[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M78XP4H03BXAPS2AFW2N5585":3,"skill-same:01M78XP4H03BXAPS2AFW2N5585":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},"01M78XP4H03BXAPS2AFW2N5585","configuration-and-providers",null,"Configure gptme config files, credential storage, provider\u002Fmodel selection, local\u002Fcustom providers, auth helpers, and optional dependency requirements.","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\u002Fgptme\u002Fsub-skills\u002Fconfiguration-and-providers\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: configuration-and-providers\ndescription: \"Configure gptme config files, credential storage, provider\u002Fmodel\n  selection, local\u002Fcustom providers, auth helpers, and optional dependency\n  requirements.\"\ndisable-model-invocation: true\nmetadata:\n  disco-role: operating\nlicense: MIT\n---\n\n# configuration-and-providers\n\nUse this sub-skill when the task is about gptme configuration files, default model selection, provider prefixes, API-key storage, `\u002Faccount` or `gptme-auth`, OpenRouter routing\u002Fprivacy settings, local OpenAI-compatible backends such as Ollama, custom provider entries or provider packages, and optional extras\u002Fsystem dependency planning.\n\nRoute away when the task is mainly about:\n\n- custom tools, plugin tools, hooks, MCP runtime behavior, skills, lessons, browser tools, or computer-use operation: use the tools\u002Fextensibility sub-skill.\n- `gptme-server` auth tokens, CORS, Host validation, REST\u002FSSE, Web UI, TUI, ACP, or deployment: use the server\u002Fprotocols sub-skill.\n- eval model benchmarking, SWE-bench\u002FT-bench, leaderboard generation, or pass-rate gates: use the evals\u002Fbenchmarks sub-skill.\n- maintainer-only changes inside a gptme checkout, test\u002Flint\u002Ftypecheck\u002Fdoc\u002Frelease workflows, or CI policy: use the repo-development sub-skill.\n\n## Read first\n\n- [references\u002Fconfiguration.md](references\u002Fconfiguration.md) for global, local, project, and per-chat config files; merge\u002Fprecedence rules; safe secret placement; model default conflicts; and static config review steps.\n- [references\u002Fproviders-and-models.md](references\u002Fproviders-and-models.md) for provider prefixes, API-key variables, `\u002Faccount`, `gptme-auth`, OpenRouter privacy\u002Frouting, local\u002FOllama setup, custom `[[providers]]`, provider plugins, and extras\u002Fsystem dependencies.\n- [references\u002Ftroubleshooting.md](references\u002Ftroubleshooting.md) for missing key errors, model-prefix mistakes, duplicate TOML keys, local model and summary-model issues, OpenRouter routing\u002Fprivacy failures, OAuth\u002Fbrowser problems, and custom-provider pitfalls.\n\n## Safe helpers\n\n- [scripts\u002Fvalidate_gptme_config.py](scripts\u002Fvalidate_gptme_config.py) statically checks TOML config\u002Fenv\u002Fprovider setup without API calls and without printing secret values.\n- [scripts\u002Fexplain_model_selection.py](scripts\u002Fexplain_model_selection.py) explains which model would win from supplied CLI, chat, config, and environment inputs without importing gptme or making network calls.\n\nExample static passes:\n\n```sh\npython scripts\u002Fvalidate_gptme_config.py --help\npython scripts\u002Fexplain_model_selection.py --help\npython scripts\u002Fexplain_model_selection.py \\\n  --models-default anthropic\u002Fclaude-sonnet-4-6 \\\n  --model-env openai\u002Fgpt-5 \\\n  --api-key-env ANTHROPIC_API_KEY\n```\n\n## Fast operating checklist\n\n1. Identify the scope: user-global config, project `gptme.toml`, an existing chat log config, credentials\u002Fauth, or provider\u002Fmodel routing.\n2. If both `[models].default` and `MODEL` are set, prefer `[models].default` for the default chat model and treat the differing `MODEL` value as a conflict to explain.\n3. Keep secrets out of committable config. Put provider keys in `config.local.toml`, `gptme.local.toml`, the credential store, or shell environment; never print the raw values.\n4. Require provider-prefixed models for unambiguous selection: `anthropic\u002F...`, `openai\u002F...`, `openrouter\u002F...`, `local\u002F...`, `gptme\u002F...`, or a configured custom provider prefix.\n5. For local Ollama\u002FOpenAI-compatible backends, pair `local\u002F\u003Cexact-model-tag>` with `OPENAI_BASE_URL` and do not expect `OPENAI_BASE_URL` to affect non-local providers.\n6. Prefer static checks and help commands (`gptme-auth --help`, `gptme-doctor --help`) before launching browsers, making model calls, testing custom provider connectivity, or running checkout-maintainer tests.\n","# configuration-and-providers\n\nUse this sub-skill when the task is about gptme configuration files, default model selection, provider prefixes, API-key storage, `\u002Faccount` or `gptme-auth`, OpenRouter routing\u002Fprivacy settings, local OpenAI-compatible backends such as Ollama, custom provider entries or provider packages, and optional extras\u002Fsystem dependency planning.\n\nRoute away when the task is mainly about:\n\n- custom tools, plugin tools, hooks, MCP runtime behavior, skills, lessons, browser tools, or computer-use operation: use the tools\u002Fextensibility sub-skill.\n- `gptme-server` auth tokens, CORS, Host validation, REST\u002FSSE, Web UI, TUI, ACP, or deployment: use the server\u002Fprotocols sub-skill.\n- eval model benchmarking, SWE-bench\u002FT-bench, leaderboard generation, or pass-rate gates: use the evals\u002Fbenchmarks sub-skill.\n- maintainer-only changes inside a gptme checkout, test\u002Flint\u002Ftypecheck\u002Fdoc\u002Frelease workflows, or CI policy: use the repo-development sub-skill.\n\n## Read first\n\n- [references\u002Fconfiguration.md](references\u002Fconfiguration.md) for global, local, project, and per-chat config files; merge\u002Fprecedence rules; safe secret placement; model default conflicts; and static config review steps.\n- [references\u002Fproviders-and-models.md](references\u002Fproviders-and-models.md) for provider prefixes, API-key variables, `\u002Faccount`, `gptme-auth`, OpenRouter privacy\u002Frouting, local\u002FOllama setup, custom `[[providers]]`, provider plugins, and extras\u002Fsystem dependencies.\n- [references\u002Ftroubleshooting.md](references\u002Ftroubleshooting.md) for missing key errors, model-prefix mistakes, duplicate TOML keys, local model and summary-model issues, OpenRouter routing\u002Fprivacy failures, OAuth\u002Fbrowser problems, and custom-provider pitfalls.\n\n## Safe helpers\n\n- [scripts\u002Fvalidate_gptme_config.py](scripts\u002Fvalidate_gptme_config.py) statically checks TOML config\u002Fenv\u002Fprovider setup without API calls and without printing secret values.\n- [scripts\u002Fexplain_model_selection.py](scripts\u002Fexplain_model_selection.py) explains which model would win from supplied CLI, chat, config, and environment inputs without importing gptme or making network calls.\n\nExample static passes:\n\n```sh\npython scripts\u002Fvalidate_gptme_config.py --help\npython scripts\u002Fexplain_model_selection.py --help\npython scripts\u002Fexplain_model_selection.py \\\n  --models-default anthropic\u002Fclaude-sonnet-4-6 \\\n  --model-env openai\u002Fgpt-5 \\\n  --api-key-env ANTHROPIC_API_KEY\n```\n\n## Fast operating checklist\n\n1. Identify the scope: user-global config, project `gptme.toml`, an existing chat log config, credentials\u002Fauth, or provider\u002Fmodel routing.\n2. If both `[models].default` and `MODEL` are set, prefer `[models].default` for the default chat model and treat the differing `MODEL` value as a conflict to explain.\n3. Keep secrets out of committable config. Put provider keys in `config.local.toml`, `gptme.local.toml`, the credential store, or shell environment; never print the raw values.\n4. Require provider-prefixed models for unambiguous selection: `anthropic\u002F...`, `openai\u002F...`, `openrouter\u002F...`, `local\u002F...`, `gptme\u002F...`, or a configured custom provider prefix.\n5. For local Ollama\u002FOpenAI-compatible backends, pair `local\u002F\u003Cexact-model-tag>` with `OPENAI_BASE_URL` and do not expect `OPENAI_BASE_URL` to affect non-local providers.\n6. Prefer static checks and help commands (`gptme-auth --help`, `gptme-doctor --help`) before launching browsers, making model calls, testing custom provider connectivity, or running checkout-maintainer tests.\n",{"name":5,"license":14,"metadata":23,"description":7,"disable-model-invocation":25},{"disco-role":24},"operating",true,"main","ac3fe1afa80fb9a09775ecfb2b6cc3ba850a2db6","skills\u002Frepositories\u002Frepo-skills\u002Fgptme\u002Fsub-skills\u002Fconfiguration-and-providers",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 configuration-and-providers",{"tool":39,"command":40},"bunx","bunx skills add VectorSpaceLab\u002FAREX-Skill --skill configuration-and-providers",{"tool":42,"command":43},"pnpm","pnpm dlx skills add VectorSpaceLab\u002FAREX-Skill --skill configuration-and-providers","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fgptme\u002Fsub-skills\u002Fconfiguration-and-providers\u002FSKILL.md",[46,52,56,60,66],{"path":47,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":50,"sourceHtmlUrl":51},"references\u002Fconfiguration.md","REFERENCE","参考文档",9474,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fgptme\u002Fsub-skills\u002Fconfiguration-and-providers\u002Freferences\u002Fconfiguration.md",{"path":53,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":54,"sourceHtmlUrl":55},"references\u002Fproviders-and-models.md",13875,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fgptme\u002Fsub-skills\u002Fconfiguration-and-providers\u002Freferences\u002Fproviders-and-models.md",{"path":57,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":58,"sourceHtmlUrl":59},"references\u002Ftroubleshooting.md",10504,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fgptme\u002Fsub-skills\u002Fconfiguration-and-providers\u002Freferences\u002Ftroubleshooting.md",{"path":61,"resourceType":62,"resourceTypeDesc":63,"sizeBytes":64,"sourceHtmlUrl":65},"scripts\u002Fexplain_model_selection.py","SCRIPT","脚本",15915,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fgptme\u002Fsub-skills\u002Fconfiguration-and-providers\u002Fscripts\u002Fexplain_model_selection.py",{"path":67,"resourceType":62,"resourceTypeDesc":63,"sizeBytes":68,"sourceHtmlUrl":69},"scripts\u002Fvalidate_gptme_config.py",26593,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fgptme\u002Fsub-skills\u002Fconfiguration-and-providers\u002Fscripts\u002Fvalidate_gptme_config.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",[],[]]