One search for your own team's files and the public ecosystem. See how real projects write their agent instructions, and bring the good ideas home.
AnthropicCLAUDE.mdanthropics/claude-quickstarts/managed-agents/copilot-kit-ag-ui/CLAUDE.md
components | | `web/src/viz/` | The interactive visuals: SVG charts, sliders, client-side finance math | | `web/src/App.tsx` | The frontend: `CopilotKitProvider` + `CopilotChat` + viz renderers | ## Commands - `npm install`, then `ant apply --yes agents environments` once
AnthropicSkillanthropics/claude-quickstarts/managed-agents/mcp-server-typescript/skill.md
docs and tend to cost debugging time. --- ## Mental model ### Claude Desktop is the frontend, Managed Agents is the backend The Claude you're typing to in Desktop is a **relay
larksuiteSkilllarksuite/cli/skills/lark-apps/SKILL.md
妙搭（Spark/Miaoda）应用开发与托管：应用创建、本地全栈开发、云端生成迭代、创意设计（UI mockup / 可交互原型 / 线框图 / 落地页 / 仪表盘 / 幻灯片 deck / 视觉探索）、AI相关能力和飞书平台能力或者其他外部能力集成、日志/Trace/监控指标/PV/UV 查询、环境变量管理、应用协作者与协作权限设置、应用角色与成员管理、自动化触发器（定时/记录变更/Webhook/飞书审批）。当用户要开发/新建一个系统·工具·平台·应用，或要本地开发 / 云端开发 / 修改 / 部署 / 发布 / 上线 / 拿可分享链接，或用 HTML 做页面·网站·部署到妙搭，或要设计 / design / mockup / prototype / wireframe / 做 PPT / deck / 视觉探索，或提到妙搭/Spark/Miaoda（应用运行时域名形如 *.aiforce.cloud）、应用数据库、应用文件存储、开放 API Key、可见范围、应用协作者/开发权限、应用角色/角色成员、线上日志、接口请求量、错误量、延迟、访问量、环境变量、给妙搭应用配自动化任务/定时触发/审批通过后自动触发时使用。不负责普通云盘文件上传（lark-drive）、飞书文档编辑（lark-doc）、原生幻灯片创建（lark-slides）。
MicrosoftCursor rulemicrosoft/data-formulator/.cursor/rules/dataframe-serialization.mdc
DataFrame Serialization All DataFrame-to-records conversion for API responses, streaming events, or frontend-visible data MUST use the centralized helpers in `data_formulator.datalake.parquet_utils`: | Source type | Helper | |---|---| | `pd.DataFrame
MicrosoftCursor rulemicrosoft/data-formulator/.cursor/rules/dev-guides-first.mdc
Require reading dev-guides before development and keeping docs in sync
MicrosoftCursor rulemicrosoft/data-formulator/.cursor/rules/i18n-no-hardcoded-strings.mdc
No hardcoded UI strings — use i18n translation keys
MicrosoftCursor rulemicrosoft/data-formulator/.cursor/rules/implementation-review-checklist.mdc
Require structural code review after implementation before final response
MicrosoftCursor rulemicrosoft/data-formulator/.cursor/rules/language-injection-conventions.mdc
Language injection conventions for LLM Agent prompts
MicrosoftSkillmicrosoft/data-formulator/.cursor/skills/error-handling/SKILL.md
统一错误处理系统。在添加 API 端点、修改错误处理、添加前端 API 调用、编写错误相关测试时使用。
MicrosoftSkillmicrosoft/data-formulator/.cursor/skills/language-injection/SKILL.md
LLM Agent 多语言注入规范。在修改 Agent 提示词、添加新的 Agent 端点、处理用户可见的后端消息（message_code）时使用。
triggerdotdevCursor ruletriggerdotdev/trigger.dev/.cursor/rules/writing-tasks.mdc
Guidelines for writing Trigger.dev tasks
composio-communitySkillcomposio-community/awesome-codex-skills/deploy-pipeline/SKILL.md
Run end-to-end deploy pipelines across Stripe, Supabase, and Vercel using the Composio CLI. Promote Stripe products, push Supabase migrations, ship Vercel deployments, and verify with post-deploy checks — all from one script.
composio-communitySkillcomposio-community/awesome-codex-skills/developer-growth-analysis/SKILL.md
Analyzes your recent Codex chat history to identify coding patterns, development gaps, and areas for improvement, curates relevant learning resources from HackerNews, and automatically sends a personalized growth report to your Slack DMs.
composio-communitySkillcomposio-community/awesome-codex-skills/skill-creator/SKILL.md
Guide for creating effective skills. This skill should be used when users want to create a new skill (or update an existing skill) that extends Codex's capabilities with specialized knowledge, workflows, or tool integrations.
ag-ui-protocolSkillag-ui-protocol/ag-ui/.github/skills/agui-dojo/SKILL.md
Run the AG-UI Dojo demo viewer locally and wire the AG-UI .NET SDK in as a dojo integration. USE FOR: starting the dojo app (apps/dojo), running the .NET dojo backend (AGUIDojoServer), registering or modifying the ag-ui-dotnet integration (agents.ts/menu.ts/env.ts/files.json), running the dojo Playwright e2e suite for the .NET integration (agUiDotnetTests), or understanding how dojo-e2e.yml runs it in CI. DO NOT USE FOR: generic Playwright validation of arbitrary pages (use agui-playwright-validate), or the docs site (use agui-dotnet-sdk-docs).
ag-ui-protocolSkillag-ui-protocol/ag-ui/.github/skills/agui-dotnet-integration-tests/SKILL.md
Write integration tests for the AG-UI .NET SDK. USE FOR: adding a new AG-UI event type and covering it end-to-end, testing SSE or protobuf streaming through the hosting pipeline, verifying AGUIChatClient maps events to ChatResponseUpdate, multi-turn conversation tests, parameterizing a test over Json/Protobuf transports, adding or updating a GettingStarted sample replay/Verify snapshot. Covers: WebApplicationFactory + DelegatingStreamingChatClient setup, IChatClient-based assertions with Assert.Collection, TransportFormat [Theory] (Json/Protobuf), recording/replay capture infrastructure, and the 8-capture-point Verify baselines. DO NOT USE FOR: unit tests of event serialization (use tests/AGUI.Abstractions.UnitTests) or stream-conversion unit tests (use tests/AGUI.Server.UnitTests).
ag-ui-protocolSkillag-ui-protocol/ag-ui/skills/ag-ui-a2ui-integration/SKILL.md
Use when adding A2UI rendering to any AG-UI-supported framework or custom AG-UI application, scaffolding an AG-UI app that should render A2UI, adapting an AG-UI integration to emit A2UI surfaces, or wiring the AG-UI A2UI middleware/toolkit with a compatible renderer.
open-metadataCLAUDE.mdopen-metadata/OpenMetadata/CLAUDE.md
discovery, observability, and governance — a multi-module project with a Java backend, a React/TypeScript frontend, a Python ingestion framework, and Docker infrastructure. ## Stack at a glance - **Backend**: Java 21 + Dropwizard
open-metadataCopilot instructionsopen-metadata/OpenMetadata/.github/copilot-instructions.md
data governance. This is a multi-module project with Java backend services, React frontend, Python ingestion framework, and comprehensive Docker infrastructure. ## Architecture Overview - **Backend**: Java 21 + Dropwizard REST API framework
open-metadataSkillopen-metadata/OpenMetadata/skills/code-review/SKILL.md
Use to review code changes with a two-stage process - first checking spec/requirements compliance, then code quality. Works on staged changes, branches, or PRs.
Plain text files in a repository that tell a coding agent how the project works: commands to run, conventions to follow and things to avoid. CLAUDE.md, AGENTS.md, cursor rules and skills are the common kinds.
CLAUDE.md is read by Claude Code. AGENTS.md is an open format that Codex, Cursor and other agents read. Many projects keep one and point the other at it.
A folder with a SKILL.md that describes one capability, such as filling PDFs or reviewing code. The agent loads it only when the task calls for it.
Your agents already can, over MCP, limited to the files you're allowed to read. Searching them from this page is coming.
