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.
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
cogine-aiSkillcogine-ai/cogine-dev-skillset/skills/peer-review/SKILL.md
Independent second-opinion code review using Codex CLI. Use when: wanting an external AI reviewer's perspective, cross-validating before push, getting a second pair of eyes. Triggers on: '/peer-review', 'codex review', 'second opinion', 'peer review my changes'.
Often used withusfiscaldataresearch-grantsget-available-resources
cogine-aiSkillcogine-ai/cogine-dev-skillset/skills/plan-devex-review/SKILL.md
Use when reviewing a plan or spec for developer-facing API, CLI, SDK, MCP, plugin, integration guide, getting-started documentation, or developer onboarding design before implementation.
Often used withios-cleanplan-tuneios-design-review
cogine-aiSkillcogine-ai/cogine-dev-skillset/skills/planmode-ceo/SKILL.md
Use when reviewing a plan from a founder or product-ceo perspective and you need to challenge premises, choose scope expansion vs hold vs reduction, and push for the best product outcome.
cogine-aiSkillcogine-ai/cogine-dev-skillset/skills/planmode-engineer/SKILL.md
Use when reviewing an execution plan and you need engineering scrutiny across architecture, data flow, diagrams, edge cases, test coverage, and performance.
cogine-aiSkillcogine-ai/cogine-dev-skillset/skills/qa-only/SKILL.md
Use when the user asks for a report-only browser QA pass on a web application, live site, preview URL, authenticated app flow, or release candidate without making code changes.
Often used withlanding-reportland-and-deploypair-agent
cogine-aiSkillcogine-ai/cogine-dev-skillset/skills/review-and-ship/SKILL.md
Review the current branch for bugs, intent fit, and test coverage; run or write tests; commit focused work; open or update a PR.
cogine-aiSkillcogine-ai/cogine-dev-skillset/skills/run-smoke-tests/SKILL.md
Run Playwright smoke tests, debug failures, and verify fixes
cogine-aiSkillcogine-ai/cogine-dev-skillset/skills/security-best-practices/SKILL.md
Use when the user explicitly requests security best practices guidance, a security review or report, or secure-by-default coding help for Python, JavaScript or TypeScript, or Go code.
cogine-aiSkillcogine-ai/cogine-dev-skillset/skills/site-design-audit/SKILL.md
Use when auditing the live design quality of a site without changing code. Trigger on "site-design-audit", design audit, visual QA, AI slop detection, typography review, spacing review, hierarchy review, or requests to review a rendered site and optionally infer DESIGN.md.
cogine-aiSkillcogine-ai/cogine-dev-skillset/skills/site-design-fix/SKILL.md
Use when auditing a live site's design and then fixing the issues in source code. Trigger on "site-design-fix", design fix loop, visual QA with fixes, AI slop cleanup, frontend polish from screenshots, or requests to audit then repair live UI issues.
cogine-aiSkillcogine-ai/cogine-dev-skillset/skills/slow-is-fast/SKILL.md
Research → Plan → Code workflow. Enforces evidence-based reasoning, codebase research, and structured planning before code modifications. Applied automatically for moderate+ tasks.
cogine-aiAGENTS.mdcogine-ai/cogine-dev-skillset/skills/supabase-postgres-best-practices/AGENTS.md
Comprehensive performance optimization guide for Postgres, maintained by Supabase. Contains rules across 8 categories, prioritized by impact to guide automated query optimization and schema design. Reference these guidelines when: - Writing SQL queries or designing schemas - Implementing indexes or query optimization - Reviewing database performance issues - Configuring connection pooling or scaling - Optimizing for Postgres-specific features - Working with Row-Level Security (RLS) Read individual rule files for detailed explanations and SQL examples: Each rule file contains: - Brief…
cogine-aiSkillcogine-ai/cogine-dev-skillset/skills/supabase-postgres-best-practices/SKILL.md
Use when writing, reviewing, or optimizing Supabase or Postgres queries, schema designs, indexes, row-level security policies, or database configuration for performance and correctness.
Often used withsupabaseshadcnfind-skills
cogine-aiAGENTS.mdcogine-ai/cogine-dev-skillset/skills/vercel-react-best-practices/AGENTS.md
Version 1.0.0 Vercel Engineering January 2026 Note: This document is mainly for agents and LLMs to follow when maintaining, generating, or refactoring React and Next.js codebases. Humans may also find it useful, but guidance here is optimized for automation and consistency by AI-assisted workflows. Comprehensive performance optimization guide for React and Next.js applications, designed for AI agents and LLMs. Contains 40+ rules across 8 categories, prioritized by impact from critical (eliminating waterfalls, reducing bundle size) to incremental (advanced patterns). Each…
cogine-aiSkillcogine-ai/cogine-dev-skillset/skills/vercel-react-best-practices/SKILL.md
Use when writing, reviewing, or refactoring React or Next.js code and you need performance-oriented guidance for components, data fetching, rendering, or bundle size decisions.
Often used withdep-refsvercel-composition-patternsnext-upgrade
cogine-aiSkillcogine-ai/cogine-dev-skillset/skills/xianyu-api-client-skill/SKILL.md
这是一个专为闲鱼管家开放平台设计的基础API客户端技能，为所有闲鱼相关操作提供安全、可靠的底层通信能力。本技能处理了所有复杂的认证、签名、错误处理等技术细节，让您能够专注于业务逻辑开发，而无需关心底层API实现。 在使用本技能之前，您必须完成以下配置： 将获取到的密钥信息配置为环境变量，这是最安全的方式： 如果您不想使用环境变量，也可以在代码中直接传入密钥： 本技能采用智能确认机制，确保操作的安全性和准确性： 对于可能产生费用或不可逆影响的操作（如批量创建商品、删除商品），系统会自动暂停并等待用户确认： 首次使用时，系统会自动验证您的API配置是否正确： 当遇到可恢复的错误时，系统会提供修复建议并等待用户选择： 您可以通过以下方式控制交互行为： 本技能是其他闲鱼相关技能的基础依赖： 如果遇到问题，请按以下步骤排查： 配置完成后，您就可以在其他闲鱼技能中无缝使用本技能，或者直接调用其提供的API方法进行自定义开发。
cogine-aiSkillcogine-ai/cogine-dev-skillset/skills/xianyu-automation-skill/SKILL.md
这是一个企业级的闲鱼店铺自动化运营技能，为您提供从商品创建到订单完成的全生命周期智能管理。本技能基于完整的闲鱼管家API体系，实现了真正的"无人值守"运营模式，让您能够专注于核心业务开发，而将日常运营工作完全交给自动化系统处理。 在启用自动化功能前，您需要明确以下运营策略： 首次使用时，系统会引导您完成完整的配置流程： 即使在全自动模式下，系统也会在关键节点请求确认： 完成初始配置后，您就可以享受真正的自动化闲鱼店铺运营体验。系统会按照您的策略自动执行所有日常操作，同时在关键时刻请求您的确认，确保安全性和可控性。
cogine-aiSkillcogine-ai/cogine-dev-skillset/skills/xianyu-product-manager-skill/SKILL.md
这是一个专为AI服务提供商设计的智能商品管理技能，帮助您快速创建、管理和优化闲鱼平台上的AI定制服务商品。本技能基于真实的市场需求和成功案例，提供标准化的商品模板和智能化的批量操作功能，让您能够高效地部署和管理完整的AI服务产品线。 在使用本技能前，您需要明确以下信息： 确定您要提供的AI服务类型，例如： 根据您的服务能力和服务成本，确定价格区间： 准备具体的服务案例和效果数据，用于生成真实可信的商品描述。 本技能提供三种预设的商品模板，每种都经过市场验证： 本技能采用分步骤的智能引导流程，确保每次操作都符合您的预期： 完成API配置后，您可以通过简单的交互式命令快速创建专业的AI服务商品，无需编写任何代码即可享受高效的批量商品管理体验。
cogine-aiSkillcogine-ai/cursourcing/skills/cursourcing/SKILL.md
Delegate a complete implementation, investigation, or debugging unit to Cursor CLI, then let Codex accept and finish the result. Use when the user wants to use Cursor capacity or reduce Codex work through delegation, with resumable sessions and explicit task boundaries.
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.
