u002Fobsidian-clipper-template-creator-antigravity-awesome-skills-main\u002FSKILL.md",[],[],{"skillNo":80,"name":81,"nameZh":6,"description":82,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":83,"categories":84,"keywords":85,"publishedAt":19},"01M7FFFY0QEM14SKWPDYGMXM2P","python-api","Programmatic Object-Detection-Metrics API guidance for BoundingBox, BoundingBoxes, Evaluator, enums, coordinate conversion, AP\u002FmAP semantics, and source-style import diagnostics.","https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F07-后端与架构\u002Fobject-detection-metrics\u002Fsub-skills\u002Fpython-api\u002FSKILL.md",[],[],{"skillNo":87,"name":88,"nameZh":6,"description":89,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":90,"categories":91,"keywords":92,"publishedAt":19},"01M7FFFVZQZ2GJ0C0TGP7JHD20","file-evaluation","Folder-based PASCAL VOC AP\u002FmAP evaluation from ground-truth and detection text files.","https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F07-后端与架构\u002Fobject-detection-metrics\u002Fsub-skills\u002Ffile-evaluation\u002FSKILL.md",[],[],{"skillNo":94,"name":95,"nameZh":6,"description":96,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":97,"categories":98,"keywords":99,"publishedAt":19},"01M7FFFSFNYSE77SJ6PE1CK2DA","object-detection-metrics","Guides legacy Object-Detection-Metrics PASCAL VOC AP\u002FmAP evaluation from detection text folders and direct Python API classes.","https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F07-后端与架构\u002Fobject-detection-metrics\u002FSKILL.md",[],[],{"skillNo":101,"name":102,"nameZh":6,"description":103,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":104,"categories":105,"keywords":106,"publishedAt":19},"01M7FFFP0GCK1RVXBCPQ8APBMT","nx-workspace-patterns","Configure and optimize Nx monorepo workspaces. Use when setting up Nx, configuring project boundaries, optimizing build caching, or implementing affected commands.","https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F07-后端与架构\u002Fnx-workspace-patterns\u002FSKILL.md",[],[]]