Downey6689Skilladvanced-evaluation
Downey6689/skills/advanced-evaluation/SKILL.md
Advanced LLM-as-judge evaluation. Invoke when you need rubrics, pairwise comparisons, or bias mitigation.
Find the best CLAUDE.md, AGENTS.md and Claude skills
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.
Your trail
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.
Worked for most · soon
Downey6689SkillDowney6689Skillbdi-mental-states
Downey6689/skills/bdi-mental-states/SKILL.md
Transforms external RDF context into BDI mental states. Invoke when modeling beliefs, desires, and intentions.
Downey6689Skillbrainstorming
Downey6689/skills/brainstorming/SKILL.md
You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.
Often used withchinese-code-reviewaddskillchinese-commit-conventions
Downey6689Skillcontext-compression
Downey6689/skills/context-compression/SKILL.md
Compresses long sessions into high-signal summaries. Invoke when history/tool outputs are too large to keep.
Downey6689Skillcontext-degradation
Downey6689/skills/context-degradation/SKILL.md
Diagnoses context failure modes. Invoke when agents forget, get distracted, or show lost-in-the-middle behavior.
Downey6689Skillcontext-fundamentals
Downey6689/skills/context-fundamentals/SKILL.md
Explains context engineering basics. Invoke when discussing context windows, attention limits, or context budgeting.
Often used withlong-horizon-promptingadvanced-evaluation
Downey6689Skillcontext-optimization
Downey6689/skills/context-optimization/SKILL.md
Optimizes context usage with masking/caching/compaction. Invoke when you need lower cost or higher reliability.
Often used withlong-horizon-promptingadvanced-evaluation
Downey6689Skilldispatching-parallel-agents
Downey6689/skills/dispatching-parallel-agents/SKILL.md
Use when facing 2+ independent tasks that can be worked on without shared state or sequential dependencies
Often used withchinese-code-reviewdiagnosing-superpowersworkflow-runner
Downey6689Skillevaluation
Downey6689/skills/evaluation/SKILL.md
Builds evaluation frameworks for agents. Invoke when measuring quality, preventing regressions, or setting metrics.
Downey6689Skillexecuting-plans
Downey6689/skills/executing-plans/SKILL.md
Use when you have a written implementation plan to execute in a separate session with review checkpoints
Often used withchinese-code-reviewdiagnosing-superpowersworkflow-runner
Downey6689Skillfilesystem-context
Downey6689/skills/filesystem-context/SKILL.md
Uses filesystem for dynamic context discovery. Invoke when organizing docs or loading information just-in-time.
Downey6689Skillfinishing-a-development-branch
Downey6689/skills/finishing-a-development-branch/SKILL.md
Use when implementation is complete, all tests pass, and you need to decide how to integrate the work - guides completion of development work by presenting structured options for merge, PR, or cleanup
Often used withchinese-code-reviewdiagnosing-superpowersworkflow-runner
Downey6689Skillhosted-agents
Downey6689/skills/hosted-agents/SKILL.md
Guidance for hosted/sandboxed agents. Invoke when running background agents in isolated VMs or multi-client setups.
Downey6689Skillmemory-systems
Downey6689/skills/memory-systems/SKILL.md
Designs agent memory (short/long-term). Invoke when deciding what to persist, retrieve, and ground responses with.
Often used withlong-horizon-promptingcontext-fundamentalsadvanced-evaluation
Downey6689Skillmulti-agent-patterns
Downey6689/skills/multi-agent-patterns/SKILL.md
Designs multi-agent architectures. Invoke when splitting work across agents or coordinating orchestrator/peers.
Often used withlong-horizon-promptingcontext-degradationadvanced-evaluation
Downey6689Skillproject-development
Downey6689/skills/project-development/SKILL.md
Methodology for building LLM projects. Invoke when moving from idea to agent pipeline, APIs, and structured outputs.
Downey6689Skillreceiving-code-review
Downey6689/skills/receiving-code-review/SKILL.md
Use when receiving code review feedback, before implementing suggestions, especially if feedback seems unclear or technically questionable - requires technical rigor and verification, not performative agreement or blind implementation
Often used withchinese-code-reviewdiagnosing-superpowersrequesting-code-review
Downey6689Skillrequesting-code-review
Downey6689/skills/requesting-code-review/SKILL.md
Use when completing tasks, implementing major features, or before merging to verify work meets requirements
Often used withchinese-code-reviewdiagnosing-superpowersworkflow-runner
Downey6689Skillsubagent-driven-development
Downey6689/skills/subagent-driven-development/SKILL.md
Use when executing implementation plans with independent tasks in the current session
Often used withchinese-code-reviewdiagnosing-superpowerswebhook-subscriptions
Downey6689Skillsystematic-debugging
Downey6689/skills/systematic-debugging/SKILL.md
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes
Often used withchinese-code-reviewdiagnosing-superpowerschinese-commit-conventions
Agent instruction files
What are agent instruction files?
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 or AGENTS.md?
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.
What is a skill?
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.
Can I search my own team's files too?
Your agents already can, over MCP, limited to the files you're allowed to read. Searching them from this page is coming.