[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M79085DACD3029DN69FZBX46":3,"skill-same:01M79085DACD3029DN69FZBX46":66},{"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},"01M79085DACD3029DN69FZBX46","software-company",null,"Use MetaGPT's core virtual software-company workflow from CLI or Python, including project generation, incremental updates, recovery, config initialization, and custom Role\u002FAction\u002FTeam patterns.","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\u002Fsub-skills\u002Fsoftware-company\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: software-company\ndescription: \"Use MetaGPT's core virtual software-company workflow from CLI or\n  Python, including project generation, incremental updates, recovery, config\n  initialization, and custom Role\u002FAction\u002FTeam patterns.\"\ndisable-model-invocation: true\nmetadata:\n  disco-role: operating\nlicense: MIT\n---\n\n# Software Company\n\nUse this sub-skill when a user asks how to run MetaGPT as a virtual software company, generate a project from a one-line idea, continue an existing project, recover a serialized team, initialize configuration, choose CLI options, or build a small custom `Action`\u002F`Role`\u002F`Team` workflow.\n\n## Quick Routing\n\n| User intent | Use this sub-skill for | Key reference |\n| --- | --- | --- |\n| \"Generate a 2048 game\" or \"build a repo from this idea\" | `metagpt` CLI and `metagpt.software_company.generate_repo` project generation | [CLI and Python recipes](references\u002Fworkflows.md#cli-project-generation) |\n| \"Explain MetaGPT CLI options\" | Option names, defaults, boolean spelling, and safe dry checks | [CLI option guide](references\u002Fapi-reference.md#cli-entry-point) |\n| \"Configure OpenAI\u002FClaude\u002FOllama\" | `config2.yaml` initialization, precedence, provider fields, and placeholder-key diagnosis | [Configuration workflow](references\u002Fworkflows.md#configuration-workflow) |\n| \"Continue this project\" | `--inc`, `--project-name`, `--project-path`, and QA rewrite inputs | [Incremental updates](references\u002Fworkflows.md#incremental-project-updates) |\n| \"Recover a previous run\" | `--recover-path` \u002F `recover_path` validation and serialized `team` storage | [Recovery workflow](references\u002Fworkflows.md#serialized-team-recovery) |\n| \"Build a custom agent\u002Fteam\" | Safe `Action`, `Role`, `RoleReactMode`, `Message`, and `Team` patterns | [Custom roles and teams](references\u002Fworkflows.md#custom-action-role-and-team-patterns) |\n\n## Before Running LLM Workflows\n\n- Confirm Python is `>=3.9,\u003C3.12`; Python 3.9 or 3.10 is the safest choice, and use the root MetaGPT installation\u002Fconfig guidance when present.\n- Confirm `metagpt --help` works before any project-generation command.\n- Initialize config with `metagpt --init-config`, then replace placeholder secrets in `~\u002F.metagpt\u002Fconfig2.yaml`; do not paste API keys into chat or generated files.\n- Treat `metagpt \"Create a 2048 game\"`, `generate_repo(...)`, `Team.run(...)`, debate examples, and custom roles that call `_aask(...)` as LLM-spending workflows requiring working provider config.\n- Use `scripts\u002Finspect_role_action.py --check-cli-help --json` for safe no-network inspection of installed APIs and CLI availability, then use root troubleshooting guidance for cross-cutting provider\u002Fconfig failures when present.\n\n## Runtime References\n\n- [Workflows](references\u002Fworkflows.md): CLI\u002FPython recipes, output layout, config, incremental\u002Frecovery usage, custom agent patterns, and safe validation.\n- [API Reference](references\u002Fapi-reference.md): important signatures, classes, parameters, defaults, and behavior notes.\n- [Troubleshooting](references\u002Ftroubleshooting.md): config placeholders, provider failures, dependency issues, Mermaid\u002Fbrowser problems, Typer\u002Fclick help, `--inc`, `recover_path`, and long outputs.\n\n## Boundaries\n\n- For Data Interpreter roles, `DataAnalyst`\u002FDI-generated project workflows, and notebook-style data analysis, route to the [`data-interpreter`](..\u002Fdata-interpreter\u002FSKILL.md) sub-skill.\n- For RAG, search, browser, tool registry, or retrieval internals, route to the [`rag-and-tools`](..\u002Frag-and-tools\u002FSKILL.md) sub-skill.\n- For AFlow, SPO, game examples beyond the core workflow, Android assistants, and environment extensions, route to `extensions-and-environments` when that sub-skill is present.\n- For serialization internals, experiment pools, repository parser internals, and maintainer APIs, route to `maintainer-apis` when that sub-skill is present.\n","# Software Company\n\nUse this sub-skill when a user asks how to run MetaGPT as a virtual software company, generate a project from a one-line idea, continue an existing project, recover a serialized team, initialize configuration, choose CLI options, or build a small custom `Action`\u002F`Role`\u002F`Team` workflow.\n\n## Quick Routing\n\n| User intent | Use this sub-skill for | Key reference |\n| --- | --- | --- |\n| \"Generate a 2048 game\" or \"build a repo from this idea\" | `metagpt` CLI and `metagpt.software_company.generate_repo` project generation | [CLI and Python recipes](references\u002Fworkflows.md#cli-project-generation) |\n| \"Explain MetaGPT CLI options\" | Option names, defaults, boolean spelling, and safe dry checks | [CLI option guide](references\u002Fapi-reference.md#cli-entry-point) |\n| \"Configure OpenAI\u002FClaude\u002FOllama\" | `config2.yaml` initialization, precedence, provider fields, and placeholder-key diagnosis | [Configuration workflow](references\u002Fworkflows.md#configuration-workflow) |\n| \"Continue this project\" | `--inc`, `--project-name`, `--project-path`, and QA rewrite inputs | [Incremental updates](references\u002Fworkflows.md#incremental-project-updates) |\n| \"Recover a previous run\" | `--recover-path` \u002F `recover_path` validation and serialized `team` storage | [Recovery workflow](references\u002Fworkflows.md#serialized-team-recovery) |\n| \"Build a custom agent\u002Fteam\" | Safe `Action`, `Role`, `RoleReactMode`, `Message`, and `Team` patterns | [Custom roles and teams](references\u002Fworkflows.md#custom-action-role-and-team-patterns) |\n\n## Before Running LLM Workflows\n\n- Confirm Python is `>=3.9,\u003C3.12`; Python 3.9 or 3.10 is the safest choice, and use the root MetaGPT installation\u002Fconfig guidance when present.\n- Confirm `metagpt --help` works before any project-generation command.\n- Initialize config with `metagpt --init-config`, then replace placeholder secrets in `~\u002F.metagpt\u002Fconfig2.yaml`; do not paste API keys into chat or generated files.\n- Treat `metagpt \"Create a 2048 game\"`, `generate_repo(...)`, `Team.run(...)`, debate examples, and custom roles that call `_aask(...)` as LLM-spending workflows requiring working provider config.\n- Use `scripts\u002Finspect_role_action.py --check-cli-help --json` for safe no-network inspection of installed APIs and CLI availability, then use root troubleshooting guidance for cross-cutting provider\u002Fconfig failures when present.\n\n## Runtime References\n\n- [Workflows](references\u002Fworkflows.md): CLI\u002FPython recipes, output layout, config, incremental\u002Frecovery usage, custom agent patterns, and safe validation.\n- [API Reference](references\u002Fapi-reference.md): important signatures, classes, parameters, defaults, and behavior notes.\n- [Troubleshooting](references\u002Ftroubleshooting.md): config placeholders, provider failures, dependency issues, Mermaid\u002Fbrowser problems, Typer\u002Fclick help, `--inc`, `recover_path`, and long outputs.\n\n## Boundaries\n\n- For Data Interpreter roles, `DataAnalyst`\u002FDI-generated project workflows, and notebook-style data analysis, route to the [`data-interpreter`](..\u002Fdata-interpreter\u002FSKILL.md) sub-skill.\n- For RAG, search, browser, tool registry, or retrieval internals, route to the [`rag-and-tools`](..\u002Frag-and-tools\u002FSKILL.md) sub-skill.\n- For AFlow, SPO, game examples beyond the core workflow, Android assistants, and environment extensions, route to `extensions-and-environments` when that sub-skill is present.\n- For serialization internals, experiment pools, repository parser internals, and maintainer APIs, route to `maintainer-apis` when that sub-skill is present.\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\u002Fsub-skills\u002Fsoftware-company",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 software-company",{"tool":39,"command":40},"bunx","bunx skills add VectorSpaceLab\u002FAREX-Skill --skill software-company",{"tool":42,"command":43},"pnpm","pnpm dlx skills add VectorSpaceLab\u002FAREX-Skill --skill software-company","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fmeta-gpt\u002Fsub-skills\u002Fsoftware-company\u002FSKILL.md",[46,52,56,60],{"path":47,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":50,"sourceHtmlUrl":51},"references\u002Fapi-reference.md","REFERENCE","参考文档",8325,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fmeta-gpt\u002Fsub-skills\u002Fsoftware-company\u002Freferences\u002Fapi-reference.md",{"path":53,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":54,"sourceHtmlUrl":55},"references\u002Ftroubleshooting.md",7630,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fmeta-gpt\u002Fsub-skills\u002Fsoftware-company\u002Freferences\u002Ftroubleshooting.md",{"path":57,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":58,"sourceHtmlUrl":59},"references\u002Fworkflows.md",9223,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fmeta-gpt\u002Fsub-skills\u002Fsoftware-company\u002Freferences\u002Fworkflows.md",{"path":61,"resourceType":62,"resourceTypeDesc":63,"sizeBytes":64,"sourceHtmlUrl":65},"scripts\u002Finspect_role_action.py","SCRIPT","脚本",12271,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fmeta-gpt\u002Fsub-skills\u002Fsoftware-company\u002Fscripts\u002Finspect_role_action.py",[67,75,82,89,96,103],{"skillNo":68,"name":69,"nameZh":6,"description":70,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":71,"licenseFileUrl":6,"sourceHtmlUrl":72,"categories":73,"keywords":74,"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":76,"name":77,"nameZh":6,"description":78,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":71,"licenseFileUrl":6,"sourceHtmlUrl":79,"categories":80,"keywords":81,"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":83,"name":84,"nameZh":6,"description":85,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":71,"licenseFileUrl":6,"sourceHtmlUrl":86,"categories":87,"keywords":88,"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":90,"name":91,"nameZh":6,"description":92,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":71,"licenseFileUrl":6,"sourceHtmlUrl":93,"categories":94,"keywords":95,"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":97,"name":98,"nameZh":6,"description":99,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":71,"licenseFileUrl":6,"sourceHtmlUrl":100,"categories":101,"keywords":102,"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":104,"name":105,"nameZh":6,"description":106,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":71,"licenseFileUrl":6,"sourceHtmlUrl":107,"categories":108,"keywords":109,"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",[],[]]