{
  "markdown": "# Agent Skills\n\nPRB's collection of AI agent skills. Designed to work across agents, but primarily built for\n[Claude Code](https://claude.com/product/claude-code) and [Codex](https://github.com/openai/codex).\n\n> [!WARNING] This catalog intentionally reflects Paul's preferred tools, defaults, safety boundaries, and writing voice;\n> it is not a neutral template. If you install it, review every workflow and customize it for your stack and agents. No\n> warranties, guarantees, or support are provided — use at your own risk.\n\n## Installation\n\n```sh\nbunx skills add PaulRBerg/agent-skills\n```\n\n## Skills\n\n| Skill                | Description                                                               |\n| -------------------- | ------------------------------------------------------------------------- |\n| agents-brain         | Create or polish README.md, AGENTS.md, context docs, and existing skills  |\n| agents-docs          | Fetch current official Codex and Claude Code docs, including hooks/trust  |\n| agents-introspection | Retrospect on Codex/Claude Code transcript history                        |\n| autoresearch         | Autonomous experiment loop                                                |\n| brainstorm           | Co-create novel ideas and converge on a testable concept                  |\n| claude-handoff       | Delegate approved Claude plans to Sonnet or Opus subagents                |\n| chromium-browser     | Shared Chromium browsing, DevTools automation, and Wayback research       |\n| cli-cast             | Foundry cast CLI guidance                                                 |\n| cli-coingecko        | CoinGecko CLI for prices and market data                                  |\n| cli-gh               | GitHub CLI operations                                                     |\n| cli-just             | Just command runner guidance                                              |\n| codebase-design      | Shared vocabulary and principles for designing deep modules               |\n| codex-handoff        | Delegate approved plans to Codex agents from Claude Code or Codex CLI     |\n| code-polish          | Simplify and/or risk-profiled review with autofix                         |\n| commit               | Semantic commit messages with deterministic ai-commit mechanics           |\n| copy-transcript-path | Copy the active Claude Code or Codex CLI transcript path                  |\n| skill-writing        | Bootstrap a new agent skill                                               |\n| effect-ts            | Effect 3 patterns and source-aligned guidance                             |\n| evm-atlas            | EVM lookup + DEX transaction/order interpretation                         |\n| frontend-design      | Distinctive, subject-specific frontend design                             |\n| fresh-eyes-sweep     | Meticulous whole-repository audit and verified fixes                      |\n| git-squash           | Squash PR branch with semantic commit message                             |\n| grill-me             | Relentlessly stress-test plans and designs                                |\n| html-debrief         | Interactive HTML task debriefs                                            |\n| html-playground      | Interactive single-file HTML playgrounds                                  |\n| interview-me         | Clarify plans and ideas through a focused, lightweight interview          |\n| wrap-up              | Wind down a session fast: collect subagent wrap-ups and hand off the rest |\n| large-file-refactor  | Large source-file report and Serena split plans                           |\n| naming-refactor      | Exhaustive behavior-preserving repository naming refactor                 |\n| node-deps-bumper     | Node.js dependency updates via taze                                       |\n| pdf                  | Exact local PDF reading and manipulation on macOS                         |\n| release-bumper       | Release workflow with changelog, tagging                                  |\n| repo-harmonization   | Audit and align multiple interdependent repositories                      |\n| repo-rename          | Rename GitHub repo, folder, and agent thread references                   |\n| skill-doctor         | Audit Agent Skills catalogs and installed skill roots                     |\n| skill-harmonization  | Harmonize repository and user-installed skill portfolios                  |\n| skill-map            | Find skill dependencies and references across machine                     |\n| spreadsheets         | Opinionated CSV/TSV/XLSX wrangling on macOS                               |\n| stale-comments-audit | Audit and fix stale comments in JavaScript, TypeScript, and Go            |\n| tailwind-css         | Tailwind CSS v4 styling guidance                                          |\n| task-handoff         | Create one single- or cross-repository Codex task handoff plan            |\n| todo-archive         | Archive checked TODO.md tasks into .ai/todos                              |\n| tool-finder          | Find and compare current developer tools                                  |\n| vitest               | Vitest test writing and debugging                                         |\n| yeet                 | GitHub contribution workflows                                             |\n\n## Forked Skills\n\n| Skill           | Source                                                                                                                                                 |\n| --------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------ |\n| html-playground | [anthropics/claude-plugins-official: playground](https://github.com/anthropics/claude-plugins-official/tree/main/plugins/playground/skills/playground) |\n\nSome mechanical skills pin `model: sonnet` in their frontmatter so they do not spend a more capable inherited model\nwhere deterministic tooling already carries the workflow.\n\n## References\n\n- [Skills Issues](https://github.com/vercel-labs/skills/issues)\n- [Introducing Skills](https://vercel.com/changelog/introducing-skills-the-open-agent-skills-ecosystem)\n- [dot-claude](https://github.com/PaulRBerg/dot-claude)\n- [dot-agents](https://github.com/PaulRBerg/dot-agents)\n\n## License\n\nMIT\n",
  "bytes": 6377,
  "sha": "7e86e40f4cc7aa358b65fc81e6be75881cddf3185eb33cfce288fb26b3451767",
  "repo_slug": "paulrberg/agent-skills",
  "fonte": "repo",
  "truncated": false,
  "api": "https://agentalog.com/api/listings/skl_paulrberg_agent_skills_bump_deps_372d9533/readme"
}