code-style
49Cursor rule Cursor
Code style conventions (formatting, in-code naming, structure) — loaded on demand for code work, not every chat.
not rated 5 3d ago A 24 tokens
original MIT
Cursor rule Cursor
Error handling patterns — no silent catches, typed errors, errors at the edges — loaded on demand for code work.
not rated 5 3d ago A 22 tokens
original MIT
performance
51Cursor rule Cursor
Performance requirements — budgets, measurement, avoid premature optimization — loaded on demand when performance matters.
not rated 5 3d ago A 17 tokens
original MIT
testing
52Cursor rule Cursor
Testing requirements — what must be tested, coverage floors, unit vs integration vs E2e — loaded on demand for code work.
not rated 5 3d ago A 25 tokens
original MIT
github
53Cursor rule Cursor
GitHub repo hygiene — security policy, CI, rulesets, Releases vs a releases/ folder — load when changing .github/ or community files.
not rated 5 3d ago A 29 tokens
original MIT
Cursor rule Cursor
Explain AI git co-authorship (Cursor/etc.), prevent it, and remove it safely.
not rated 5 3d ago A 1,070 tokens
original MIT
Cursor rule Cursor
Ask when unclear; never guess requirements or product truth.
not rated 5 3d ago A 186 tokens
original MIT
caveman
56Cursor rule Cursor
Terse responses with full technical substance (default full intensity).
not rated 5 3d ago A 338 tokens
original MIT
Cursor rule Cursor
Always enhance user prompts internally before acting (auto/self mode) -- install only with enhance-prompt-auto setup.
not rated 5 3d ago A 360 tokens
original MIT
Cursor rule Cursor needs its repo
Folder and file naming, layout, grouping; fix legacy paths only with permission.
not rated 5 3d ago A 1,135 tokens
original MIT
git-workflow
59Cursor rule Cursor
Git setup, Conventional Commits, backups, and commit/push only with user permission.
not rated 5 3d ago A 929 tokens
original MIT
migration
60Cursor rule Cursor
Safe refactors—moves, renames, and splitting code; update all references before removing the old.
not rated 5 3d ago A 864 tokens
original MIT
ponytail
61Cursor rule Cursor
Ponytail, lazy senior dev mode. Always pick the simplest solution that works.
not rated 5 3d ago A 583 tokens
copy · 94% MIT
Cursor rule Cursor
Read and update project context after every task when context exists.
not rated 5 3d ago A 432 tokens
original MIT
Cursor rule Cursor
Observability requirements — structured logs, spans, metrics on new endpoints — loaded on demand for ops-sensitive work.
not rated 5 3d ago A 21 tokens
original MIT
Cursor rule Cursor
Prompt quality rules - clarity, precision, scope, output format, measurability, must-nots - loaded on demand for prompt engineering or when building new agent instructions.
not rated 5 3d ago A 33 tokens
original MIT
security
65Cursor rule Cursor
Security requirements — input validation at trust boundaries, secret handling, auth — loaded on demand for security-sensitive work.
not rated 5 3d ago A 21 tokens
original MIT
a11y
66Skill Claude CodeCodex
Run an accessibility audit — keyboard nav, ARIA, contrast, focus, labels, landmarks — and report gaps against WCAG 2.2 AA. Reports, does not auto-fix. Automation-first; asks only for the target surface. Use whenever the user wants an accessibility audit, a WCAG check, or runs /a11y, or after building any UI component.
not rated 5 3d ago A 81 tokens
original MIT
architect
67Skill Claude CodeCodex
Think through what you are about to build like a senior engineer before writing any code. Surfaces decisions, aligns on language, and produces a clear implementation plan written to context/plan.md. Automation-first — answers its own questions from the context system and only surfaces genuinely blocking decisions. Use…
not rated 5 3d ago A 114 tokens
original MIT
cleanup
68Skill Claude CodeCodex
Run a focused tech-debt cleanup pass — dead code, duplicate helpers, stale deps, unused exports, drift from conventions — and produce a safe, ordered removal plan. Automation-first; asks only before destructive removals. Use whenever the user wants a cleanup pass, to reduce tech debt, or runs /cleanup. Distinct from…
not rated 5 3d ago A 76 tokens
original MIT
groundwork
69Skill Claude CodeCodex
Scaffold and continuously improve a project's shared context system — a context/ folder plus AGENTS.md, CLAUDE.md, and README.md — so AI agents build within a defined, accurate, modern structure instead of improvising. Self-improving; every run and every use makes the context more detailed and more true.…
not rated 5 3d ago A 132 tokens
original MIT
imprint
70Skill Claude CodeCodex
After building any UI component, extract the visual patterns that matter for consistency and save them to context/memory/ui-registry.md, so every component built afterward matches what came before. Uses context/design-system.md (tokens, rules) as the standard and context/design/ as the reference. Runs automatically…
not rated 5 3d ago A 122 tokens
original MIT
postmortem
71Skill Claude CodeCodex
Write a postmortem from an incident timeline and contributing factors — timeline, impact, root cause, contributing factors, action items with owners. Automation-first; asks only when the timeline is unclear. Use whenever the user wants to write a postmortem, an incident report, or runs /postmortem, after /recover has…
not rated 5 3d ago A 74 tokens
original MIT
recover
72Skill Claude CodeCodex
When something goes wrong during a build, diagnose what type of failure it is before deciding how to respond — targeted fix, hard reset, or full rethink. Uses the context system to tell a local bug apart from a polluted session or a wrong foundation, and routes a rethink back through /architect. Automation-first …
not rated 5 3d ago A 120 tokens
original MIT
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: