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.
aaronbrethorstSkillaaronbrethorst/claude-skills/uikit-app-modernization/SKILL.md
Modernizes UIKit apps for multi-window environments by replacing legacy shared-state APIs with context-appropriate modern alternatives. This includes references to mainScreen, interfaceOrientation, application and scene lifecycle, as well as safe area inset updates.
Often used withc-bounds-safety
aaronbrethorstSkillaaronbrethorst/claude-skills/wwdcnotes/SKILL.md
Search and read community notes on Apple WWDC sessions (2010–present) from wwdcnotes.com, without a local checkout. Starts from the site's llms.txt and its machine-readable indexes to find sessions, then fetches the live note page as Markdown and downloads its images (diagrams, slides, sketchnotes) so you can view them for the full picture. Use when the user asks what a WWDC session covered, which sessions discuss an API or framework (SwiftData, App Intents, visionOS…), wants notes, takeaways, or code from a WWDC talk, asks "what's new in X" across WWDC years, or mentions WWDCNotes or wwdcnotes.com.
aaronbrethorstSkillaaronbrethorst/claude-skills/xcodebuildmcp-cli/SKILL.md
Official skill for the XcodeBuildMCP CLI. Use when doing iOS/macOS/watchOS/tvOS/visionOS work (build, test, run, debug, log, UI automation).
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.
