[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7963AXWAZNKP377Z2DG770F":3,"skill-same:01M7963AXWAZNKP377Z2DG770F":75},{"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},"01M7963AXWAZNKP377Z2DG770F","agents-and-specifications",null,"Use Tensorforce Agent.create, Agent.load, algorithm aliases, state\u002Faction specifications, action masking, and low-level act\u002Fobserve or experience\u002Fupdate APIs.","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\u002Ftensorforce\u002Fsub-skills\u002Fagents-and-specifications\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: agents-and-specifications\ndescription: \"Use Tensorforce Agent.create, Agent.load, algorithm aliases,\n  state\u002Faction specifications, action masking, and low-level act\u002Fobserve or\n  experience\u002Fupdate APIs.\"\ndisable-model-invocation: true\nmetadata:\n  disco-role: operating\nlicense: Apache 2.0\n---\n\n# Tensorforce Agents and Specifications\n\nUse this sub-skill when a task asks how to construct or load a Tensorforce agent, choose an algorithm alias, write state\u002Faction specifications, pass action masks, or drive an agent without `Runner` through `act`, `observe`, `experience`, and `update`.\n\n## Route by task\n\n- **Create or load an agent**: read [`references\u002Fagent-specifications.md`](references\u002Fagent-specifications.md), then confirm exact public signatures and aliases in [`references\u002Fapi-reference.md`](references\u002Fapi-reference.md).\n- **Choose between `ppo`, `dqn`, `random`, `tensorforce`, and other aliases**: use the alias table in [`references\u002Fapi-reference.md`](references\u002Fapi-reference.md). Route deep network, optimizer, memory, objective, policy, preprocessing, and parameter catalogs to `..\u002Fmodules-and-configuration\u002F`.\n- **Write state\u002Faction schemas**: use [`references\u002Fagent-specifications.md`](references\u002Fagent-specifications.md). Route custom environment implementations and adapter spaces to `..\u002Fenvironments-and-interaction\u002F`.\n- **Use action masking**: read the action-mask section in [`references\u002Fagent-specifications.md`](references\u002Fagent-specifications.md) and run or adapt [`scripts\u002Faction_masking_smoke.py`](scripts\u002Faction_masking_smoke.py).\n- **Write a manual training\u002Fevaluation loop**: read [`references\u002Finteraction-apis.md`](references\u002Finteraction-apis.md) and run or adapt [`scripts\u002Fact_observe_smoke.py`](scripts\u002Fact_observe_smoke.py).\n- **Diagnose errors**: use [`references\u002Ftroubleshooting.md`](references\u002Ftroubleshooting.md) before changing dependencies or agent specs.\n\n## Key operating rules\n\n1. Prefer `Agent.create(..., environment=environment)` when an environment object is already available; Tensorforce then infers `states`, `actions`, and `max_episode_timesteps` where possible.\n2. If no environment object is available, pass explicit `states`, `actions`, and any required algorithm arguments. The primitive value spec is `dict(type='bool'|'int'|'float', shape=..., num_values=..., min_value=..., max_value=...)`.\n3. For non-independent training, every `agent.act(states=...)` must be followed by exactly one `agent.observe(terminal=..., reward=...)` for the same parallel interaction.\n4. For evaluation, offline recording, or externally collected episodes, call `agent.act(..., independent=True)` and use `agent.initial_internals()` when recurrent\u002Finternal states are present.\n5. Action masks are auxiliary state entries, not part of `states` specs. For a singleton integer action, use `action_mask`; for a named integer action such as `move`, use `move_mask`.\n6. Always close agents and environments you created directly. If `Runner` owns construction\u002Fclosing, route to `..\u002Frunner-and-cli-workflows\u002F`.\n\n## Boundaries\n\nThis sub-skill owns agent creation\u002Floading, algorithm alias selection, state\u002Faction specifications, action masking, and low-level interaction APIs. It intentionally excludes Runner orchestration and CLI workflows, custom environment implementation details, persistence\u002Fexport\u002Frecording depth, and exhaustive module catalogs; use the sibling routes named above for those areas.\n","# Tensorforce Agents and Specifications\n\nUse this sub-skill when a task asks how to construct or load a Tensorforce agent, choose an algorithm alias, write state\u002Faction specifications, pass action masks, or drive an agent without `Runner` through `act`, `observe`, `experience`, and `update`.\n\n## Route by task\n\n- **Create or load an agent**: read [`references\u002Fagent-specifications.md`](references\u002Fagent-specifications.md), then confirm exact public signatures and aliases in [`references\u002Fapi-reference.md`](references\u002Fapi-reference.md).\n- **Choose between `ppo`, `dqn`, `random`, `tensorforce`, and other aliases**: use the alias table in [`references\u002Fapi-reference.md`](references\u002Fapi-reference.md). Route deep network, optimizer, memory, objective, policy, preprocessing, and parameter catalogs to `..\u002Fmodules-and-configuration\u002F`.\n- **Write state\u002Faction schemas**: use [`references\u002Fagent-specifications.md`](references\u002Fagent-specifications.md). Route custom environment implementations and adapter spaces to `..\u002Fenvironments-and-interaction\u002F`.\n- **Use action masking**: read the action-mask section in [`references\u002Fagent-specifications.md`](references\u002Fagent-specifications.md) and run or adapt [`scripts\u002Faction_masking_smoke.py`](scripts\u002Faction_masking_smoke.py).\n- **Write a manual training\u002Fevaluation loop**: read [`references\u002Finteraction-apis.md`](references\u002Finteraction-apis.md) and run or adapt [`scripts\u002Fact_observe_smoke.py`](scripts\u002Fact_observe_smoke.py).\n- **Diagnose errors**: use [`references\u002Ftroubleshooting.md`](references\u002Ftroubleshooting.md) before changing dependencies or agent specs.\n\n## Key operating rules\n\n1. Prefer `Agent.create(..., environment=environment)` when an environment object is already available; Tensorforce then infers `states`, `actions`, and `max_episode_timesteps` where possible.\n2. If no environment object is available, pass explicit `states`, `actions`, and any required algorithm arguments. The primitive value spec is `dict(type='bool'|'int'|'float', shape=..., num_values=..., min_value=..., max_value=...)`.\n3. For non-independent training, every `agent.act(states=...)` must be followed by exactly one `agent.observe(terminal=..., reward=...)` for the same parallel interaction.\n4. For evaluation, offline recording, or externally collected episodes, call `agent.act(..., independent=True)` and use `agent.initial_internals()` when recurrent\u002Finternal states are present.\n5. Action masks are auxiliary state entries, not part of `states` specs. For a singleton integer action, use `action_mask`; for a named integer action such as `move`, use `move_mask`.\n6. Always close agents and environments you created directly. If `Runner` owns construction\u002Fclosing, route to `..\u002Frunner-and-cli-workflows\u002F`.\n\n## Boundaries\n\nThis sub-skill owns agent creation\u002Floading, algorithm alias selection, state\u002Faction specifications, action masking, and low-level interaction APIs. It intentionally excludes Runner orchestration and CLI workflows, custom environment implementation details, persistence\u002Fexport\u002Frecording depth, and exhaustive module catalogs; use the sibling routes named above for those areas.\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\u002Ftensorforce\u002Fsub-skills\u002Fagents-and-specifications",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 agents-and-specifications",{"tool":40,"command":41},"bunx","bunx skills add VectorSpaceLab\u002FAREX-Skill --skill agents-and-specifications",{"tool":43,"command":44},"pnpm","pnpm dlx skills add VectorSpaceLab\u002FAREX-Skill --skill agents-and-specifications","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Ftensorforce\u002Fsub-skills\u002Fagents-and-specifications\u002FSKILL.md",[47,53,57,61,65,71],{"path":48,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":51,"sourceHtmlUrl":52},"references\u002Fagent-specifications.md","REFERENCE","参考文档",9445,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Ftensorforce\u002Fsub-skills\u002Fagents-and-specifications\u002Freferences\u002Fagent-specifications.md",{"path":54,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":55,"sourceHtmlUrl":56},"references\u002Fapi-reference.md",10550,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Ftensorforce\u002Fsub-skills\u002Fagents-and-specifications\u002Freferences\u002Fapi-reference.md",{"path":58,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":59,"sourceHtmlUrl":60},"references\u002Finteraction-apis.md",7815,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Ftensorforce\u002Fsub-skills\u002Fagents-and-specifications\u002Freferences\u002Finteraction-apis.md",{"path":62,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":63,"sourceHtmlUrl":64},"references\u002Ftroubleshooting.md",9428,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Ftensorforce\u002Fsub-skills\u002Fagents-and-specifications\u002Freferences\u002Ftroubleshooting.md",{"path":66,"resourceType":67,"resourceTypeDesc":68,"sizeBytes":69,"sourceHtmlUrl":70},"scripts\u002Fact_observe_smoke.py","SCRIPT","脚本",7718,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Ftensorforce\u002Fsub-skills\u002Fagents-and-specifications\u002Fscripts\u002Fact_observe_smoke.py",{"path":72,"resourceType":67,"resourceTypeDesc":68,"sizeBytes":73,"sourceHtmlUrl":74},"scripts\u002Faction_masking_smoke.py",3604,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Ftensorforce\u002Fsub-skills\u002Fagents-and-specifications\u002Fscripts\u002Faction_masking_smoke.py",[76,83,90,97,104,111],{"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},"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":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},"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":14,"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":14,"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":14,"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":14,"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",[],[]]