[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M698T4860A55PX5MFZ6G9KQH":3,"skill-same:01M698T4860A55PX5MFZ6G9KQH":57},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":9,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":15,"categories":16,"keywords":17,"publishedAt":29,"linkOnly":30,"markdownContent":31,"markdownBody":32,"frontMatter":33,"refName":34,"commitSha":35,"skillDirectory":36,"forksCount":37,"repositoryHtmlUrl":38,"repositoryHomepageUrl":39,"ownerHtmlUrl":40,"ownerBlogUrl":39,"ownerDescription":41,"updatedAt":42,"install":43,"resources":56},"01M698T4860A55PX5MFZ6G9KQH","add-model-provider",null,"Add and live-prove a model provider with non-interactive config one-liners, without exposing credentials.","openclaw\u002Fopenclaw","openclaw","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F252820863?v=4","01M698P3FSAZ6B4R928ZF19KPT","01M698PDMDRVH56MV30D253NFP",394406,"MIT","https:\u002F\u002Fgithub.com\u002Fopenclaw\u002Fopenclaw\u002Fblob\u002Fmain\u002Fcustodian-skills\u002Fadd-model-provider\u002FSKILL.md",[],[18,19,20,21,22,23,24,25,26,27,28],"add model provider","model","provider","add","add model","config","credentials","interactive","live","with","prove","2026-11-10 10:12:30",false,"---\nname: add-model-provider\ndescription: Add and live-prove a model provider with non-interactive config one-liners, without exposing credentials.\n---\n\n# Add a model provider\n\nNever print or persist secret values; credentials enter config only as SecretRefs (env or file source). Never hand-edit config files on disk — every mutation goes through `openclaw config` so it is validated and audited. Every run ends with the observable Prove result or an exact explanation of why it could not be proven.\n\nIn-session `config_set`\u002F`config_set_ref` tool actions are policy-blocked for `models.*` and `secrets.*`; use the trusted shell (`exec`) for the commands below. `set_default_model` is the one in-session action allowed to change the default route — it live-tests before saving.\n\n## Gather\n\n```\nopenclaw config get models --json          # \"Config path not found\" is normal before first setup\nopenclaw models list --agent \u003CagentId>     # --agent is required in multi-agent rosters\nopenclaw models auth list --agent \u003CagentId>\nopenclaw config schema --json | jq '.properties.models'   # confirm exact provider paths before writing\nopenclaw plugins list   # OpenAI routes need the codex harness plugin; enable\u002Finstall NOW, not mid-proof\n```\n\nIf the harness plugin for the target provider is missing or disabled, remediate here (`openclaw plugins enable codex` or `openclaw plugins install @openclaw\u002Fcodex`) so the Prove step does not stall on it later; plugin enable is picked up by gateway hot-reload.\n\nDecide the auth contract: API-key providers take a SecretRef on `models.providers.\u003Cid>.apiKey`; subscription\u002FOAuth providers (ChatGPT\u002FCodex, Claude subscriptions) use `openclaw models auth login --provider \u003Cid>` instead and must not be given an API key path.\n\n## Mutate\n\nAPI-key example (OpenAI), key staged by the operator in a `0600` file — validate first with `--dry-run`, then write:\n\n```\nopenclaw config set secrets.providers.openai_key_file --provider-source file --provider-path \u002Fpath\u002Fto\u002Fopenai.key --provider-mode singleValue --dry-run\nopenclaw config set secrets.providers.openai_key_file --provider-source file --provider-path \u002Fpath\u002Fto\u002Fopenai.key --provider-mode singleValue\nopenclaw config set models.providers.openai.apiKey --ref-provider openai_key_file --ref-source file --ref-id value\n```\n\nEnv-var alternative when the gateway process env carries the key:\n\n```\nopenclaw config set models.providers.openai.apiKey --ref-provider default --ref-source env --ref-id OPENAI_API_KEY\n```\n\nTo change a default model, use the in-session `set_default_model` action (with `agentId` for a non-default agent); it live-tests the route before saving. Do not change defaults with raw config writes.\n\n## Repair\n\n```\nopenclaw doctor --lint\n```\n\n`doctor --lint` can exit `1` for findings: read the report and continue the remaining checks. Ordinary `doctor` and `doctor --non-interactive` can write config\u002Fstate; do not use them for diagnosis before approval. If a repair is needed, get explicit approval, run `openclaw doctor --fix --non-interactive`, then re-run the Gather reads.\n\n## Prove\n\nRoster-safe test (works in every setup; use your own agent id or any configured agent):\n\n```\nopenclaw agent --agent \u003CagentId> --model openai\u002Fgpt-5.4 -m \"Reply with exactly: PROVIDER-PROOF-OK\"\n```\n\nSingle-agent installs can use the lighter completion test instead — it has no `--agent` flag and fails with \"no explicit owner\" on multi-agent rosters, so do not retry it there:\n\n```\nopenclaw infer model run --gateway --model openai\u002Fgpt-5.4 --prompt \"Reply with exactly: PROVIDER-PROOF-OK\"\n```\n\nExpect the exact requested reply; record model id and wall time. Known dependency: OpenAI routes need the codex harness plugin at runtime — if the test reports the runtime unavailable, run `openclaw plugins install @openclaw\u002Fcodex` and restart the gateway, then test again.\n\n## Report\n\nState the provider added, the SecretRef path written (never the value), the test result with model id and latency, and whether the default model changed. If the test failed, report the exact error and the next command to try.\n\nFurther reference: https:\u002F\u002Fdocs.openclaw.ai\u002Fproviders\u002Fmodels and https:\u002F\u002Fdocs.openclaw.ai\u002Fproviders\u002Fopenai\n","# Add a model provider\n\nNever print or persist secret values; credentials enter config only as SecretRefs (env or file source). Never hand-edit config files on disk — every mutation goes through `openclaw config` so it is validated and audited. Every run ends with the observable Prove result or an exact explanation of why it could not be proven.\n\nIn-session `config_set`\u002F`config_set_ref` tool actions are policy-blocked for `models.*` and `secrets.*`; use the trusted shell (`exec`) for the commands below. `set_default_model` is the one in-session action allowed to change the default route — it live-tests before saving.\n\n## Gather\n\n```\nopenclaw config get models --json          # \"Config path not found\" is normal before first setup\nopenclaw models list --agent \u003CagentId>     # --agent is required in multi-agent rosters\nopenclaw models auth list --agent \u003CagentId>\nopenclaw config schema --json | jq '.properties.models'   # confirm exact provider paths before writing\nopenclaw plugins list   # OpenAI routes need the codex harness plugin; enable\u002Finstall NOW, not mid-proof\n```\n\nIf the harness plugin for the target provider is missing or disabled, remediate here (`openclaw plugins enable codex` or `openclaw plugins install @openclaw\u002Fcodex`) so the Prove step does not stall on it later; plugin enable is picked up by gateway hot-reload.\n\nDecide the auth contract: API-key providers take a SecretRef on `models.providers.\u003Cid>.apiKey`; subscription\u002FOAuth providers (ChatGPT\u002FCodex, Claude subscriptions) use `openclaw models auth login --provider \u003Cid>` instead and must not be given an API key path.\n\n## Mutate\n\nAPI-key example (OpenAI), key staged by the operator in a `0600` file — validate first with `--dry-run`, then write:\n\n```\nopenclaw config set secrets.providers.openai_key_file --provider-source file --provider-path \u002Fpath\u002Fto\u002Fopenai.key --provider-mode singleValue --dry-run\nopenclaw config set secrets.providers.openai_key_file --provider-source file --provider-path \u002Fpath\u002Fto\u002Fopenai.key --provider-mode singleValue\nopenclaw config set models.providers.openai.apiKey --ref-provider openai_key_file --ref-source file --ref-id value\n```\n\nEnv-var alternative when the gateway process env carries the key:\n\n```\nopenclaw config set models.providers.openai.apiKey --ref-provider default --ref-source env --ref-id OPENAI_API_KEY\n```\n\nTo change a default model, use the in-session `set_default_model` action (with `agentId` for a non-default agent); it live-tests the route before saving. Do not change defaults with raw config writes.\n\n## Repair\n\n```\nopenclaw doctor --lint\n```\n\n`doctor --lint` can exit `1` for findings: read the report and continue the remaining checks. Ordinary `doctor` and `doctor --non-interactive` can write config\u002Fstate; do not use them for diagnosis before approval. If a repair is needed, get explicit approval, run `openclaw doctor --fix --non-interactive`, then re-run the Gather reads.\n\n## Prove\n\nRoster-safe test (works in every setup; use your own agent id or any configured agent):\n\n```\nopenclaw agent --agent \u003CagentId> --model openai\u002Fgpt-5.4 -m \"Reply with exactly: PROVIDER-PROOF-OK\"\n```\n\nSingle-agent installs can use the lighter completion test instead — it has no `--agent` flag and fails with \"no explicit owner\" on multi-agent rosters, so do not retry it there:\n\n```\nopenclaw infer model run --gateway --model openai\u002Fgpt-5.4 --prompt \"Reply with exactly: PROVIDER-PROOF-OK\"\n```\n\nExpect the exact requested reply; record model id and wall time. Known dependency: OpenAI routes need the codex harness plugin at runtime — if the test reports the runtime unavailable, run `openclaw plugins install @openclaw\u002Fcodex` and restart the gateway, then test again.\n\n## Report\n\nState the provider added, the SecretRef path written (never the value), the test result with model id and latency, and whether the default model changed. If the test failed, report the exact error and the next command to try.\n\nFurther reference: https:\u002F\u002Fdocs.openclaw.ai\u002Fproviders\u002Fmodels and https:\u002F\u002Fdocs.openclaw.ai\u002Fproviders\u002Fopenai\n",{"name":5,"description":7},"main","f1c93577085244aa96aa87b53a2df9b59d293bd7","custodian-skills\u002Fadd-model-provider",82884,"https:\u002F\u002Fgithub.com\u002Fopenclaw\u002Fopenclaw","https:\u002F\u002Fopenclaw.ai","https:\u002F\u002Fgithub.com\u002Fopenclaw","Your personal, open source AI assistant.","2026-11-13 03:01:37",{"source":8,"skillName":5,"commands":44,"prompt":54,"zipAvailable":55},[45,48,51],{"tool":46,"command":47},"npx","npx skills add openclaw\u002Fopenclaw --skill add-model-provider",{"tool":49,"command":50},"bunx","bunx skills add openclaw\u002Fopenclaw --skill add-model-provider",{"tool":52,"command":53},"pnpm","pnpm dlx skills add openclaw\u002Fopenclaw --skill add-model-provider","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fopenclaw\u002Fopenclaw\u002Fblob\u002Fmain\u002Fcustodian-skills\u002Fadd-model-provider\u002FSKILL.md",true,[],[58,64,87,104,126,150],{"skillNo":59,"name":60,"nameZh":6,"description":6,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":9,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":61,"categories":62,"keywords":63,"publishedAt":29},"01M698VP84FNM6G9MR1HPX7MF7","lobster","https:\u002F\u002Fgithub.com\u002Fopenclaw\u002Fopenclaw\u002Fblob\u002Fmain\u002Fextensions\u002Flobster\u002FSKILL.md",[],[60],{"skillNo":65,"name":66,"nameZh":6,"description":67,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":9,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":68,"categories":69,"keywords":70,"publishedAt":29},"01M698YY8QGQ7S8TJNKJG6VTPH","xurl","xurl CLI for authenticated X posts, replies, reads\u002Fsearch, DMs, media upload, followers, auth status, or raw v2 API calls.","https:\u002F\u002Fgithub.com\u002Fopenclaw\u002Fopenclaw\u002Fblob\u002Fmain\u002Fskills\u002Fxurl\u002FSKILL.md",[],[66,71,72,73,74,75,76,77,78,79,80,81,82,83,84,85,86],"for","api","calls","replies","posts","upload","tap","install","brew","node","Media","search","npm","status","auth","cli",{"skillNo":88,"name":89,"nameZh":6,"description":90,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":9,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":91,"categories":92,"keywords":93,"publishedAt":29},"01M698YWT1CJ0WK88WB909R9RT","weather","Current weather and forecasts with web_fetch, falling back to wttr.in curl for locations, rain, temperature, travel planning.","https:\u002F\u002Fgithub.com\u002Fopenclaw\u002Fopenclaw\u002Fblob\u002Fmain\u002Fskills\u002Fweather\u002FSKILL.md",[],[89,94,95,78,96,79,97,98,99,100,101,102,71,103,27],"travel planning","travel","fetch","curl","https","help","planning","web","back","temperature",{"skillNo":105,"name":106,"nameZh":6,"description":107,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":9,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":108,"categories":109,"keywords":115,"publishedAt":29},"01M698YV2Q0R0JJKAWGFS21K0N","visualize","Create inline visuals for code and explanations, or author persistent OpenClaw dashboard widgets with show_widget.","https:\u002F\u002Fgithub.com\u002Fopenclaw\u002Fopenclaw\u002Fblob\u002Fmain\u002Fskills\u002Fvisualize\u002FSKILL.md",[110],{"categoryNo":111,"categoryName":112,"taxonomyType":113,"taxonomyTypeDesc":114},"01JBSEEDCAT000000000000033","数据分析师","PROFESSION","适用职业",[106,116,117,118,119,71,27,120,121,122,123,124,9,125],"widgets","openclaw dashboard","author","inline","show","code","create","visuals","dashboard","widget",{"skillNo":127,"name":128,"nameZh":6,"description":129,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":9,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":130,"categories":131,"keywords":140,"publishedAt":29},"01M698YS2TRJH9ENG28HD9CD87","trello","Manage Trello boards, lists, and cards via the Trello REST API.","https:\u002F\u002Fgithub.com\u002Fopenclaw\u002Fopenclaw\u002Fblob\u002Fmain\u002Fskills\u002Ftrello\u002FSKILL.md",[132,137],{"categoryNo":133,"categoryName":134,"taxonomyType":135,"taxonomyTypeDesc":136},"01JBSEEDCAT000000000000010","后端与接口","SCENARIO","使用场景",{"categoryNo":138,"categoryName":139,"taxonomyType":113,"taxonomyTypeDesc":114},"01JBSEEDCAT000000000000030","开发工程师",[128,98,141,142,143,144,145,146,78,79,147,97,72,148,149],"cloud","manage","via","rest api","token","atlassian","jq","REST","developer",{"skillNo":151,"name":152,"nameZh":6,"description":153,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":9,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":154,"categories":155,"keywords":156,"publishedAt":29},"01M698YQ9Q3M4W78EWV2KSCSVW","tmux","Control tmux sessions\u002Fpanes for interactive CLIs: list, capture output, send keys, paste text, monitor prompts.","https:\u002F\u002Fgithub.com\u002Fopenclaw\u002Fopenclaw\u002Fblob\u002Fmain\u002Fskills\u002Ftmux\u002FSKILL.md",[],[152,78,157,158,71,159,160,161,162,163,25,164,79,165,166,167,168,169,170],"send","darwin","keys","paste","output","control","prompts","list","capture","panes","text","monitor","sessions","linux"]