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.
ZekiogSkillZekiog/ruflo/.agents/skills/agent-coordination/SKILL.md
Agent spawning, lifecycle management, and coordination patterns. Manages 60+ agent types with specialized capabilities. Use when: spawning agents, coordinating multi-agent tasks, managing agent pools. Skip when: single-agent work, no coordination needed.
Steady55 mentions in 2 weeks
12 projects use a version of this
ZekiogSkillZekiog/ruflo/.agents/skills/agent-coordinator-swarm-init/SKILL.md
Agent skill for coordinator-swarm-init - invoke with $agent-coordinator-swarm-init
Steady55 mentions in 2 weeks
5 projects use a version of this
ZekiogSkillZekiog/ruflo/.agents/skills/agent-crdt-synchronizer/SKILL.md
Agent skill for crdt-synchronizer - invoke with $agent-crdt-synchronizer
Steady55 mentions in 2 weeks
5 projects use a version of this
ZekiogSkillZekiog/ruflo/.agents/skills/agent-data-ml-model/SKILL.md
Agent skill for data-ml-model - invoke with $agent-data-ml-model
Steady55 mentions in 2 weeks
5 projects use a version of this
ZekiogSkillZekiog/ruflo/.agents/skills/agentdb-advanced/SKILL.md
Master advanced AgentDB features including QUIC synchronization, multi-database management, custom distance metrics, hybrid search, and distributed systems integration. Use when building distributed AI systems, multi-agent coordination, or advanced vector search applications.
Steady55 mentions in 2 weeks
30 projects use a version of this
Often used withV3 DDD ArchitectureV3 Memory UnificationV3 Performance Optimization
ZekiogSkillZekiog/ruflo/.agents/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.
Steady55 mentions in 2 weeks
30 projects use a version of this
Often used withV3 DDD ArchitectureV3 Memory UnificationV3 Performance Optimization
ZekiogSkillZekiog/ruflo/.agents/skills/agentdb-memory-patterns/SKILL.md
Implement persistent memory patterns for AI agents using AgentDB. Includes session memory, long-term storage, pattern learning, and context management. Use when building stateful agents, chat systems, or intelligent assistants.
Steady55 mentions in 2 weeks
30 projects use a version of this
Often used withV3 Core Implementationagentic-jujutsuV3 DDD Architecture
ZekiogSkillZekiog/ruflo/.agents/skills/agentdb-optimization/SKILL.md
Optimize AgentDB performance with quantization (4-32x memory reduction), HNSW indexing (150x faster search), caching, and batch operations. Use when optimizing memory usage, improving search speed, or scaling to millions of vectors.
Steady55 mentions in 2 weeks
30 projects use a version of this
Often used withV3 Core Implementationagentic-jujutsuV3 DDD Architecture
ZekiogSkillZekiog/ruflo/.agents/skills/agentdb-vector-search/SKILL.md
Implement semantic vector search with AgentDB for intelligent document retrieval, similarity matching, and context-aware querying. Use when building RAG systems, semantic search engines, or intelligent knowledge bases.
Steady55 mentions in 2 weeks
30 projects use a version of this
Often used withV3 DDD ArchitectureV3 Memory UnificationV3 Performance Optimization
ZekiogSkillZekiog/ruflo/.agents/skills/agent-dev-backend-api/SKILL.md
Agent skill for dev-backend-api - invoke with $agent-dev-backend-api
Steady55 mentions in 2 weeks
5 projects use a version of this
ZekiogSkillZekiog/ruflo/.agents/skills/agent-docs-api-openapi/SKILL.md
Agent skill for docs-api-openapi - invoke with $agent-docs-api-openapi
ZekiogSkillZekiog/ruflo/.agents/skills/agent-github-modes/SKILL.md
Agent skill for github-modes - invoke with $agent-github-modes
Steady55 mentions in 2 weeks
5 projects use a version of this
ZekiogSkillZekiog/ruflo/.agents/skills/agent-github-pr-manager/SKILL.md
Agent skill for github-pr-manager - invoke with $agent-github-pr-manager
Steady55 mentions in 2 weeks
5 projects use a version of this
ZekiogSkillZekiog/ruflo/.agents/skills/agent-goal-planner/SKILL.md
Agent skill for goal-planner - invoke with $agent-goal-planner
Steady55 mentions in 2 weeks
5 projects use a version of this
ZekiogSkillZekiog/ruflo/.agents/skills/agent-gossip-coordinator/SKILL.md
Agent skill for gossip-coordinator - invoke with $agent-gossip-coordinator
Steady55 mentions in 2 weeks
5 projects use a version of this
ZekiogSkillZekiog/ruflo/.agents/skills/agent-hierarchical-coordinator/SKILL.md
Agent skill for hierarchical-coordinator - invoke with $agent-hierarchical-coordinator
Steady55 mentions in 2 weeks
5 projects use a version of this
ZekiogSkillZekiog/ruflo/.agents/skills/agentic-jujutsu/SKILL.md
Quantum-resistant, self-learning version control for AI agents with ReasoningBank intelligence and multi-agent coordination
Steady55 mentions in 2 weeks
14 projects use a version of this
Often used withV3 Core ImplementationV3 DDD ArchitectureV3 Deep Integration
ZekiogSkillZekiog/ruflo/.agents/skills/agent-implementer-sparc-coder/SKILL.md
Agent skill for implementer-sparc-coder - invoke with $agent-implementer-sparc-coder
Steady55 mentions in 2 weeks
5 projects use a version of this
ZekiogSkillZekiog/ruflo/.agents/skills/agent-issue-tracker/SKILL.md
Agent skill for issue-tracker - invoke with $agent-issue-tracker
Steady55 mentions in 2 weeks
5 projects use a version of this
ZekiogSkillZekiog/ruflo/.agents/skills/agent-load-balancer/SKILL.md
Agent skill for load-balancer - invoke with $agent-load-balancer
Steady55 mentions in 2 weeks
5 projects use a version of this
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.
