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.
weirdgmeReads credentialsSkillweirdgme/Claude-code-infrastructure-showcase/.claude/skills/route-tester/SKILL.md
Test authenticated routes in the your project using cookie-based authentication. Use this skill when testing API endpoints, validating route functionality, or debugging authentication issues. Includes patterns for using test-auth-route.js and mock authentication.
weirdgmeSkillweirdgme/Claude-code-infrastructure-showcase/.claude/skills/skill-developer/SKILL.md
Create and manage Claude Code skills following Anthropic best practices. Use when creating new skills, modifying skill-rules.json, understanding trigger patterns, working with hooks, debugging skill activation, or implementing progressive disclosure. Covers skill structure, YAML frontmatter, trigger types (keywords, intent patterns, file paths, content patterns), enforcement levels (block, suggest, warn), hook mechanisms (UserPromptSubmit, PreToolUse), session tracking, and the 500-line rule.
weirdgmeSkillweirdgme/Claude-code-infrastructure-showcase/.claude/skills/sre/SKILL.md
Comprehensive guide for implementing SRE practices: SLI/SLO/SLA definitions, error budgets, incident management, on-call best practices, chaos engineering, observability, and reliability patterns for production systems. Enable teams to build and operate reliable, scalable systems by applying software engineering principles to infrastructure and operations challenges. Automatically activates when working on: - Defining SLIs, SLOs, and SLAs - Managing error budgets - Incident response and management - On-call rotation and procedures - Observability and monitoring - Chaos engineering and resilience testing - Capacity…
weirdgmeSkillweirdgme/Claude-code-infrastructure-showcase/.claude/skills/systems-engineering/SKILL.md
Systems engineering and administration covering Linux and Windows administration, networking fundamentals, performance tuning, configuration management (Ansible/Chef/Puppet), system monitoring, shell scripting (bash/PowerShell), and troubleshooting. Use when managing Linux or Windows systems, optimizing performance, automating operations, or debugging system issues. (project)
weirdgmeSkillweirdgme/Claude-code-infrastructure-showcase/.claude/skills/technical-leadership/SKILL.md
For engineering managers who need to make sound technical decisions without being hands-on. You don't need to be the best coder on your team. You need to ask the right questions, evaluate proposals effectively, and make decisions that balance technical excellence with business needs. You're a manager who needs help with: - Reviewing architecture proposals from your team - Evaluating technical decisions (build vs buy, technology choices) - Assessing technical risk without deep expertise - Prioritizing technical debt vs features…
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.
