[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7ECG1Y2KC8KQM85F87RJ8GD":3,"skill-same:01M7ECG1Y2KC8KQM85F87RJ8GD":62},{"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},"01M7ECG1Y2KC8KQM85F87RJ8GD","vectorization",null,"Create, step, wrap, and troubleshoot Gymnasium vectorized environments for batched training and evaluation.","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\u002F03-逆向工程\u002Fgymnasium\u002Fsub-skills\u002Fvectorization\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: vectorization\ndescription: \"Create, step, wrap, and troubleshoot Gymnasium vectorized\n  environments for batched training and evaluation.\"\ndisable-model-invocation: true\nmetadata:\n  disco-role: operating\nlicense: MIT\n---\n\n# Gymnasium Vectorization\n\nUse this sub-skill when a task needs multiple Gymnasium environments stepped as one batch: `gymnasium.make_vec`, `SyncVectorEnv`, `AsyncVectorEnv`, vector wrappers, batched observations\u002Factions\u002Frewards\u002Fmasks\u002Finfos, autoreset modes, or vector multiprocessing troubleshooting.\n\n## Start Here\n\n1. Prefer `gymnasium.make_vec(env_id, num_envs=..., vectorization_mode=\"sync\" | \"async\")` for registered environments.\n2. Use `envs.action_space.sample()` or another action batch matching `envs.action_space`; use `envs.single_action_space` only to reason about one sub-environment.\n3. Treat `rewards`, `terminations`, and `truncations` as arrays of shape `(num_envs,)`, not scalar booleans.\n4. Check `envs.metadata[\"autoreset_mode\"]` before interpreting post-terminal observations or writing bootstrapping logic.\n5. Use `gymnasium.wrappers.vector` wrappers around vector envs; pass single-env wrappers through `make_vec(..., wrappers=[...])` only when they should wrap each sub-environment before vectorization.\n6. Always call `envs.close()`, especially for `AsyncVectorEnv` worker processes.\n\n## Route by Task\n\n| Task | Read |\n| --- | --- |\n| Create or step vector envs, choose sync vs async, handle batched outputs | [references\u002Fvector-envs.md](references\u002Fvector-envs.md) |\n| Apply vector wrappers, transform batched spaces, use vector space utilities | [references\u002Fvector-wrappers-and-spaces.md](references\u002Fvector-wrappers-and-spaces.md) |\n| Debug actions, masks, autoreset, multiprocessing, shared memory, render\u002Fvideo | [references\u002Ftroubleshooting.md](references\u002Ftroubleshooting.md) |\n| Prove a small local vector loop works | [`scripts\u002Fvector_env_smoke.py`](scripts\u002Fvector_env_smoke.py) |\n\n## Minimum Correct Pattern\n\n```python\nimport gymnasium as gym\n\nenvs = gym.make_vec(\"CartPole-v1\", num_envs=4, vectorization_mode=\"sync\")\ntry:\n    observations, infos = envs.reset(seed=123)\n    actions = envs.action_space.sample()\n    observations, rewards, terminations, truncations, infos = envs.step(actions)\n    done_mask = terminations | truncations\nfinally:\n    envs.close()\n```\n\nFor a quick sanity check from this sub-skill directory, run `python scripts\u002Fvector_env_smoke.py --help` and then `python scripts\u002Fvector_env_smoke.py --mode sync --num-envs 2 --steps 4`.\n\n## Scope Boundaries\n\n- Use `..\u002Fenvironment-api\u002FSKILL.md` for single `Env` contracts, custom environment classes, registration, `check_env`, and non-vector reset\u002Fstep migration.\n- Use `..\u002Fspaces-data\u002FSKILL.md` for fundamental `Space` constructors, dtype\u002Fshape design, `contains`, flattening, and JSONable conversion.\n- Use `..\u002Fwrappers-recording\u002FSKILL.md` for single-environment wrappers, recording, rendering, and custom wrapper subclassing depth.\n- Use `..\u002Fbuiltin-envs\u002FSKILL.md` for built-in family selection, optional extras\u002Fbackends, Atari\u002FALE, Box2D, MuJoCo, and Toy Text action masks.\n\nKeep runtime guidance self-contained. Do not depend on the Gymnasium source tree, tests, or documentation paths at runtime.\n","# Gymnasium Vectorization\n\nUse this sub-skill when a task needs multiple Gymnasium environments stepped as one batch: `gymnasium.make_vec`, `SyncVectorEnv`, `AsyncVectorEnv`, vector wrappers, batched observations\u002Factions\u002Frewards\u002Fmasks\u002Finfos, autoreset modes, or vector multiprocessing troubleshooting.\n\n## Start Here\n\n1. Prefer `gymnasium.make_vec(env_id, num_envs=..., vectorization_mode=\"sync\" | \"async\")` for registered environments.\n2. Use `envs.action_space.sample()` or another action batch matching `envs.action_space`; use `envs.single_action_space` only to reason about one sub-environment.\n3. Treat `rewards`, `terminations`, and `truncations` as arrays of shape `(num_envs,)`, not scalar booleans.\n4. Check `envs.metadata[\"autoreset_mode\"]` before interpreting post-terminal observations or writing bootstrapping logic.\n5. Use `gymnasium.wrappers.vector` wrappers around vector envs; pass single-env wrappers through `make_vec(..., wrappers=[...])` only when they should wrap each sub-environment before vectorization.\n6. Always call `envs.close()`, especially for `AsyncVectorEnv` worker processes.\n\n## Route by Task\n\n| Task | Read |\n| --- | --- |\n| Create or step vector envs, choose sync vs async, handle batched outputs | [references\u002Fvector-envs.md](references\u002Fvector-envs.md) |\n| Apply vector wrappers, transform batched spaces, use vector space utilities | [references\u002Fvector-wrappers-and-spaces.md](references\u002Fvector-wrappers-and-spaces.md) |\n| Debug actions, masks, autoreset, multiprocessing, shared memory, render\u002Fvideo | [references\u002Ftroubleshooting.md](references\u002Ftroubleshooting.md) |\n| Prove a small local vector loop works | [`scripts\u002Fvector_env_smoke.py`](scripts\u002Fvector_env_smoke.py) |\n\n## Minimum Correct Pattern\n\n```python\nimport gymnasium as gym\n\nenvs = gym.make_vec(\"CartPole-v1\", num_envs=4, vectorization_mode=\"sync\")\ntry:\n    observations, infos = envs.reset(seed=123)\n    actions = envs.action_space.sample()\n    observations, rewards, terminations, truncations, infos = envs.step(actions)\n    done_mask = terminations | truncations\nfinally:\n    envs.close()\n```\n\nFor a quick sanity check from this sub-skill directory, run `python scripts\u002Fvector_env_smoke.py --help` and then `python scripts\u002Fvector_env_smoke.py --mode sync --num-envs 2 --steps 4`.\n\n## Scope Boundaries\n\n- Use `..\u002Fenvironment-api\u002FSKILL.md` for single `Env` contracts, custom environment classes, registration, `check_env`, and non-vector reset\u002Fstep migration.\n- Use `..\u002Fspaces-data\u002FSKILL.md` for fundamental `Space` constructors, dtype\u002Fshape design, `contains`, flattening, and JSONable conversion.\n- Use `..\u002Fwrappers-recording\u002FSKILL.md` for single-environment wrappers, recording, rendering, and custom wrapper subclassing depth.\n- Use `..\u002Fbuiltin-envs\u002FSKILL.md` for built-in family selection, optional extras\u002Fbackends, Atari\u002FALE, Box2D, MuJoCo, and Toy Text action masks.\n\nKeep runtime guidance self-contained. Do not depend on the Gymnasium source tree, tests, or documentation paths at runtime.\n",{"name":5,"license":15,"metadata":24,"description":7,"disable-model-invocation":26},{"disco-role":25},"operating",true,"main","d69096e239f2a89aabc2cd078c47664a9d3b1e11","03-逆向工程\u002Fgymnasium\u002Fsub-skills\u002Fvectorization",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 vectorization",{"tool":41,"command":42},"bunx","bunx skills add lza6\u002FArmor-piercing-system-prompts --skill vectorization",{"tool":44,"command":45},"pnpm","pnpm dlx skills add lza6\u002FArmor-piercing-system-prompts --skill vectorization","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F03-逆向工程\u002Fgymnasium\u002Fsub-skills\u002Fvectorization\u002FSKILL.md",[48,54,58],{"path":49,"resourceType":50,"resourceTypeDesc":51,"sizeBytes":52,"sourceHtmlUrl":53},"references\u002Ftroubleshooting.md","REFERENCE","参考文档",6640,"https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F03-逆向工程\u002Fgymnasium\u002Fsub-skills\u002Fvectorization\u002Freferences\u002Ftroubleshooting.md",{"path":55,"resourceType":50,"resourceTypeDesc":51,"sizeBytes":56,"sourceHtmlUrl":57},"references\u002Fvector-envs.md",7228,"https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F03-逆向工程\u002Fgymnasium\u002Fsub-skills\u002Fvectorization\u002Freferences\u002Fvector-envs.md",{"path":59,"resourceType":50,"resourceTypeDesc":51,"sizeBytes":60,"sourceHtmlUrl":61},"references\u002Fvector-wrappers-and-spaces.md",6644,"https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F03-逆向工程\u002Fgymnasium\u002Fsub-skills\u002Fvectorization\u002Freferences\u002Fvector-wrappers-and-spaces.md",[63,71,76,83,90,97],{"skillNo":64,"name":65,"nameZh":6,"description":66,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":67,"categories":68,"keywords":69,"publishedAt":70},"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",[],[],"2026-11-16 10:05:34",{"skillNo":72,"name":65,"nameZh":6,"description":66,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":73,"categories":74,"keywords":75,"publishedAt":70},"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":77,"name":78,"nameZh":6,"description":79,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":80,"categories":81,"keywords":82,"publishedAt":70},"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":84,"name":85,"nameZh":6,"description":86,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":87,"categories":88,"keywords":89,"publishedAt":70},"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":91,"name":92,"nameZh":6,"description":93,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":94,"categories":95,"keywords":96,"publishedAt":70},"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":98,"name":99,"nameZh":6,"description":100,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":101,"categories":102,"keywords":103,"publishedAt":70},"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",[],[]]