[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7AWBDGFAK5AC335A5R0RSRA":3,"skill-same:01M7AWBDGFAK5AC335A5R0RSRA":44},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":16,"categories":17,"keywords":18,"publishedAt":19,"linkOnly":20,"markdownContent":21,"markdownBody":22,"frontMatter":23,"refName":24,"commitSha":25,"skillDirectory":26,"forksCount":14,"repositoryHtmlUrl":27,"repositoryHomepageUrl":6,"ownerHtmlUrl":28,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":29,"install":30,"resources":43},"01M7AWBDGFAK5AC335A5R0RSRA","wfx-models-sync",null,"Sync a provider's live \u002Fmodels catalog into wfx named profiles (%USERPROFILE%\\.wfx\\config.json) using tools\u002FSync-WfxProfiles.ps1. Use when the user wants to add, update, refresh, or list the available models of a wfx provider (venice, deepseek, gemini, qwen-token-plan, cursor, ollama, etc.) as selectable profiles.","perezdap\u002Fwfx","perezdap","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F21178040?v=4","01M7AW8W56519ZV2R4GZKJRNJ6","David Perez","01M7AW8W61AN9Z6ZN8MDZ9N34Z",0,"MIT","https:\u002F\u002Fgithub.com\u002Fperezdap\u002Fwfx\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fwfx-models-sync\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: wfx-models-sync\ndescription: \"Sync a provider's live \u002Fmodels catalog into wfx named profiles (%USERPROFILE%\\\\.wfx\\\\config.json) using tools\u002FSync-WfxProfiles.ps1. Use when the user wants to add, update, refresh, or list the available models of a wfx provider (venice, deepseek, gemini, qwen-token-plan, cursor, ollama, etc.) as selectable profiles.\"\n---\n\n# WFX Models Sync\n\nSyncs a provider's live model catalog into wfx **named profiles** (issue #7's\nfeature): one profile per model under the `\u003Cprovider>\u002F\u003Cmodel-id>` namespace in\nthe wfx configuration file. Adapted from the pi `*-models-sync` skills, but\nPowerShell-first (no Node.js) and targeting wfx's settings-layer config instead\nof pi's `models.json`.\n\n## Requirements\n\n- PowerShell 7+.\n- The provider's API key env var must be set **for the sync to read the\n  catalog** (see the table). The synced profiles never contain secrets.\n\n## Run\n\nFrom the repo root:\n\n```powershell\n# Preview without writing\npwsh tools\u002FSync-WfxProfiles.ps1 venice -DryRun\n\n# Sync into the user config (default: %USERPROFILE%\\.wfx\\config.json)\npwsh tools\u002FSync-WfxProfiles.ps1 deepseek\n\n# Sync into a project config instead\npwsh tools\u002FSync-WfxProfiles.ps1 zai-coding -ConfigPath .\\.wfx\\config.json\n\n# List the provider registry\npwsh tools\u002FSync-WfxProfiles.ps1 -ListProviders\n```\n\n## Provider registry\n\n| Provider | Catalog endpoint | Key env var |\n| --- | --- | --- |\n| `atlas-cloud` | api.atlascloud.ai\u002Fv1 | `ATLAS_CLOUD_API_KEY` |\n| `cursor` | 127.0.0.1:8080\u002Fv1 (local proxy) | none |\n| `deepseek` | api.deepseek.com | `DEEPSEEK_API_KEY` |\n| `fireworks` | api.fireworks.ai\u002Finference\u002Fv1 | `FIREWORKS_API_KEY` |\n| `gemini` | generativelanguage.googleapis.com\u002Fv1beta (`v1beta\u002Fopenai` shim written to profiles) | `GEMINI_API_KEY` |\n| `inception` | api.inceptionlabs.ai\u002Fv1 | `INCEPTION_API_KEY` |\n| `meta` | api.meta.ai\u002Fv1 | `META_AI_API_KEY` |\n| `neuralwatt` | api.neuralwatt.com\u002Fv1 | `NEURALWATT_API_KEY` |\n| `ollama` | 127.0.0.1:11434\u002Fv1 (local OpenAI-compat daemon) | none |\n| `poe` | api.poe.com\u002Fv1 | `POE_API_KEY` |\n| `qwen-token-plan` | token-plan.ap-southeast-1.maas.aliyuncs.com\u002Fcompatible-mode\u002Fv1 | `QWEN_TOKEN_PLAN_API_KEY` |\n| `routera` | api.routera.one\u002Fv1 | `ROUTERA_API_KEY` |\n| `sakana` | api.sakana.ai\u002Fv1 | `SAKANA_API_KEY` |\n| `venice` | api.venice.ai\u002Fapi\u002Fv1 (text models only) | `VENICE_API_KEY` |\n| `zai-coding` | api.z.ai\u002Fapi\u002Fcoding\u002Fpaas\u002Fv4 | `ZAI_API_KEY` |\n\nNot yet ported from the pi collection: the Cloudflare-AI-Gateway-routed\nproviders (`asterlab`, `nube`, `cloudflare-vertex`), Chatbox AI, and Cline.\nAdd them to the hashtable in `tools\u002FSync-WfxProfiles.ps1` when needed.\nRegistry entries are ported from the pi skills; only `venice`, `deepseek`,\n`gemini`, `cursor`, and `ollama` have been verified live so far.\n\n## Behavior to know before running\n\n- **Sync owns the `\u003Cprovider>\u002F*` namespace.** Profiles under it are added,\n  updated, or removed to match the catalog. Hand-written profiles should use\n  other names; everything outside the namespace is preserved.\n- **Secrets:** profiles carry `provider`, `base_url`, and `model` only. At wfx\n  runtime, credentials come from `WFX_API_KEY` (any provider; `OPENAI_API_KEY`\n  is the generic fallback for non-OpenRouter providers) or a hand-added\n  `\"api_key\"` in the profile. The script never writes keys.\n- **Writing normalizes the file to plain JSON.** Comments and trailing commas\n  are tolerated on read but not preserved on write; when the catalog matches\n  the managed profiles, the file is left untouched. Before overwriting, the\n  previous file is saved to `config.json.bak` — the backup keeps any\n  hand-written secrets the original held, so treat it as a secrets file.\n- Useful flags: `-DryRun`, `-Include \u003Cregex[]>`, `-Exclude \u003Cregex[]>`,\n  `-PreserveRouting` (keep existing provider\u002Fbase_url), `-Prefix`,\n  `-ModelsEndpoint`, `-BaseUrl`, `-EnvVar`, `-WhatIf`.\n\n## Validation\n\nAfter syncing, verify wfx resolves a synced profile:\n\n```powershell\nwfx config --profile venice\u002Fllama-3.3-70b\n```\n\nExpected: `Provider:`\u002F`Profile:`\u002F`Model:`\u002F`Base URL:` lines resolve, and\n`Credentials: not configured` unless a key is in scope. Never print or commit\nAPI keys.\n","# WFX Models Sync\n\nSyncs a provider's live model catalog into wfx **named profiles** (issue #7's\nfeature): one profile per model under the `\u003Cprovider>\u002F\u003Cmodel-id>` namespace in\nthe wfx configuration file. Adapted from the pi `*-models-sync` skills, but\nPowerShell-first (no Node.js) and targeting wfx's settings-layer config instead\nof pi's `models.json`.\n\n## Requirements\n\n- PowerShell 7+.\n- The provider's API key env var must be set **for the sync to read the\n  catalog** (see the table). The synced profiles never contain secrets.\n\n## Run\n\nFrom the repo root:\n\n```powershell\n# Preview without writing\npwsh tools\u002FSync-WfxProfiles.ps1 venice -DryRun\n\n# Sync into the user config (default: %USERPROFILE%\\.wfx\\config.json)\npwsh tools\u002FSync-WfxProfiles.ps1 deepseek\n\n# Sync into a project config instead\npwsh tools\u002FSync-WfxProfiles.ps1 zai-coding -ConfigPath .\\.wfx\\config.json\n\n# List the provider registry\npwsh tools\u002FSync-WfxProfiles.ps1 -ListProviders\n```\n\n## Provider registry\n\n| Provider | Catalog endpoint | Key env var |\n| --- | --- | --- |\n| `atlas-cloud` | api.atlascloud.ai\u002Fv1 | `ATLAS_CLOUD_API_KEY` |\n| `cursor` | 127.0.0.1:8080\u002Fv1 (local proxy) | none |\n| `deepseek` | api.deepseek.com | `DEEPSEEK_API_KEY` |\n| `fireworks` | api.fireworks.ai\u002Finference\u002Fv1 | `FIREWORKS_API_KEY` |\n| `gemini` | generativelanguage.googleapis.com\u002Fv1beta (`v1beta\u002Fopenai` shim written to profiles) | `GEMINI_API_KEY` |\n| `inception` | api.inceptionlabs.ai\u002Fv1 | `INCEPTION_API_KEY` |\n| `meta` | api.meta.ai\u002Fv1 | `META_AI_API_KEY` |\n| `neuralwatt` | api.neuralwatt.com\u002Fv1 | `NEURALWATT_API_KEY` |\n| `ollama` | 127.0.0.1:11434\u002Fv1 (local OpenAI-compat daemon) | none |\n| `poe` | api.poe.com\u002Fv1 | `POE_API_KEY` |\n| `qwen-token-plan` | token-plan.ap-southeast-1.maas.aliyuncs.com\u002Fcompatible-mode\u002Fv1 | `QWEN_TOKEN_PLAN_API_KEY` |\n| `routera` | api.routera.one\u002Fv1 | `ROUTERA_API_KEY` |\n| `sakana` | api.sakana.ai\u002Fv1 | `SAKANA_API_KEY` |\n| `venice` | api.venice.ai\u002Fapi\u002Fv1 (text models only) | `VENICE_API_KEY` |\n| `zai-coding` | api.z.ai\u002Fapi\u002Fcoding\u002Fpaas\u002Fv4 | `ZAI_API_KEY` |\n\nNot yet ported from the pi collection: the Cloudflare-AI-Gateway-routed\nproviders (`asterlab`, `nube`, `cloudflare-vertex`), Chatbox AI, and Cline.\nAdd them to the hashtable in `tools\u002FSync-WfxProfiles.ps1` when needed.\nRegistry entries are ported from the pi skills; only `venice`, `deepseek`,\n`gemini`, `cursor`, and `ollama` have been verified live so far.\n\n## Behavior to know before running\n\n- **Sync owns the `\u003Cprovider>\u002F*` namespace.** Profiles under it are added,\n  updated, or removed to match the catalog. Hand-written profiles should use\n  other names; everything outside the namespace is preserved.\n- **Secrets:** profiles carry `provider`, `base_url`, and `model` only. At wfx\n  runtime, credentials come from `WFX_API_KEY` (any provider; `OPENAI_API_KEY`\n  is the generic fallback for non-OpenRouter providers) or a hand-added\n  `\"api_key\"` in the profile. The script never writes keys.\n- **Writing normalizes the file to plain JSON.** Comments and trailing commas\n  are tolerated on read but not preserved on write; when the catalog matches\n  the managed profiles, the file is left untouched. Before overwriting, the\n  previous file is saved to `config.json.bak` — the backup keeps any\n  hand-written secrets the original held, so treat it as a secrets file.\n- Useful flags: `-DryRun`, `-Include \u003Cregex[]>`, `-Exclude \u003Cregex[]>`,\n  `-PreserveRouting` (keep existing provider\u002Fbase_url), `-Prefix`,\n  `-ModelsEndpoint`, `-BaseUrl`, `-EnvVar`, `-WhatIf`.\n\n## Validation\n\nAfter syncing, verify wfx resolves a synced profile:\n\n```powershell\nwfx config --profile venice\u002Fllama-3.3-70b\n```\n\nExpected: `Provider:`\u002F`Profile:`\u002F`Model:`\u002F`Base URL:` lines resolve, and\n`Credentials: not configured` unless a key is in scope. Never print or commit\nAPI keys.\n",{"name":5,"description":7},"main","ac9d9701802c6b29b4f4f9f8c92fb750933bfe72",".agents\u002Fskills\u002Fwfx-models-sync","https:\u002F\u002Fgithub.com\u002Fperezdap\u002Fwfx","https:\u002F\u002Fgithub.com\u002Fperezdap","2026-09-03 05:51:57",{"source":8,"skillName":5,"commands":31,"prompt":41,"zipAvailable":42},[32,35,38],{"tool":33,"command":34},"npx","npx skills add perezdap\u002Fwfx --skill wfx-models-sync",{"tool":36,"command":37},"bunx","bunx skills add perezdap\u002Fwfx --skill wfx-models-sync",{"tool":39,"command":40},"pnpm","pnpm dlx skills add perezdap\u002Fwfx --skill wfx-models-sync","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fperezdap\u002Fwfx\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fwfx-models-sync\u002FSKILL.md",true,[],[45,52,59,66,73,80],{"skillNo":46,"name":47,"nameZh":6,"description":48,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":49,"categories":50,"keywords":51,"publishedAt":19},"01M7AWJ3PTP6N84KXAT5JPQQ3V","writing-shape","Writing, exploit: shape raw material into an article, paragraph by paragraph.","https:\u002F\u002Fgithub.com\u002Fperezdap\u002Fwfx\u002Fblob\u002Fmain\u002F.windsurf\u002Fskills\u002Fwriting-shape\u002FSKILL.md",[],[],{"skillNo":53,"name":54,"nameZh":6,"description":55,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":56,"categories":57,"keywords":58,"publishedAt":19},"01M7AWJ24RFESG46S4S4HVD3PD","writing-fragments","Writing, explore: mine raw fragments, no structure yet.","https:\u002F\u002Fgithub.com\u002Fperezdap\u002Fwfx\u002Fblob\u002Fmain\u002F.windsurf\u002Fskills\u002Fwriting-fragments\u002FSKILL.md",[],[],{"skillNo":60,"name":61,"nameZh":6,"description":62,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":63,"categories":64,"keywords":65,"publishedAt":19},"01M7AWJ00DPCDAMAHS9TPG12T1","writing-for-agents","Writing documents for agents. Use when creating or editing skills, or modifying AGENTS.md or CLAUDE.md.","https:\u002F\u002Fgithub.com\u002Fperezdap\u002Fwfx\u002Fblob\u002Fmain\u002F.windsurf\u002Fskills\u002Fwriting-for-agents\u002FSKILL.md",[],[],{"skillNo":67,"name":68,"nameZh":6,"description":69,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":70,"categories":71,"keywords":72,"publishedAt":19},"01M7AWHXJ57V4QHNYE4V940CGP","writing-beats","Writing, exploit; assemble raw material into a journey of beats, grounding each term before a beat leans on it.","https:\u002F\u002Fgithub.com\u002Fperezdap\u002Fwfx\u002Fblob\u002Fmain\u002F.windsurf\u002Fskills\u002Fwriting-beats\u002FSKILL.md",[],[],{"skillNo":74,"name":75,"nameZh":6,"description":76,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":77,"categories":78,"keywords":79,"publishedAt":19},"01M7AWHRHCGV27WWQP2JNPFPRM","wizard","Generate an interactive bash wizard that walks a human through steps only they can perform. Use when provisioning infrastructure, setting up credentials or CI secrets, walking an unfamiliar third-party dashboard, or running a one-off migration or cutover. Don't invoke this for steps the agent can perform itself.","https:\u002F\u002Fgithub.com\u002Fperezdap\u002Fwfx\u002Fblob\u002Fmain\u002F.windsurf\u002Fskills\u002Fwizard\u002FSKILL.md",[],[],{"skillNo":81,"name":82,"nameZh":6,"description":83,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":84,"categories":85,"keywords":86,"publishedAt":19},"01M7AWHNNNADXD1D7FSN97F20A","wayfinder","Plan a huge chunk of work (more than one agent session can hold) as a shared map of decision tickets on your issue tracker, and resolve them one at a time until the way to the destination is clear.","https:\u002F\u002Fgithub.com\u002Fperezdap\u002Fwfx\u002Fblob\u002Fmain\u002F.windsurf\u002Fskills\u002Fwayfinder\u002FSKILL.md",[],[]]