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.
GoogleSkillgoogle-gemini/gemini-cli/tools/gemini-cli-bot/.gemini/skills/metrics/SKILL.md
Expertise in analyzing time-series repository health metrics, investigating root causes, and proposing proactive workflow improvements.
Steady3 mentions in 2 weeks
20 projects use a version of this
denolandDeletes or force-pushesSkilldenoland/deno/.claude/skills/issue-triage/SKILL.md
Triage a Deno GitHub issue — reproduce bugs, classify, label, and comment with findings. Use when asked to triage an issue or when an issue number/URL is provided for triage.
63 projects use a version of this
denolandCopilot instructionsdenoland/deno/.github/copilot-instructions.md
derefs 2. **Public API leaks** — internal fields accidentally exposed in public return types 3. **Security** — unsafe blocks with incorrect safety invariants, unsanitized inputs at system boundaries 4. **Missing error handling
No other project uses it yet
pytorchSkillpytorch/pytorch/.agents/skills/fix-issue/SKILL.md
Fix bugs reported in PyTorch GitHub issues by reproducing, root-causing, and implementing a fix in the local working tree. Use when the user asks to fix a PyTorch GitHub issue.
pytorchSkillpytorch/pytorch/.agents/skills/skill-writer/SKILL.md
Guide users through creating Agent Skills for Claude Code. Use when the user wants to create, write, author, or design a new Skill, or needs help with SKILL.md files, frontmatter, or skill structure.
pytorchSkillpytorch/pytorch/.agents/skills/triaging-issues/SKILL.md
Triages GitHub issues by routing to oncall teams, applying labels, and closing questions. Use when processing new PyTorch issues or when asked to triage an issue.
ruvnetReads credentialsAGENTS.mdruvnet/wifi-densepose/AGENTS.md
complements `CLAUDE.md`; scoped `AGENTS.md` files may add local rules but must not weaken the security, evidence, or release requirements here. RuView is a camera-free RF perception system. Production Rust
1 project uses a version of this
ruvnetReads credentialsCLAUDE.mdruvnet/wifi-densepose/CLAUDE.md
them. ## Contributor metaharness (`@ruvnet/ruview@0.4.0`) ADR-283 defines the current community metaharness. It adds secure local Claude/Codex execution, a reviewed shared brain, default-deny MCP mutation policy, and gated Darwin/Flywheel
1 project uses a version of this
ruvnetSkillruvnet/wifi-densepose/.claude/skills/agentdb-learning/SKILL.md
Create and train AI learning plugins with AgentDB's 9 reinforcement learning algorithms. Includes Decision Transformer, Q-Learning, SARSA, Actor-Critic, and more. Use when building self-learning agents, implementing RL, or optimizing agent behavior through experience.
32 projects use a version of this
Often used withV3 DDD Architectureagent-agentV3 Memory Unification
ruvnetReads credentialsSkillruvnet/wifi-densepose/.claude/skills/github-code-review/SKILL.md
Comprehensive GitHub code review with AI-powered swarm coordination
Often used withV3 CLI Modernizationnative-mcpagentic-jujutsu
ruvnetReads credentialsSkillruvnet/wifi-densepose/.claude/skills/github-multi-repo/SKILL.md
Multi-repository coordination, synchronization, and architecture management with AI swarm orchestration
Often used withV3 DDD Architectureworker-benchmarksagent-agent
ruvnetSkillruvnet/wifi-densepose/.claude/skills/github-project-management/SKILL.md
Comprehensive GitHub project management with swarm-coordinated issue tracking, project board automation, and sprint planning
Often used withV3 DDD Architectureworker-benchmarksagent-agent
ruvnetReads credentialsSkillruvnet/wifi-densepose/.claude/skills/github-release-management/SKILL.md
Comprehensive GitHub release orchestration with AI swarm coordination for automated versioning, testing, deployment, and rollback management
Often used withV3 Core Implementationagentic-jujutsuV3 DDD Architecture
ruvnetReads credentialsSkillruvnet/wifi-densepose/.claude/skills/github-workflow-automation/SKILL.md
Advanced GitHub Actions workflow automation with AI swarm coordination, intelligent CI/CD pipelines, and comprehensive repository management
Often used withV3 DDD Architectureworker-benchmarksagent-agent
ruvnetReads credentialsSkillruvnet/wifi-densepose/.claude/skills/hooks-automation/SKILL.md
Automated coordination, formatting, and learning from Claude Code operations using intelligent hooks with MCP integration. Includes pre/post task hooks, session management, Git integration, memory coordination, and neural pattern training for enhanced development workflows.
Often used withV3 Core Implementationagentic-jujutsuV3 DDD Architecture
ruvnetSkillruvnet/wifi-densepose/.claude/skills/sparc-methodology/SKILL.md
SPARC (Specification, Pseudocode, Architecture, Refinement, Completion) comprehensive development methodology with multi-agent orchestration
Often used withV3 Core Implementationagentic-jujutsuV3 DDD Architecture
ruvnetSkillruvnet/wifi-densepose/.claude/skills/stream-chain/SKILL.md
Stream-JSON chaining for multi-agent pipelines, data transformation, and sequential workflows
Often used withV3 DDD Architectureworker-benchmarksagent-agent
ruvnetSkillruvnet/wifi-densepose/.claude/skills/swarm-advanced/SKILL.md
Advanced swarm orchestration patterns for research, development, testing, and complex distributed workflows
Often used withV3 CLI Modernizationagentic-jujutsubrowser
ruvnetSkillruvnet/wifi-densepose/.claude/skills/v3-integration-deep/SKILL.md
Deep agentic-flow@alpha integration implementing ADR-001. Eliminates 10,000+ duplicate lines by building claude-flow as specialized extension rather than parallel implementation.
Often used withagentic-jujutsuflow-nexus-neuralflow-nexus-platform
ruvnetSkillruvnet/wifi-densepose/.claude/skills/v3-performance-optimization/SKILL.md
Achieve aggressive v3 performance targets: 2.49x-7.47x Flash Attention speedup, 150x-12,500x search improvements, 50-75% memory reduction. Comprehensive benchmarking and optimization suite.
Often used withagent-agentagent-analyze-code-qualityagent-app-store
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.
