Platform
OpenAI Codex
Rules, skills, and instructions for OpenAI Codex. Copy them directly or export in the platform's native format.
38 published items · Filter in browse
Writing Tests
Write unit and integration tests for existing code in the project's own ecosystem. Detects the test runner, identifies untested paths, and writes tests with proper mocking, edge cases, and assertio...
Writing Commit Messages
Write clear, conventional commit messages with proper type prefixes, scopes, and body content. Use when the user asks to commit, write a commit message, or review staged changes for a commit.
Visual Qa Testing
Visually QA a web application in the harness's browser tool: screenshot the changed page, read console errors, and check for failed network requests. Use after making UI changes to verify they look...
Verification Before Completion (superpowers skill)
Jesse Vincent's skill that forbids claiming success without running the verification command and reading its output first; evidence before assertions.
Test-Driven Development (superpowers skill)
Jesse Vincent's TDD skill: the iron law (watch the test fail first), red-green-refactor steps, rationalization red flags and a guide to writing good tests.
TDD red/green/refactor loop
Strict red/green/refactor loop with a behavior list, one failing test at a time, and explicit stop points for user confirmation.
Systematic Debugging (superpowers skill)
Jesse Vincent's debugging skill: four-phase root-cause process, root-cause tracing, defense in depth, condition-based waiting, and a test-polluter finder script.
Suggesting Skills
When the user struggles with a task that a known skill could handle, suggest installing or using a skill from the project's `.agents/skills/` directory.
SQL query explainer and optimizer
Explains a SQL query clause by clause, reads EXPLAIN output for scans, misestimates, loops and spills, and proposes verified index and rewrite fixes per engine.
OWASP-oriented security review of a diff
Boundary-tagged diff review that traces inputs to sinks, applies a 13-section OWASP checklist from references/, and reports severity-rated findings with fixes.
Saving Workspace Context
Persist project knowledge that should outlast this conversation: decisions, gotchas, research, and commands. Writes to AGENTS.md or a docs folder the project already uses. Use when the user asks to...
Responsive Testing
Open the app in the harness's browser tool at multiple viewport sizes, screenshot each, and report layout breakage. Use after UI layout changes or when the user asks to verify responsive behavior.
Release notes from merged PRs since last tag
Collects merged PRs and commits since the last tag, classifies by user impact, rewrites in user vocabulary, and adds upgrade steps.
Prompt Engineering
Write effective prompts and system prompts for current LLMs, including reasoning models, tool use, structured output, and prompt caching. Use when the user asks to improve a prompt, design a system...
PR title and body from branch diff
Generates a PR title and body with purpose-grouped changes, evidence-based testing notes, and a risks section from the branch diff.
Parallel Exploring
Explore a large codebase in parallel by launching several read-only subagents that each investigate a different area at once. Use when onboarding onto a new project, understanding architecture, or ...
Blameless incident postmortem
Blameless postmortem template with timeline anchors, TTD/TTM metrics, why-chains, owned action items, and a responder interview guide.
Safe dependency upgrade procedure
Changelog review, one-package-per-commit bumps, frozen-lockfile install, test and typecheck gates, and a written rollback plan.
Dark Mode Testing
Toggle between light and dark mode in the harness's browser tool, screenshot both states, and flag missing token mappings or contrast issues. Use after theme or styling changes, or when the user as...
Conventional Commits from a diff
Writes a Conventional Commits message from the staged diff, matching the repo's existing type and scope style.
Codebase onboarding map
Time-boxed procedure to map an unfamiliar repo (entry points, layers, entities, commands, hotspots) and persist it to a notes file.
API design review with scoring rubric
REST and GraphQL contract review checklist (naming, errors, pagination, versioning, auth) with an 8-dimension, 40-point rubric in references/.
Pydantic AI CLAUDE.md (Python library)
Pydantic AI's real CLAUDE.md/AGENTS.md: contributor philosophy, task-readiness checks, uv workflow, test isolation and coding guidelines for a typed Python library.
Vercel AI SDK AGENTS.md
The AI SDK's 324-line AGENTS.md: repo map, pnpm commands, Zod and JSON-parsing rules, error-class pattern, provider architecture, changesets, per-change-type completion checklists and a Do-Not list.