Agent Skills
PRB's collection of AI agent skills. Designed to work across agents, but primarily built for Claude Code and Codex.
[!WARNING]
These skills are optimized for my personal setup and workflow. If you install them, do your own due diligence and customize them to fit your stack and agents. No warranties, guarantees, or support are provided — use at your own risk.
Installation
bunx skills add PaulRBerg/agent-skills
Skills
| Skill | Description |
|---|
| agents-context-management | Create or polish README.md, AGENTS.md, and existing skills |
| agents-introspection | Retrospect on Codex/Claude Code transcript history |
| autoresearch | Autonomous experiment loop |
| bump-deps | Node.js dependency updates via taze |
| bump-release | Release workflow with changelog, tagging |
| cli-cast | Foundry cast CLI guidance |
| cli-gh | GitHub CLI operations |
| cli-just | Just command runner guidance |
| code-polish | Simplify and/or risk-profiled review with autofix |
| coingecko-cli | CoinGecko CLI for prices and market data |
| coingecko-historical | Open CoinGecko historical data page in Chromium |
| commit | Git commit with conventional commits |
| create-skill | Bootstrap a new agent skill |
| debrief | Interactive HTML or Markdown task debrief |
| diagnosing-bugs | Loop-first bug diagnosis and regression tests |
| effect-ts | Effect-TS patterns and guidance |
| evm-atlas | EVM chain/account lookup + cross-chain data routing |
| find-tool | Find and compare current developer tools |
| git-squash | Squash PR branch with semantic commit message |
| grill-me | Relentlessly stress-test plans and designs |
| loop-skill | Repeat a skill multiple times with one net report |
| playground | Interactive single-file HTML playgrounds |
| repo-rename | Rename GitHub repo, folder, and agent thread references |
| skill-doctor | Audit Agent Skills catalogs and installed skill roots |
| skill-map | Find skill dependencies and references across machine |
| spreadsheets | Opinionated CSV/TSV/XLSX wrangling on macOS |
| tailwind-css | Tailwind CSS v4 styling guidance |
| todo-archive | Archive checked TODO.md tasks into .ai/todos |
| vitest | Vitest test writing and debugging |
| work | End-to-end task implementation |
| yeet | GitHub contribution workflows |
Forked Skills
Some skills pin model: opus in their frontmatter: their workflows are mechanical enough that Opus-level intelligence is sufficient, so there is no need to spend a more capable default model on them.
References
License
MIT
'%20stop-opacity%3D'0.16'%2F%3E%3Cstop%20offset%3D'1'%20stop-color%3D'rgb(200%2C90%2C60)'%20stop-opacity%3D'0.03'%2F%3E%3C%2FlinearGradient%3E%3C%2Fdefs%3E%3Crect%20width%3D'320'%20height%3D'200'%20fill%3D'url(%23g)'%2F%3E%3Ccircle%20cx%3D'250'%20cy%3D'56'%20r%3D'92'%20fill%3D'rgb(200%2C90%2C60)'%20fill-opacity%3D'0.06'%2F%3E%3Ccircle%20cx%3D'64'%20cy%3D'172'%20r%3D'58'%20fill%3D'rgb(200%2C90%2C60)'%20fill-opacity%3D'0.05'%2F%3E%3C%2Fsvg%3E)
