[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7907P57THHAT21CVYQE3DFM":3,"skill-same:01M7907P57THHAT21CVYQE3DFM":70},{"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},"01M7907P57THHAT21CVYQE3DFM","meta-gpt",null,"Use MetaGPT for multi-agent software-company workflows, Data Interpreter tasks, RAG\u002Ftools, extensions\u002Fenvironments, and repository maintenance.","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\u002Fmeta-gpt\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: meta-gpt\ndescription: \"Use MetaGPT for multi-agent software-company workflows, Data\n  Interpreter tasks, RAG\u002Ftools, extensions\u002Fenvironments, and repository\n  maintenance.\"\ndisable-model-invocation: true\nmetadata:\n  disco-role: operating\nlicense: MIT\n---\n\n# MetaGPT\n\nUse this repo skill when the user asks about MetaGPT, the `metagpt` Python package, the `metagpt` CLI, multi-agent software-company generation, Data Interpreter, RoleZero agents, MetaGPT RAG\u002Ftools, AFlow\u002FSPO\u002Fextension environments, or maintaining MetaGPT internals.\n\n## Start Here\n\n1. Read [installation-and-configuration.md](references\u002Finstallation-and-configuration.md) before running MetaGPT, changing providers, diagnosing config, or selecting optional dependencies.\n2. Run [scripts\u002Fcheck_metagpt_environment.py](scripts\u002Fcheck_metagpt_environment.py) for safe import\u002Fconfig\u002FCLI diagnostics that do not call an LLM or write a project.\n3. Read [troubleshooting.md](references\u002Ftroubleshooting.md) when imports, config validation, provider calls, optional dependencies, browser\u002FMermaid, or CLI commands fail.\n4. Read [repo-provenance.md](references\u002Frepo-provenance.md) before deciding whether this skill is current for a MetaGPT checkout.\n\n## Route By Task\n\n| User task | Read |\n| --- | --- |\n| Generate a project from a one-line idea, use `metagpt` CLI options, initialize config, continue an existing project, recover a team, or build custom `Action`\u002F`Role`\u002F`Team` workflows | [software-company](sub-skills\u002Fsoftware-company\u002FSKILL.md) |\n| Use Data Interpreter, RoleZero, DataAnalyst, SWEAgent, notebook\u002Fcode execution, DI benchmark prompts, or tool-assisted data tasks | [data-interpreter](sub-skills\u002Fdata-interpreter\u002FSKILL.md) |\n| Build or debug RAG pipelines, document stores, retrievers\u002Frankers, search\u002Fbrowser\u002Fdata\u002Feditor tools, tool registry, or optional RAG dependencies | [rag-and-tools](sub-skills\u002Frag-and-tools\u002FSKILL.md) |\n| Use AFlow, SPO, Android Assistant, Stanford Town, werewolf\u002FMinecraft\u002FAPI environments, CR\u002FSELA, or other extension integrations | [extensions-and-environments](sub-skills\u002Fextensions-and-environments\u002FSKILL.md) |\n| Maintain serialization, memory, experience pools, skill management, repo parsing, config models, focused tests, or public symbol inventories | [maintainer-apis](sub-skills\u002Fmaintainer-apis\u002FSKILL.md) |\n\n## Install Baseline\n\nMetaGPT is packaged as `metagpt==1.0.0` and declares Python `>=3.9,\u003C3.12`. Prefer Python 3.9 or 3.10 for production-style use when following the project docs; Python 3.11 is useful for inspection but some dependencies can be slow or version-sensitive.\n\n```bash\npython -m pip install metagpt\n# or, for a local checkout\npython -m pip install -e .\nmetagpt --help\n```\n\nBefore any workflow that calls an LLM, create or fix `~\u002F.metagpt\u002Fconfig2.yaml` and replace placeholder API keys. `~\u002F.metagpt\u002Fconfig2.yaml` has higher precedence than a checkout-local `config\u002Fconfig2.yaml`.\n\n## Safe Validation\n\nUse safe checks before expensive runs:\n\n```bash\npython scripts\u002Fcheck_metagpt_environment.py --json\nmetagpt --help\n```\n\nDo not use project generation, Data Interpreter, AFlow\u002FSPO optimization, external environment simulations, browser automation, email automation, or RAG indexing as smoke tests unless the user has explicitly provided credentials, data, services, and cost approval.\n\n## Capability Map\n\n- **Software-company generation:** `metagpt \"Create a 2048 game\"`, `metagpt.software_company.generate_repo(...)`, incremental `--inc` mode, team recovery, custom roles\u002Factions.\n- **Data Interpreter:** planning, generated-code execution, data analysis, benchmark prompts, RoleZero-family roles, browser\u002FOCR\u002Femail\u002FStable Diffusion examples behind explicit prerequisites.\n- **RAG and tools:** document stores, retrievers\u002Frankers, RAG factories, search providers, browser engines, tool registry\u002Frecommendation, optional dependency diagnostics.\n- **Extensions\u002Fenvironments:** AFlow and SPO optimizers, Android Assistant, Stanford Town, werewolf, Minecraft\u002FAPI\u002Fsoftware environments, CR\u002FSELA experiments.\n- **Maintainer APIs:** serialization\u002Fdeserialization, memory storage, experience pools, skill management, repo parser, config models, focused pytest selection.\n\n## Common Decisions\n\n- If a task is about using MetaGPT as a package or CLI, route to `software-company` unless Data Interpreter, RAG\u002Ftools, or extensions are named.\n- If a task names a missing optional package, vector store, browser, Android device, dataset, or external service, route to the owning sub-skill and root troubleshooting before installing broad extras.\n- If a task edits MetaGPT source code, route to `maintainer-apis` for focused tests and internals, then cross-link to the user-facing sub-skill that owns the affected workflow.\n- If a run would call an LLM, spend tokens, send data to a provider, browse the web, reply to email, download datasets, or run a simulation, ask for explicit credentials\u002Fsafety confirmation first.\n","# MetaGPT\n\nUse this repo skill when the user asks about MetaGPT, the `metagpt` Python package, the `metagpt` CLI, multi-agent software-company generation, Data Interpreter, RoleZero agents, MetaGPT RAG\u002Ftools, AFlow\u002FSPO\u002Fextension environments, or maintaining MetaGPT internals.\n\n## Start Here\n\n1. Read [installation-and-configuration.md](references\u002Finstallation-and-configuration.md) before running MetaGPT, changing providers, diagnosing config, or selecting optional dependencies.\n2. Run [scripts\u002Fcheck_metagpt_environment.py](scripts\u002Fcheck_metagpt_environment.py) for safe import\u002Fconfig\u002FCLI diagnostics that do not call an LLM or write a project.\n3. Read [troubleshooting.md](references\u002Ftroubleshooting.md) when imports, config validation, provider calls, optional dependencies, browser\u002FMermaid, or CLI commands fail.\n4. Read [repo-provenance.md](references\u002Frepo-provenance.md) before deciding whether this skill is current for a MetaGPT checkout.\n\n## Route By Task\n\n| User task | Read |\n| --- | --- |\n| Generate a project from a one-line idea, use `metagpt` CLI options, initialize config, continue an existing project, recover a team, or build custom `Action`\u002F`Role`\u002F`Team` workflows | [software-company](sub-skills\u002Fsoftware-company\u002FSKILL.md) |\n| Use Data Interpreter, RoleZero, DataAnalyst, SWEAgent, notebook\u002Fcode execution, DI benchmark prompts, or tool-assisted data tasks | [data-interpreter](sub-skills\u002Fdata-interpreter\u002FSKILL.md) |\n| Build or debug RAG pipelines, document stores, retrievers\u002Frankers, search\u002Fbrowser\u002Fdata\u002Feditor tools, tool registry, or optional RAG dependencies | [rag-and-tools](sub-skills\u002Frag-and-tools\u002FSKILL.md) |\n| Use AFlow, SPO, Android Assistant, Stanford Town, werewolf\u002FMinecraft\u002FAPI environments, CR\u002FSELA, or other extension integrations | [extensions-and-environments](sub-skills\u002Fextensions-and-environments\u002FSKILL.md) |\n| Maintain serialization, memory, experience pools, skill management, repo parsing, config models, focused tests, or public symbol inventories | [maintainer-apis](sub-skills\u002Fmaintainer-apis\u002FSKILL.md) |\n\n## Install Baseline\n\nMetaGPT is packaged as `metagpt==1.0.0` and declares Python `>=3.9,\u003C3.12`. Prefer Python 3.9 or 3.10 for production-style use when following the project docs; Python 3.11 is useful for inspection but some dependencies can be slow or version-sensitive.\n\n```bash\npython -m pip install metagpt\n# or, for a local checkout\npython -m pip install -e .\nmetagpt --help\n```\n\nBefore any workflow that calls an LLM, create or fix `~\u002F.metagpt\u002Fconfig2.yaml` and replace placeholder API keys. `~\u002F.metagpt\u002Fconfig2.yaml` has higher precedence than a checkout-local `config\u002Fconfig2.yaml`.\n\n## Safe Validation\n\nUse safe checks before expensive runs:\n\n```bash\npython scripts\u002Fcheck_metagpt_environment.py --json\nmetagpt --help\n```\n\nDo not use project generation, Data Interpreter, AFlow\u002FSPO optimization, external environment simulations, browser automation, email automation, or RAG indexing as smoke tests unless the user has explicitly provided credentials, data, services, and cost approval.\n\n## Capability Map\n\n- **Software-company generation:** `metagpt \"Create a 2048 game\"`, `metagpt.software_company.generate_repo(...)`, incremental `--inc` mode, team recovery, custom roles\u002Factions.\n- **Data Interpreter:** planning, generated-code execution, data analysis, benchmark prompts, RoleZero-family roles, browser\u002FOCR\u002Femail\u002FStable Diffusion examples behind explicit prerequisites.\n- **RAG and tools:** document stores, retrievers\u002Frankers, RAG factories, search providers, browser engines, tool registry\u002Frecommendation, optional dependency diagnostics.\n- **Extensions\u002Fenvironments:** AFlow and SPO optimizers, Android Assistant, Stanford Town, werewolf, Minecraft\u002FAPI\u002Fsoftware environments, CR\u002FSELA experiments.\n- **Maintainer APIs:** serialization\u002Fdeserialization, memory storage, experience pools, skill management, repo parser, config models, focused pytest selection.\n\n## Common Decisions\n\n- If a task is about using MetaGPT as a package or CLI, route to `software-company` unless Data Interpreter, RAG\u002Ftools, or extensions are named.\n- If a task names a missing optional package, vector store, browser, Android device, dataset, or external service, route to the owning sub-skill and root troubleshooting before installing broad extras.\n- If a task edits MetaGPT source code, route to `maintainer-apis` for focused tests and internals, then cross-link to the user-facing sub-skill that owns the affected workflow.\n- If a run would call an LLM, spend tokens, send data to a provider, browse the web, reply to email, download datasets, or run a simulation, ask for explicit credentials\u002Fsafety confirmation first.\n",{"name":5,"license":14,"metadata":23,"description":7,"disable-model-invocation":25},{"disco-role":24},"operating",true,"main","ac3fe1afa80fb9a09775ecfb2b6cc3ba850a2db6","skills\u002Frepositories\u002Frepo-skills\u002Fmeta-gpt",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 meta-gpt",{"tool":39,"command":40},"bunx","bunx skills add VectorSpaceLab\u002FAREX-Skill --skill meta-gpt",{"tool":42,"command":43},"pnpm","pnpm dlx skills add VectorSpaceLab\u002FAREX-Skill --skill meta-gpt","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fmeta-gpt\u002FSKILL.md",[46,52,56,60,64],{"path":47,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":50,"sourceHtmlUrl":51},"references\u002Finstallation-and-configuration.md","REFERENCE","参考文档",4328,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fmeta-gpt\u002Freferences\u002Finstallation-and-configuration.md",{"path":53,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":54,"sourceHtmlUrl":55},"references\u002Frepo-provenance.md",2323,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fmeta-gpt\u002Freferences\u002Frepo-provenance.md",{"path":57,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":58,"sourceHtmlUrl":59},"references\u002Frepo-routing-metadata.json",491,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fmeta-gpt\u002Freferences\u002Frepo-routing-metadata.json",{"path":61,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":62,"sourceHtmlUrl":63},"references\u002Ftroubleshooting.md",4549,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fmeta-gpt\u002Freferences\u002Ftroubleshooting.md",{"path":65,"resourceType":66,"resourceTypeDesc":67,"sizeBytes":68,"sourceHtmlUrl":69},"scripts\u002Fcheck_metagpt_environment.py","SCRIPT","脚本",5890,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fmeta-gpt\u002Fscripts\u002Fcheck_metagpt_environment.py",[71,79,86,93,100,107],{"skillNo":72,"name":73,"nameZh":6,"description":74,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":75,"licenseFileUrl":6,"sourceHtmlUrl":76,"categories":77,"keywords":78,"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":80,"name":81,"nameZh":6,"description":82,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":75,"licenseFileUrl":6,"sourceHtmlUrl":83,"categories":84,"keywords":85,"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":87,"name":88,"nameZh":6,"description":89,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":75,"licenseFileUrl":6,"sourceHtmlUrl":90,"categories":91,"keywords":92,"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":94,"name":95,"nameZh":6,"description":96,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":75,"licenseFileUrl":6,"sourceHtmlUrl":97,"categories":98,"keywords":99,"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":101,"name":102,"nameZh":6,"description":103,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":75,"licenseFileUrl":6,"sourceHtmlUrl":104,"categories":105,"keywords":106,"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":108,"name":109,"nameZh":6,"description":110,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":75,"licenseFileUrl":6,"sourceHtmlUrl":111,"categories":112,"keywords":113,"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",[],[]]