[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7FBYCDK2XACJ5SN7SKZAP6D":3,"skill-same:01M7FBYCDK2XACJ5SN7SKZAP6D":63},{"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":28,"commitSha":29,"skillDirectory":30,"forksCount":31,"repositoryHtmlUrl":32,"repositoryHomepageUrl":6,"ownerHtmlUrl":33,"ownerBlogUrl":6,"ownerDescription":34,"updatedAt":35,"install":36,"resources":48},"01M7FBYCDK2XACJ5SN7SKZAP6D","rex-gym",null,"Operate the legacy Rex-Gym quadruped reinforcement-learning package for PyBullet environments, kinematics and gait modeling, PPO training setup, and packaged policy playback.","lza6\u002FArmor-piercing-system-prompts","lza6","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F128880206?v=4","01M7EB3K7WPX5T28EJ2NVHE6EG","Chinese-tingfeng","01M7EB3K97E1KQ16QWKJMFNGX8",11,"Apache-2.0","https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F06-前端与设计\u002Frex-gym\u002FSKILL.md",[],[],"2026-11-16 10:05:34",false,"---\nname: rex-gym\ndescription: \"Operate the legacy Rex-Gym quadruped reinforcement-learning\n  package for PyBullet environments, kinematics and gait modeling, PPO training\n  setup, and packaged policy playback.\"\ndisable-model-invocation: true\nmetadata:\n  disco-role: operating\nlicense: Apache 2.0\n---\n\n# Rex-Gym operating skill\n\nUse this skill when a task involves the `rex_gym` package, Rex\u002FSpotMicro\nquadruped simulation, PyBullet Gym environments, inverse kinematics, Bezier\nwalking\u002Fgalloping, motor models, legacy PPO training, or shipped policy\ncheckpoints.\n\n## Route the request\n\n- Use [simulation-environments](sub-skills\u002Fsimulation-environments\u002FSKILL.md) for\n  environment construction, task\u002Fsignal\u002Fterrain\u002Fmark selection, reset\u002Fstep,\n  observations, rewards, termination, and headless or GUI simulation.\n- Use [locomotion-modeling](sub-skills\u002Flocomotion-modeling\u002FSKILL.md) for\n  `Kinematics`, `GaitPlanner`, pose\u002Fframe ordering, motor constants, and torque\n  conversion.\n- Use [training-policy](sub-skills\u002Ftraining-policy\u002FSKILL.md) for `rex-gym\n  train`, `rex-gym policy`, PPO configuration, agent counts, log directories,\n  policy ids, checkpoints, and TensorFlow compatibility.\n\nRead [troubleshooting](references\u002Ftroubleshooting.md) first when installation,\nlegacy dependencies, package data, or a runtime error is involved. Read\n[repository provenance](references\u002Frepo-provenance.md) before deciding whether\nthis graph matches a changed checkout. Run the shared [package inspector](scripts\u002Finspect_rex_gym.py)\nfor a no-training import, CLI, mapping, and deterministic-kinematics check; use\n[troubleshooting](references\u002Ftroubleshooting.md) for cross-cutting failures.\n\n## Install and establish the compatibility family\n\nThe public distribution is `rex_gym`, imported as `rex_gym`, and exposes the\n`rex-gym` console command:\n\n```bash\npython -m pip install rex_gym\npython -c \"import rex_gym; print('rex_gym import ok')\"\nrex-gym --help\n```\n\nFor the pinned repository behavior, prefer an isolated Python 3.7 environment\nwith NumPy 1.17.3, PyBullet 2.8.3, Gym 0.17.1, TensorFlow 1.15.5,\nTensorFlow Probability 0.8, `ruamel.yaml`, and Click. Modern pip reports an\nupstream metadata conflict between Gym 0.17.1's `cloudpickle` range and TFP\n0.8's exact pin; do not casually upgrade this legacy family. TensorFlow 1.15\nalso needs a protobuf 3.20.x-or-earlier runtime on modern installations. See\nthe training route for the optional PPO surface and the troubleshooting\nreference for recovery.\n\n## Choose a safe execution mode\n\nPrefer headless PyBullet (`render=False`) and a bounded step count on servers,\nCI, and first checks. Use the simulation smoke helper for a deterministic\npackage\u002FAPI check; it supplies `terrain_id` explicitly and always closes the\nenvironment. Do not start full training or policy playback merely to test an\nimport. GUI playback and playground training require a display and can run\nuntil the environment ends.\n\nThe legacy environment API is `reset()` followed by `step(action)` returning\n`(observation, reward, done, info)`, not the newer terminated\u002Ftruncated pair.\nUse task-specific action spaces, and expect `info[\"action\"]` to contain the\ntransformed motor command. Always close environments in `finally` blocks.\n\n## Scope and non-goals\n\nThis graph covers the public simulation and learning tools in Rex-Gym. It does\nnot operate physical hardware, replace `rexctl`, validate sim-to-real transfer,\nclaim policy quality, or prescribe long PPO experiments without an explicit\nbounded run plan. Large TensorFlow checkpoint binaries remain package data;\ninspect their catalog and sidecars rather than copying them into this skill.\n\nThe source package is legacy and has no dedicated repository test suite or\nexamples tree. The bundled routes and scripts therefore combine documented\nworkflows, source-backed API facts, live import checks, and bounded synthetic\nsmokes. Use the verification artifacts only as construction evidence; they are\nnot runtime dependencies.\n","# Rex-Gym operating skill\n\nUse this skill when a task involves the `rex_gym` package, Rex\u002FSpotMicro\nquadruped simulation, PyBullet Gym environments, inverse kinematics, Bezier\nwalking\u002Fgalloping, motor models, legacy PPO training, or shipped policy\ncheckpoints.\n\n## Route the request\n\n- Use [simulation-environments](sub-skills\u002Fsimulation-environments\u002FSKILL.md) for\n  environment construction, task\u002Fsignal\u002Fterrain\u002Fmark selection, reset\u002Fstep,\n  observations, rewards, termination, and headless or GUI simulation.\n- Use [locomotion-modeling](sub-skills\u002Flocomotion-modeling\u002FSKILL.md) for\n  `Kinematics`, `GaitPlanner`, pose\u002Fframe ordering, motor constants, and torque\n  conversion.\n- Use [training-policy](sub-skills\u002Ftraining-policy\u002FSKILL.md) for `rex-gym\n  train`, `rex-gym policy`, PPO configuration, agent counts, log directories,\n  policy ids, checkpoints, and TensorFlow compatibility.\n\nRead [troubleshooting](references\u002Ftroubleshooting.md) first when installation,\nlegacy dependencies, package data, or a runtime error is involved. Read\n[repository provenance](references\u002Frepo-provenance.md) before deciding whether\nthis graph matches a changed checkout. Run the shared [package inspector](scripts\u002Finspect_rex_gym.py)\nfor a no-training import, CLI, mapping, and deterministic-kinematics check; use\n[troubleshooting](references\u002Ftroubleshooting.md) for cross-cutting failures.\n\n## Install and establish the compatibility family\n\nThe public distribution is `rex_gym`, imported as `rex_gym`, and exposes the\n`rex-gym` console command:\n\n```bash\npython -m pip install rex_gym\npython -c \"import rex_gym; print('rex_gym import ok')\"\nrex-gym --help\n```\n\nFor the pinned repository behavior, prefer an isolated Python 3.7 environment\nwith NumPy 1.17.3, PyBullet 2.8.3, Gym 0.17.1, TensorFlow 1.15.5,\nTensorFlow Probability 0.8, `ruamel.yaml`, and Click. Modern pip reports an\nupstream metadata conflict between Gym 0.17.1's `cloudpickle` range and TFP\n0.8's exact pin; do not casually upgrade this legacy family. TensorFlow 1.15\nalso needs a protobuf 3.20.x-or-earlier runtime on modern installations. See\nthe training route for the optional PPO surface and the troubleshooting\nreference for recovery.\n\n## Choose a safe execution mode\n\nPrefer headless PyBullet (`render=False`) and a bounded step count on servers,\nCI, and first checks. Use the simulation smoke helper for a deterministic\npackage\u002FAPI check; it supplies `terrain_id` explicitly and always closes the\nenvironment. Do not start full training or policy playback merely to test an\nimport. GUI playback and playground training require a display and can run\nuntil the environment ends.\n\nThe legacy environment API is `reset()` followed by `step(action)` returning\n`(observation, reward, done, info)`, not the newer terminated\u002Ftruncated pair.\nUse task-specific action spaces, and expect `info[\"action\"]` to contain the\ntransformed motor command. Always close environments in `finally` blocks.\n\n## Scope and non-goals\n\nThis graph covers the public simulation and learning tools in Rex-Gym. It does\nnot operate physical hardware, replace `rexctl`, validate sim-to-real transfer,\nclaim policy quality, or prescribe long PPO experiments without an explicit\nbounded run plan. Large TensorFlow checkpoint binaries remain package data;\ninspect their catalog and sidecars rather than copying them into this skill.\n\nThe source package is legacy and has no dedicated repository test suite or\nexamples tree. The bundled routes and scripts therefore combine documented\nworkflows, source-backed API facts, live import checks, and bounded synthetic\nsmokes. Use the verification artifacts only as construction evidence; they are\nnot runtime dependencies.\n",{"name":5,"license":24,"metadata":25,"description":7,"disable-model-invocation":27},"Apache 2.0",{"disco-role":26},"operating",true,"main","d69096e239f2a89aabc2cd078c47664a9d3b1e11","06-前端与设计\u002Frex-gym",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":37,"prompt":47,"zipAvailable":27},[38,41,44],{"tool":39,"command":40},"npx","npx skills add lza6\u002FArmor-piercing-system-prompts --skill rex-gym",{"tool":42,"command":43},"bunx","bunx skills add lza6\u002FArmor-piercing-system-prompts --skill rex-gym",{"tool":45,"command":46},"pnpm","pnpm dlx skills add lza6\u002FArmor-piercing-system-prompts --skill rex-gym","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\u002Frex-gym\u002FSKILL.md",[49,55,59],{"path":50,"resourceType":51,"resourceTypeDesc":52,"sizeBytes":53,"sourceHtmlUrl":54},"references\u002Frepo-provenance.md","REFERENCE","参考文档",1737,"https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F06-前端与设计\u002Frex-gym\u002Freferences\u002Frepo-provenance.md",{"path":56,"resourceType":51,"resourceTypeDesc":52,"sizeBytes":57,"sourceHtmlUrl":58},"references\u002Frepo-routing-metadata.json",502,"https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F06-前端与设计\u002Frex-gym\u002Freferences\u002Frepo-routing-metadata.json",{"path":60,"resourceType":51,"resourceTypeDesc":52,"sizeBytes":61,"sourceHtmlUrl":62},"references\u002Ftroubleshooting.md",5283,"https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F06-前端与设计\u002Frex-gym\u002Freferences\u002Ftroubleshooting.md",[64,72,77,84,91,98],{"skillNo":65,"name":66,"nameZh":6,"description":67,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":68,"licenseFileUrl":6,"sourceHtmlUrl":69,"categories":70,"keywords":71,"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.","MIT","https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F07-后端与架构\u002Fobsidian-clipper-template-creator\u002FSKILL.md",[],[],{"skillNo":73,"name":66,"nameZh":6,"description":67,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":68,"licenseFileUrl":6,"sourceHtmlUrl":74,"categories":75,"keywords":76,"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":78,"name":79,"nameZh":6,"description":80,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":68,"licenseFileUrl":6,"sourceHtmlUrl":81,"categories":82,"keywords":83,"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":85,"name":86,"nameZh":6,"description":87,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":68,"licenseFileUrl":6,"sourceHtmlUrl":88,"categories":89,"keywords":90,"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":92,"name":93,"nameZh":6,"description":94,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":68,"licenseFileUrl":6,"sourceHtmlUrl":95,"categories":96,"keywords":97,"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":99,"name":100,"nameZh":6,"description":101,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":68,"licenseFileUrl":6,"sourceHtmlUrl":102,"categories":103,"keywords":104,"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",[],[]]