[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7CTM9FZ296SS5YF6ZE0DSA0":3,"skill-same:01M7CTM9FZ296SS5YF6ZE0DSA0":67},{"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":27,"repositoryHtmlUrl":28,"repositoryHomepageUrl":6,"ownerHtmlUrl":29,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":30,"install":31,"resources":44},"01M7CTM9FZ296SS5YF6ZE0DSA0","opencode-plugins",null,"Use when creating or updating OpenCode plugin files in .opencode\u002Fplugins\u002F. Covers plugin structure, hook events (tool.execute.before\u002Fafter, session.*, file.*, etc.), blocking operations via throw, custom tools, environment injection, and TypeScript types.","xiaden\u002FSkyScow","xiaden","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F3605480?v=4","01M7CTGKNTD1XNQE710J977HVD","Lucian Hardy","01M7CTGKPVQ3XRNXNRJ3A6E31F",1,"MIT","https:\u002F\u002Fgithub.com\u002Fxiaden\u002FSkyScow\u002Fblob\u002Fmain\u002Fconfig\u002Fskills\u002Fopencode-plugins\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: opencode-plugins\ndescription: Use when creating or updating OpenCode plugin files in .opencode\u002Fplugins\u002F. Covers plugin structure, hook events (tool.execute.before\u002Fafter, session.*, file.*, etc.), blocking operations via throw, custom tools, environment injection, and TypeScript types.\n---\n\n# OpenCode Plugins\n\nPlugins extend OpenCode by hooking into events and customizing behavior. They provide deterministic automation: blocking dangerous operations, injecting context, adding custom tools, modifying LLM parameters, and logging.\n\n**Do NOT use this skill for:** configuring `opencode.json` or `opencode.jsonc` (use `customize-opencode`), writing commands (use `command-creation-guide`), or creating standalone custom tools in `.opencode\u002Ftools\u002F` (see [`references\u002Fstandalone-tools.md`](file:\u002F\u002F\u002Fhome\u002Fopencode\u002F.config\u002Fopencode\u002Fskills\u002Fopencode-plugins\u002Freferences\u002Fstandalone-tools.md)).\n\n---\n\n## Plugin Installation\n\n### Local Files\n\nPlace JavaScript or TypeScript files in the plugin directory:\n\n| Location | Scope |\n|----------|-------|\n| `.opencode\u002Fplugins\u002F*.js` or `*.ts` | Project-level |\n| `~\u002F.config\u002Fopencode\u002Fplugins\u002F*.js` or `*.ts` | Global |\n\nFiles in these directories are automatically loaded at startup.\n\n### npm Packages\n\nSpecify npm packages in your config file (`opencode.json`):\n\n```json\n{\n  \"plugin\": [\"opencode-helicone-session\", \"opencode-wakatime\", \"@my-org\u002Fcustom-plugin\"]\n}\n```\n\nBoth regular and scoped npm packages are supported. Plugins are installed automatically via Bun at startup and cached in `~\u002F.cache\u002Fopencode\u002Fnode_modules\u002F`. Duplicate packages with the same name and version are loaded once.\n\n---\n\n## Basic Structure\n\n```javascript\n\u002F\u002F .opencode\u002Fplugins\u002Fexample.js\nexport const MyPlugin = async ({ project, client, $, directory, worktree, serverUrl }) => {\n  console.log(\"Plugin initialized!\")\n\n  return {\n    \u002F\u002F Hook implementations go here\n  }\n}\n```\n\nThe plugin function receives:\n- `project`: Current project information\n- `directory`: Current working directory\n- `worktree`: Git worktree path\n- `client`: OpenCode SDK client for AI interactions\n- `$`: Bun's shell API for executing commands\n- `serverUrl`: OpenCode server URL\n\n### TypeScript Support\n\n```typescript\nimport type { Plugin } from \"@opencode-ai\u002Fplugin\"\n\nexport const MyPlugin: Plugin = async ({ project, client, $, directory, worktree, serverUrl }) => {\n  return {\n    \u002F\u002F Type-safe hook implementations\n  }\n}\n```\n\n---\n\n## Hook Events\n\n### Tool Events (Primary Hook Targets)\n\n| Event | Fires when | Common uses |\n|-------|------------|-------------|\n| `tool.execute.before` | Before tool runs | Block dangerous ops, validate args, inject context |\n| `tool.execute.after` | After tool completes | Run formatters, log results, trigger follow-up |\n\n### Chat \u002F LLM Hooks\n\n| Event | Fires when | Common uses |\n|-------|------------|-------------|\n| `chat.message` | New message is received | Augment messages, inject context |\n| `chat.params` | Before LLM call | Override temperature, topP, topK, maxOutputTokens |\n| `chat.headers` | Before LLM call | Inject custom HTTP headers for providers |\n| `experimental.chat.messages.transform` | Before messages sent to LLM | Transform message list |\n| `experimental.chat.system.transform` | Before system prompt assembled | Inject or modify system prompt lines |\n| `experimental.text.complete` | During text completion | Intercept completion results |\n\n### Permission & Command Hooks\n\n| Event | Fires when | Common uses |\n|-------|------------|-------------|\n| `permission.ask` | Permission dialog shown | Auto-allow or auto-deny operations |\n| `command.execute.before` | Before command runs | Validate or augment command context |\n\n### Session Events\n\n| Event | Fires when |\n|-------|------------|\n| `session.created` | New session starts |\n| `session.compacted` | Context compaction completes |\n| `session.deleted` | Session is deleted |\n| `session.diff` | Diff is generated |\n| `session.error` | Session encounters error |\n| `session.idle` | Session becomes idle |\n| `session.status` | Status changes |\n| `session.updated` | Session data changes |\n| `experimental.session.compacting` | Before compaction prompt generation |\n| `experimental.compaction.autocontinue` | After compaction, before auto-continue message |\n\n### File Events\n\n| Event | Fires when |\n|-------|------------|\n| `file.edited` | File is modified |\n| `file.watcher.updated` | File watcher state changes |\n\n### Lifecycle & Config Hooks\n\n| Event | Fires when | Common uses |\n|-------|------------|-------------|\n| `config` | During startup | Modify configuration at runtime |\n| `dispose` | Plugin shutdown \u002F reload | Clean up resources |\n| `event` | Any event fires | Listen to all session events |\n| `tool.definition` | Tool definition sent to LLM | Modify tool descriptions\u002Fparameters |\n| `shell.env` | Before shell execution | Inject environment variables |\n| `experimental.provider.small_model` | Small model selection | Select alternative model for lightweight tasks |\n\n### Auth Hooks\n\n| Event | Fires when | Common uses |\n|-------|------------|-------------|\n| `auth` | Provider authentication | Add OAuth or API-key auth for LLM providers |\n| `provider` | Provider initialization | Register custom model providers |\n\n---\n\n## Blocking Operations\n\nTo block a tool execution, **throw an error** in `tool.execute.before`:\n\n```javascript\nexport const EnvProtection = async ({ project, client, $, directory, worktree, serverUrl }) => {\n  return {\n    \"tool.execute.before\": async (input, output) => {\n      if (input.tool === \"read\" && output.args.filePath.includes(\".env\")) {\n        throw new Error(\"Do not read .env files\")\n      }\n    },\n  }\n}\n```\n\nThe error message is shown to the model as feedback.\n\n---\n\n## Environment Injection\n\nInject environment variables into all shell execution:\n\n```javascript\nexport const InjectEnvPlugin = async () => {\n  return {\n    \"shell.env\": async (input, output) => {\n      output.env.MY_API_KEY = \"secret\"\n      output.env.PROJECT_ROOT = input.cwd\n    },\n  }\n}\n```\n\n---\n\n## Reference Files\n\nThis skill covers core concepts. For detailed implementation patterns, load these reference files on demand:\n\n- **[`references\u002Fhooks.md`](file:\u002F\u002F\u002Fhome\u002Fopencode\u002F.config\u002Fopencode\u002Fskills\u002Fopencode-plugins\u002Freferences\u002Fhooks.md)** — Detailed hook implementations: `tool.execute.before`, `tool.execute.after`, `permission.ask`, `command.execute.before`, `tool.definition`, compaction hooks, notifications, logging, config hook, dispose hook, and event listener\n- **[`references\u002Fchat-hooks.md`](file:\u002F\u002F\u002Fhome\u002Fopencode\u002F.config\u002Fopencode\u002Fskills\u002Fopencode-plugins\u002Freferences\u002Fchat-hooks.md)** — Chat lifecycle hooks: `chat.message`, `chat.params`, `chat.headers`, `experimental.chat.messages.transform`, `experimental.chat.system.transform`, `experimental.text.complete`\n- **[`references\u002Fcustom-tools.md`](file:\u002F\u002F\u002Fhome\u002Fopencode\u002F.config\u002Fopencode\u002Fskills\u002Fopencode-plugins\u002Freferences\u002Fcustom-tools.md)** — Plugin-based custom tools API: `ToolResult` type, common mistakes, args schema helpers, and complete examples with error handling\n- **[`references\u002Fstandalone-tools.md`](file:\u002F\u002F\u002Fhome\u002Fopencode\u002F.config\u002Fopencode\u002Fskills\u002Fopencode-plugins\u002Freferences\u002Fstandalone-tools.md)** — Standalone custom tools in `.opencode\u002Ftools\u002F`: file naming, multiple exports, plain Zod approach, context access, invoking scripts in other languages\n- **[`references\u002Fadditional-topics.md`](file:\u002F\u002F\u002Fhome\u002Fopencode\u002F.config\u002Fopencode\u002Fskills\u002Fopencode-plugins\u002Freferences\u002Fadditional-topics.md)** — npm plugin loading, dependencies, load order with deduplication, `OPENCODE_DISABLE_DEFAULT_PLUGINS`, and Copilot Hooks migration guide\n\n---\n\n## Authoring Checklist\n\n- [ ] Plugin exports a named function\n- [ ] Returns object with hook implementations\n- [ ] Uses `throw new Error()` to block (not return values)\n- [ ] Handles errors gracefully (don't crash on unexpected input)\n- [ ] Uses `client.app.log()` for debugging\n- [ ] TypeScript types imported from `@opencode-ai\u002Fplugin`\n- [ ] Dependencies declared in `.opencode\u002Fpackage.json` if needed\n- [ ] Custom tools return `{ output: string, title?, metadata? }` — never `{ error, data, ok, result }` or other shapes\n- [ ] Custom tools `throw new Error(...)` on failure — never return error objects\n- [ ] Every arg in `args` uses `tool.schema` and has `.describe()`\n","# OpenCode Plugins\n\nPlugins extend OpenCode by hooking into events and customizing behavior. They provide deterministic automation: blocking dangerous operations, injecting context, adding custom tools, modifying LLM parameters, and logging.\n\n**Do NOT use this skill for:** configuring `opencode.json` or `opencode.jsonc` (use `customize-opencode`), writing commands (use `command-creation-guide`), or creating standalone custom tools in `.opencode\u002Ftools\u002F` (see [`references\u002Fstandalone-tools.md`](file:\u002F\u002F\u002Fhome\u002Fopencode\u002F.config\u002Fopencode\u002Fskills\u002Fopencode-plugins\u002Freferences\u002Fstandalone-tools.md)).\n\n---\n\n## Plugin Installation\n\n### Local Files\n\nPlace JavaScript or TypeScript files in the plugin directory:\n\n| Location | Scope |\n|----------|-------|\n| `.opencode\u002Fplugins\u002F*.js` or `*.ts` | Project-level |\n| `~\u002F.config\u002Fopencode\u002Fplugins\u002F*.js` or `*.ts` | Global |\n\nFiles in these directories are automatically loaded at startup.\n\n### npm Packages\n\nSpecify npm packages in your config file (`opencode.json`):\n\n```json\n{\n  \"plugin\": [\"opencode-helicone-session\", \"opencode-wakatime\", \"@my-org\u002Fcustom-plugin\"]\n}\n```\n\nBoth regular and scoped npm packages are supported. Plugins are installed automatically via Bun at startup and cached in `~\u002F.cache\u002Fopencode\u002Fnode_modules\u002F`. Duplicate packages with the same name and version are loaded once.\n\n---\n\n## Basic Structure\n\n```javascript\n\u002F\u002F .opencode\u002Fplugins\u002Fexample.js\nexport const MyPlugin = async ({ project, client, $, directory, worktree, serverUrl }) => {\n  console.log(\"Plugin initialized!\")\n\n  return {\n    \u002F\u002F Hook implementations go here\n  }\n}\n```\n\nThe plugin function receives:\n- `project`: Current project information\n- `directory`: Current working directory\n- `worktree`: Git worktree path\n- `client`: OpenCode SDK client for AI interactions\n- `$`: Bun's shell API for executing commands\n- `serverUrl`: OpenCode server URL\n\n### TypeScript Support\n\n```typescript\nimport type { Plugin } from \"@opencode-ai\u002Fplugin\"\n\nexport const MyPlugin: Plugin = async ({ project, client, $, directory, worktree, serverUrl }) => {\n  return {\n    \u002F\u002F Type-safe hook implementations\n  }\n}\n```\n\n---\n\n## Hook Events\n\n### Tool Events (Primary Hook Targets)\n\n| Event | Fires when | Common uses |\n|-------|------------|-------------|\n| `tool.execute.before` | Before tool runs | Block dangerous ops, validate args, inject context |\n| `tool.execute.after` | After tool completes | Run formatters, log results, trigger follow-up |\n\n### Chat \u002F LLM Hooks\n\n| Event | Fires when | Common uses |\n|-------|------------|-------------|\n| `chat.message` | New message is received | Augment messages, inject context |\n| `chat.params` | Before LLM call | Override temperature, topP, topK, maxOutputTokens |\n| `chat.headers` | Before LLM call | Inject custom HTTP headers for providers |\n| `experimental.chat.messages.transform` | Before messages sent to LLM | Transform message list |\n| `experimental.chat.system.transform` | Before system prompt assembled | Inject or modify system prompt lines |\n| `experimental.text.complete` | During text completion | Intercept completion results |\n\n### Permission & Command Hooks\n\n| Event | Fires when | Common uses |\n|-------|------------|-------------|\n| `permission.ask` | Permission dialog shown | Auto-allow or auto-deny operations |\n| `command.execute.before` | Before command runs | Validate or augment command context |\n\n### Session Events\n\n| Event | Fires when |\n|-------|------------|\n| `session.created` | New session starts |\n| `session.compacted` | Context compaction completes |\n| `session.deleted` | Session is deleted |\n| `session.diff` | Diff is generated |\n| `session.error` | Session encounters error |\n| `session.idle` | Session becomes idle |\n| `session.status` | Status changes |\n| `session.updated` | Session data changes |\n| `experimental.session.compacting` | Before compaction prompt generation |\n| `experimental.compaction.autocontinue` | After compaction, before auto-continue message |\n\n### File Events\n\n| Event | Fires when |\n|-------|------------|\n| `file.edited` | File is modified |\n| `file.watcher.updated` | File watcher state changes |\n\n### Lifecycle & Config Hooks\n\n| Event | Fires when | Common uses |\n|-------|------------|-------------|\n| `config` | During startup | Modify configuration at runtime |\n| `dispose` | Plugin shutdown \u002F reload | Clean up resources |\n| `event` | Any event fires | Listen to all session events |\n| `tool.definition` | Tool definition sent to LLM | Modify tool descriptions\u002Fparameters |\n| `shell.env` | Before shell execution | Inject environment variables |\n| `experimental.provider.small_model` | Small model selection | Select alternative model for lightweight tasks |\n\n### Auth Hooks\n\n| Event | Fires when | Common uses |\n|-------|------------|-------------|\n| `auth` | Provider authentication | Add OAuth or API-key auth for LLM providers |\n| `provider` | Provider initialization | Register custom model providers |\n\n---\n\n## Blocking Operations\n\nTo block a tool execution, **throw an error** in `tool.execute.before`:\n\n```javascript\nexport const EnvProtection = async ({ project, client, $, directory, worktree, serverUrl }) => {\n  return {\n    \"tool.execute.before\": async (input, output) => {\n      if (input.tool === \"read\" && output.args.filePath.includes(\".env\")) {\n        throw new Error(\"Do not read .env files\")\n      }\n    },\n  }\n}\n```\n\nThe error message is shown to the model as feedback.\n\n---\n\n## Environment Injection\n\nInject environment variables into all shell execution:\n\n```javascript\nexport const InjectEnvPlugin = async () => {\n  return {\n    \"shell.env\": async (input, output) => {\n      output.env.MY_API_KEY = \"secret\"\n      output.env.PROJECT_ROOT = input.cwd\n    },\n  }\n}\n```\n\n---\n\n## Reference Files\n\nThis skill covers core concepts. For detailed implementation patterns, load these reference files on demand:\n\n- **[`references\u002Fhooks.md`](file:\u002F\u002F\u002Fhome\u002Fopencode\u002F.config\u002Fopencode\u002Fskills\u002Fopencode-plugins\u002Freferences\u002Fhooks.md)** — Detailed hook implementations: `tool.execute.before`, `tool.execute.after`, `permission.ask`, `command.execute.before`, `tool.definition`, compaction hooks, notifications, logging, config hook, dispose hook, and event listener\n- **[`references\u002Fchat-hooks.md`](file:\u002F\u002F\u002Fhome\u002Fopencode\u002F.config\u002Fopencode\u002Fskills\u002Fopencode-plugins\u002Freferences\u002Fchat-hooks.md)** — Chat lifecycle hooks: `chat.message`, `chat.params`, `chat.headers`, `experimental.chat.messages.transform`, `experimental.chat.system.transform`, `experimental.text.complete`\n- **[`references\u002Fcustom-tools.md`](file:\u002F\u002F\u002Fhome\u002Fopencode\u002F.config\u002Fopencode\u002Fskills\u002Fopencode-plugins\u002Freferences\u002Fcustom-tools.md)** — Plugin-based custom tools API: `ToolResult` type, common mistakes, args schema helpers, and complete examples with error handling\n- **[`references\u002Fstandalone-tools.md`](file:\u002F\u002F\u002Fhome\u002Fopencode\u002F.config\u002Fopencode\u002Fskills\u002Fopencode-plugins\u002Freferences\u002Fstandalone-tools.md)** — Standalone custom tools in `.opencode\u002Ftools\u002F`: file naming, multiple exports, plain Zod approach, context access, invoking scripts in other languages\n- **[`references\u002Fadditional-topics.md`](file:\u002F\u002F\u002Fhome\u002Fopencode\u002F.config\u002Fopencode\u002Fskills\u002Fopencode-plugins\u002Freferences\u002Fadditional-topics.md)** — npm plugin loading, dependencies, load order with deduplication, `OPENCODE_DISABLE_DEFAULT_PLUGINS`, and Copilot Hooks migration guide\n\n---\n\n## Authoring Checklist\n\n- [ ] Plugin exports a named function\n- [ ] Returns object with hook implementations\n- [ ] Uses `throw new Error()` to block (not return values)\n- [ ] Handles errors gracefully (don't crash on unexpected input)\n- [ ] Uses `client.app.log()` for debugging\n- [ ] TypeScript types imported from `@opencode-ai\u002Fplugin`\n- [ ] Dependencies declared in `.opencode\u002Fpackage.json` if needed\n- [ ] Custom tools return `{ output: string, title?, metadata? }` — never `{ error, data, ok, result }` or other shapes\n- [ ] Custom tools `throw new Error(...)` on failure — never return error objects\n- [ ] Every arg in `args` uses `tool.schema` and has `.describe()`\n",{"name":5,"description":7},"main","8f95d6b7cbf4ec39161b4e6c8bc5e1493e58003c","config\u002Fskills\u002Fopencode-plugins",0,"https:\u002F\u002Fgithub.com\u002Fxiaden\u002FSkyScow","https:\u002F\u002Fgithub.com\u002Fxiaden","2026-09-30 22:33:49",{"source":8,"skillName":5,"commands":32,"prompt":42,"zipAvailable":43},[33,36,39],{"tool":34,"command":35},"npx","npx skills add xiaden\u002FSkyScow --skill opencode-plugins",{"tool":37,"command":38},"bunx","bunx skills add xiaden\u002FSkyScow --skill opencode-plugins",{"tool":40,"command":41},"pnpm","pnpm dlx skills add xiaden\u002FSkyScow --skill opencode-plugins","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fxiaden\u002FSkyScow\u002Fblob\u002Fmain\u002Fconfig\u002Fskills\u002Fopencode-plugins\u002FSKILL.md",true,[45,51,55,59,63],{"path":46,"resourceType":47,"resourceTypeDesc":48,"sizeBytes":49,"sourceHtmlUrl":50},"references\u002Fadditional-topics.md","REFERENCE","参考文档",4111,"https:\u002F\u002Fgithub.com\u002Fxiaden\u002FSkyScow\u002Fblob\u002Fmain\u002Fconfig\u002Fskills\u002Fopencode-plugins\u002Freferences\u002Fadditional-topics.md",{"path":52,"resourceType":47,"resourceTypeDesc":48,"sizeBytes":53,"sourceHtmlUrl":54},"references\u002Fchat-hooks.md",3531,"https:\u002F\u002Fgithub.com\u002Fxiaden\u002FSkyScow\u002Fblob\u002Fmain\u002Fconfig\u002Fskills\u002Fopencode-plugins\u002Freferences\u002Fchat-hooks.md",{"path":56,"resourceType":47,"resourceTypeDesc":48,"sizeBytes":57,"sourceHtmlUrl":58},"references\u002Fcustom-tools.md",5772,"https:\u002F\u002Fgithub.com\u002Fxiaden\u002FSkyScow\u002Fblob\u002Fmain\u002Fconfig\u002Fskills\u002Fopencode-plugins\u002Freferences\u002Fcustom-tools.md",{"path":60,"resourceType":47,"resourceTypeDesc":48,"sizeBytes":61,"sourceHtmlUrl":62},"references\u002Fhooks.md",6547,"https:\u002F\u002Fgithub.com\u002Fxiaden\u002FSkyScow\u002Fblob\u002Fmain\u002Fconfig\u002Fskills\u002Fopencode-plugins\u002Freferences\u002Fhooks.md",{"path":64,"resourceType":47,"resourceTypeDesc":48,"sizeBytes":65,"sourceHtmlUrl":66},"references\u002Fstandalone-tools.md",5525,"https:\u002F\u002Fgithub.com\u002Fxiaden\u002FSkyScow\u002Fblob\u002Fmain\u002Fconfig\u002Fskills\u002Fopencode-plugins\u002Freferences\u002Fstandalone-tools.md",[68,74,81,87,94,101],{"skillNo":69,"name":70,"nameZh":6,"description":6,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":71,"categories":72,"keywords":73,"publishedAt":19},"01M7CTNJ49PJ794TEFBCNYYKQM","unquoted-colon","https:\u002F\u002Fgithub.com\u002Fxiaden\u002FSkyScow\u002Fblob\u002Fmain\u002Fconfig\u002Ftools\u002Ftests\u002Ffixtures\u002Fskills\u002Funquoted-colon\u002FSKILL.md",[],[],{"skillNo":75,"name":76,"nameZh":6,"description":77,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":78,"categories":79,"keywords":80,"publishedAt":19},"01M7CTNENFBZPEX63HNSRBCW4T","quoted-description","Use when a plain scalar contains a colon: like this one.","https:\u002F\u002Fgithub.com\u002Fxiaden\u002FSkyScow\u002Fblob\u002Fmain\u002Fconfig\u002Ftools\u002Ftests\u002Ffixtures\u002Fskills\u002Fquoted-description\u002FSKILL.md",[],[],{"skillNo":82,"name":83,"nameZh":6,"description":77,"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},"01M7CTNBBPKA6GMCVEM3GPB59F","block-description","https:\u002F\u002Fgithub.com\u002Fxiaden\u002FSkyScow\u002Fblob\u002Fmain\u002Fconfig\u002Ftools\u002Ftests\u002Ffixtures\u002Fskills\u002Fblock-description\u002FSKILL.md",[],[],{"skillNo":88,"name":89,"nameZh":6,"description":90,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":91,"categories":92,"keywords":93,"publishedAt":19},"01M7CTN4M0SR4Z4TPJMHWC3A3B","work-routing","Canonical authority for who owns the next unit of work — direct work versus delegation, task tiers, bounded localization, the Change DAG size threshold, R&D evaluation routing, progressive research escalation, researcher scope signals, and QA\u002Fsupport owner selection. Use before choosing execution, investigation, design, or QA ownership; do not use to construct dispatch prompts, handoff schemas, or Change DAG\u002FDD tool operation.","https:\u002F\u002Fgithub.com\u002Fxiaden\u002FSkyScow\u002Fblob\u002Fmain\u002Fconfig\u002Fskills\u002Fwork-routing\u002FSKILL.md",[],[],{"skillNo":95,"name":96,"nameZh":6,"description":97,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":98,"categories":99,"keywords":100,"publishedAt":19},"01M7CTMY5AY3NSNHGQJA0M7VP9","update-docs","Update project documentation to match code changes — generate codemaps, refresh READMEs, detect doc\u002Fcode drift using AST analysis. Use when updating documentation after code changes, generating codemaps, verifying doc accuracy, or detecting stale documentation. Do NOT use for writing API reference docs from scratch (use doc-coauthoring) or for creating new skill files (use making-editing-skills).","https:\u002F\u002Fgithub.com\u002Fxiaden\u002FSkyScow\u002Fblob\u002Fmain\u002Fconfig\u002Fskills\u002Fupdate-docs\u002FSKILL.md",[],[],{"skillNo":102,"name":103,"nameZh":6,"description":104,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":105,"categories":106,"keywords":107,"publishedAt":19},"01M7CTMSQD82CPD53C6F07J0R9","skill-loading-system","Explain or troubleshoot OpenCode skill discovery, loading, permissions, availability, or prompt injection.","https:\u002F\u002Fgithub.com\u002Fxiaden\u002FSkyScow\u002Fblob\u002Fmain\u002Fconfig\u002Fskills\u002Fskill-loading-system\u002FSKILL.md",[],[]]