[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7C1E9TK0ZRHDCRSSYHT2MC5":3,"skill-same:01M7C1E9TK0ZRHDCRSSYHT2MC5":54},{"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":23,"commitSha":24,"skillDirectory":25,"forksCount":26,"repositoryHtmlUrl":27,"repositoryHomepageUrl":6,"ownerHtmlUrl":28,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":29,"install":30,"resources":43},"01M7C1E9TK0ZRHDCRSSYHT2MC5","cc-config",null,"Use when working with Claude Code CLI, plugins, hooks, MCP servers, skills, configuration, or any Claude Code feature - routes to the official documentation instead of guessing, and can cache it locally for offline use","zak-keown\u002Fmoe","zak-keown","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F320717241?v=4","01M7BZFXME0NW6TQX0H7AZM2KS","01M7BZFXN32VR0JN5AATRD53H4",0,"Apache-2.0","https:\u002F\u002Fgithub.com\u002Fzak-keown\u002Fmoe\u002Fblob\u002Fmain\u002Fplugins\u002Fmoe\u002F.opencode\u002Fskills\u002Fcc-config\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: cc-config\ndescription: Use when working with Claude Code CLI, plugins, hooks, MCP servers, skills, configuration, or any Claude Code feature - routes to the official documentation instead of guessing, and can cache it locally for offline use\n---\n\n# Working with Claude Code\n\n## Overview\n\nClaude Code's own documentation is the authority on configuration paths, manifest\nschemas, hook events and CLI flags. This skill's job is to send you there rather\nthan let you guess — and, when you want it offline, to fetch it.\n\n**It ships no documentation of its own.** The upstream version of this skill\ncommitted a 42-file mirror of `docs.claude.com\u002Fen\u002Fdocs\u002Fclaude-code\u002F*`. That copy\nwas dropped on import: it was nine months stale, it omitted eight plugin manifest\nkeys that this monorepo's own `packages\u002Fmint\u002Fschemas\u002Fclaude-code-plugin-manifest.json`\nalready validates, and a skill whose pitch is \"authoritative, stop guessing\" that\nis behind the repo's own schema launders a wrong answer as an official one.\n\n## When to Use\n\n- Creating or configuring Claude Code plugins\n- Setting up MCP servers\n- Working with hooks (SessionStart, Stop, PostToolUse, …)\n- Writing or testing skills\n- Configuring Claude Code settings\n- Troubleshooting Claude Code issues\n- Understanding CLI commands\n- Setting up integrations (VS Code, JetBrains, …)\n- Configuring networking, security, or enterprise features\n\n## How to Get an Answer\n\n**Default: fetch the one page you need.** Every topic is a single markdown file\nunder one predictable URL:\n\n```\nhttps:\u002F\u002Fdocs.claude.com\u002Fen\u002Fdocs\u002Fclaude-code\u002F\u003Ctopic>.md\n```\n\nUse `webfetch` on that URL. One page, current, no cache to go stale.\n\n| Question | Topic |\n|---|---|\n| Create a plugin | `plugins`, then `plugins-reference` |\n| Plugin marketplaces | `plugin-marketplaces` |\n| Set up an MCP server | `mcp` |\n| Configure hooks | `hooks`, then `hooks-guide` |\n| Write a skill | `skills` |\n| Slash commands | `slash-commands` |\n| Subagents | `sub-agents` |\n| CLI flags | `cli-reference` |\n| Headless \u002F scripting | `headless` |\n| Settings reference | `settings` |\n| Memory and context | `memory` |\n| Costs and usage | `costs`, `monitoring-usage` |\n| Troubleshoot | `troubleshooting` |\n| Install and set up | `setup`, `quickstart` |\n\n`https:\u002F\u002Fdocs.claude.com\u002Fllms.txt` lists every page if the topic you want is not\nin the table.\n\n## Working Offline\n\nWhen you have no network, or you want to search across the whole corpus with\n`grep`, populate a local cache first:\n\nResolve [skills\u002Fcc-config\u002Fscripts\u002Fupdate_docs.mjs](scripts\u002Fupdate_docs.mjs)\nrelative to this loaded document, then invoke it with `node`.\n\nIt reads `llms.txt`, extracts every `claude-code\u002F*.md` URL, and writes each page\ninto the sibling `references\u002F` directory beside the resolved script's parent\ndirectory. Then use `read` or `grep` on that directory as usual.\n\nTwo things to know about the cache:\n\n- **It is not committed.** A fresh checkout has no `references\u002F` directory at\n  all, and this skill's answers do not depend on one existing.\n- **It goes stale silently.** Nothing dates it and nothing warns you. If a cached\n  page disagrees with a fetched one, the fetched one wins — re-run the script\n  rather than reasoning from the cache.\n\n## What This Skill Does NOT Do\n\n- It provides **documentation access**, not procedural guidance. For how to\n  *build* a plugin — the workflow, the manifest, the release path in this\n  repo — use the `cc-plugins` skill.\n- It is a **reference router**, not a tutorial.\n\n## Red Flags\n\nIf you find yourself:\n\n- Guessing where a config file lives → fetch `settings`\n- Speculating about a manifest key → fetch `plugins-reference`\n- Unsure which hook event fires when → fetch `hooks`\n- Assuming a feature exists → check the docs first\n\n**Consult the documentation before guessing. Do not answer from a stale cache\nwhen the network is available.**\n","# Working with Claude Code\n\n## Overview\n\nClaude Code's own documentation is the authority on configuration paths, manifest\nschemas, hook events and CLI flags. This skill's job is to send you there rather\nthan let you guess — and, when you want it offline, to fetch it.\n\n**It ships no documentation of its own.** The upstream version of this skill\ncommitted a 42-file mirror of `docs.claude.com\u002Fen\u002Fdocs\u002Fclaude-code\u002F*`. That copy\nwas dropped on import: it was nine months stale, it omitted eight plugin manifest\nkeys that this monorepo's own `packages\u002Fmint\u002Fschemas\u002Fclaude-code-plugin-manifest.json`\nalready validates, and a skill whose pitch is \"authoritative, stop guessing\" that\nis behind the repo's own schema launders a wrong answer as an official one.\n\n## When to Use\n\n- Creating or configuring Claude Code plugins\n- Setting up MCP servers\n- Working with hooks (SessionStart, Stop, PostToolUse, …)\n- Writing or testing skills\n- Configuring Claude Code settings\n- Troubleshooting Claude Code issues\n- Understanding CLI commands\n- Setting up integrations (VS Code, JetBrains, …)\n- Configuring networking, security, or enterprise features\n\n## How to Get an Answer\n\n**Default: fetch the one page you need.** Every topic is a single markdown file\nunder one predictable URL:\n\n```\nhttps:\u002F\u002Fdocs.claude.com\u002Fen\u002Fdocs\u002Fclaude-code\u002F\u003Ctopic>.md\n```\n\nUse `webfetch` on that URL. One page, current, no cache to go stale.\n\n| Question | Topic |\n|---|---|\n| Create a plugin | `plugins`, then `plugins-reference` |\n| Plugin marketplaces | `plugin-marketplaces` |\n| Set up an MCP server | `mcp` |\n| Configure hooks | `hooks`, then `hooks-guide` |\n| Write a skill | `skills` |\n| Slash commands | `slash-commands` |\n| Subagents | `sub-agents` |\n| CLI flags | `cli-reference` |\n| Headless \u002F scripting | `headless` |\n| Settings reference | `settings` |\n| Memory and context | `memory` |\n| Costs and usage | `costs`, `monitoring-usage` |\n| Troubleshoot | `troubleshooting` |\n| Install and set up | `setup`, `quickstart` |\n\n`https:\u002F\u002Fdocs.claude.com\u002Fllms.txt` lists every page if the topic you want is not\nin the table.\n\n## Working Offline\n\nWhen you have no network, or you want to search across the whole corpus with\n`grep`, populate a local cache first:\n\nResolve [skills\u002Fcc-config\u002Fscripts\u002Fupdate_docs.mjs](scripts\u002Fupdate_docs.mjs)\nrelative to this loaded document, then invoke it with `node`.\n\nIt reads `llms.txt`, extracts every `claude-code\u002F*.md` URL, and writes each page\ninto the sibling `references\u002F` directory beside the resolved script's parent\ndirectory. Then use `read` or `grep` on that directory as usual.\n\nTwo things to know about the cache:\n\n- **It is not committed.** A fresh checkout has no `references\u002F` directory at\n  all, and this skill's answers do not depend on one existing.\n- **It goes stale silently.** Nothing dates it and nothing warns you. If a cached\n  page disagrees with a fetched one, the fetched one wins — re-run the script\n  rather than reasoning from the cache.\n\n## What This Skill Does NOT Do\n\n- It provides **documentation access**, not procedural guidance. For how to\n  *build* a plugin — the workflow, the manifest, the release path in this\n  repo — use the `cc-plugins` skill.\n- It is a **reference router**, not a tutorial.\n\n## Red Flags\n\nIf you find yourself:\n\n- Guessing where a config file lives → fetch `settings`\n- Speculating about a manifest key → fetch `plugins-reference`\n- Unsure which hook event fires when → fetch `hooks`\n- Assuming a feature exists → check the docs first\n\n**Consult the documentation before guessing. Do not answer from a stale cache\nwhen the network is available.**\n",{"name":5,"description":7},"main","728894f3f85fbd4e788f015ddfd72bb6155d5dd5","plugins\u002Fmoe\u002F.opencode\u002Fskills\u002Fcc-config",1,"https:\u002F\u002Fgithub.com\u002Fzak-keown\u002Fmoe","https:\u002F\u002Fgithub.com\u002Fzak-keown","2026-09-05 06:29:06",{"source":8,"skillName":5,"commands":31,"prompt":41,"zipAvailable":42},[32,35,38],{"tool":33,"command":34},"npx","npx skills add zak-keown\u002Fmoe --skill cc-config",{"tool":36,"command":37},"bunx","bunx skills add zak-keown\u002Fmoe --skill cc-config",{"tool":39,"command":40},"pnpm","pnpm dlx skills add zak-keown\u002Fmoe --skill cc-config","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fzak-keown\u002Fmoe\u002Fblob\u002Fmain\u002Fplugins\u002Fmoe\u002F.opencode\u002Fskills\u002Fcc-config\u002FSKILL.md",true,[44,50],{"path":45,"resourceType":46,"resourceTypeDesc":47,"sizeBytes":48,"sourceHtmlUrl":49},"scripts\u002Fupdate_docs.d.mts","SCRIPT","脚本",160,"https:\u002F\u002Fgithub.com\u002Fzak-keown\u002Fmoe\u002Fblob\u002Fmain\u002Fplugins\u002Fmoe\u002F.opencode\u002Fskills\u002Fcc-config\u002Fscripts\u002Fupdate_docs.d.mts",{"path":51,"resourceType":46,"resourceTypeDesc":47,"sizeBytes":52,"sourceHtmlUrl":53},"scripts\u002Fupdate_docs.mjs",4264,"https:\u002F\u002Fgithub.com\u002Fzak-keown\u002Fmoe\u002Fblob\u002Fmain\u002Fplugins\u002Fmoe\u002F.opencode\u002Fskills\u002Fcc-config\u002Fscripts\u002Fupdate_docs.mjs",[55,62,69,76,83,90],{"skillNo":56,"name":57,"nameZh":6,"description":58,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":59,"categories":60,"keywords":61,"publishedAt":18},"01M7C1Z5362Y8NVRZ69HWP0ZD0","write-skill","Use when creating new skills, editing existing skills, or verifying skills work before deployment","https:\u002F\u002Fgithub.com\u002Fzak-keown\u002Fmoe\u002Fblob\u002Fmain\u002Fplugins\u002Fmoe\u002Fskills\u002Fwrite-skill\u002FSKILL.md",[],[],{"skillNo":63,"name":64,"nameZh":6,"description":65,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":66,"categories":67,"keywords":68,"publishedAt":18},"01M7C1YZ9966WK9R6ZRPCGWF3G","write-plan","Use when you have a spec or requirements for a multi-step task, before touching code","https:\u002F\u002Fgithub.com\u002Fzak-keown\u002Fmoe\u002Fblob\u002Fmain\u002Fplugins\u002Fmoe\u002Fskills\u002Fwrite-plan\u002FSKILL.md",[],[],{"skillNo":70,"name":71,"nameZh":6,"description":72,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":73,"categories":74,"keywords":75,"publishedAt":18},"01M7C1YMR4SJD7BPBBPXZCVGVH","write-clearly","Apply Strunk's timeless writing rules to ANY prose humans will read—documentation, commit messages, error messages, explanations, reports, or UI text. Makes your writing clearer, stronger, and more professional.","https:\u002F\u002Fgithub.com\u002Fzak-keown\u002Fmoe\u002Fblob\u002Fmain\u002Fplugins\u002Fmoe\u002Fskills\u002Fwrite-clearly\u002FSKILL.md",[],[],{"skillNo":77,"name":78,"nameZh":6,"description":79,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":80,"categories":81,"keywords":82,"publishedAt":18},"01M7C1YH9805YSM0N20VQAVSXF","windows-vm","Create, manage, or connect to a headless Windows 11 VM running in Docker with SSH access. Use when the user wants to spin up, stop, restart, or SSH into a Windows VM.","https:\u002F\u002Fgithub.com\u002Fzak-keown\u002Fmoe\u002Fblob\u002Fmain\u002Fplugins\u002Fmoe\u002Fskills\u002Fwindows-vm\u002FSKILL.md",[],[],{"skillNo":84,"name":85,"nameZh":6,"description":86,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":87,"categories":88,"keywords":89,"publishedAt":18},"01M7C1YD87SCNEJ2C9B8HFR2NQ","verify-completion","Use when about to claim work is complete, fixed, or passing, before committing or creating MRs - requires running verification commands and confirming output before making any success claims; evidence before assertions always","https:\u002F\u002Fgithub.com\u002Fzak-keown\u002Fmoe\u002Fblob\u002Fmain\u002Fplugins\u002Fmoe\u002Fskills\u002Fverify-completion\u002FSKILL.md",[],[],{"skillNo":91,"name":92,"nameZh":6,"description":93,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":94,"categories":95,"keywords":96,"publishedAt":18},"01M7C1YARDEHT0TJ9BRG30ZCF4","using-moe","Use when starting any conversation - establishes how to find and use skills, requiring skill invocation before ANY response including clarifying questions","https:\u002F\u002Fgithub.com\u002Fzak-keown\u002Fmoe\u002Fblob\u002Fmain\u002Fplugins\u002Fmoe\u002Fskills\u002Fusing-moe\u002FSKILL.md",[],[]]