Eliminate unnecessary sharing or partition ownership before adding locks, queues, or coordination. Use when concurrency, locks, queues, shared state, or complex coordination are being considered.
Break work into small units that each end with a proof and order delivery so every next unit builds on verified state. Use when for migrations, sweeps, repeated edits, and stacks.
Call the system the way its consumer does and assert meaningful observable output; avoid mocks or assertions that only mirror internal calls. Use when when writing or evaluating tests.
Make invalid states hard or impossible to represent and parse external primitives into meaningful internal types at the edge. Use at data modeling, API design, or external data ingestion points.
Draw what an app's user sees as a Mermaid statechart from a TLA+ model. States are gray if they work, red if still wrong, and green if fixed. Each bug TLC finds is a numbered path. Use for /statechart, \"show the PM the bug\", or to turn an agreed chart into a TLA+ skeleton.
Write a minimal failing test before implementation, make it pass with the simplest code, and refactor cleanly. Use when implementing bug fixes or features with clear verification targets.
Recover why a system or decision exists by triangulating source history and connected evidence. Use for rationale archaeology and historical questions.
Make polished, continuously moving short films in code (product launch films, UI walkthroughs, animated explainers, motion-design reels and sizzles, kinetic typography posters, app and brand promos, 3D product and character scenes, data stories) and export frame-exact MP4 with an original score. Use when asked to make an animation, motion graphic, promo, teaser, launch video, demo video, explainer, showreel or animated chart, to edit one, or to critique one. Asks style, colours and length up front; offers six style presets. Built on a deterministic DOM + Three.js stage with camera, cursor, typing, hand-drawn marks and a synth, and a direction method that produces films rather than animated slideshows.
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.