obra/
superpowers
obra/superpowersSkills
An agentic skills framework & software development methodology that works.
285k
1 add
Skill pack for Claude Code and Codex
This repo packages a large set of agent skills for common builder tasks like research, code review, refactors, handoffs, and repo maintenance. The skills live in separate folders and are backed by scripts and tests that help publish, check, and sync them.
70 stars•3 forks•Python•Updated 7d ago
Who it's for
Builders who want reusable agent skills for Claude Code, Codex, or other compatible agents.
What it delivers
You can add ready-made skills to your agent workflow instead of recreating instructions for each task.
What it does
Many task-specific skills
Includes skills for brainstorming, code polishing, fresh-eyes review, handoffs, repo renames, dependency updates, and more.
Agent-focused context files
Ships `CLAUDE.md`, `AGENTS.md`, and `.claude/settings.json` to shape how agents work in the repo.
Publishing and validation scripts
Includes scripts such as `scripts/publish-skills.ts`, `scripts/readme-skills-check.ts`, and `scripts/sync-invocation-policy.ts`.
Test coverage for skills
Has matching test folders under `tests/` for many skills to keep behavior checked.
Cross-agent orientation
Explicitly aims to work across agents, while being primarily built for Claude Code and Codex.
How to get it
- 1Run
bunx skills add PaulRBerg/agent-skills
README
Agent Skills
PRB's collection of AI agent skills. Designed to work across agents, but primarily built for Claude Code and Codex.
[!WARNING] This catalog intentionally reflects Paul's preferred tools, defaults, safety boundaries, and writing voice; it is not a neutral template. If you install it, review every workflow and customize it for 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-brain | Create or polish README.md, AGENTS.md, context docs, and existing skills |
| agents-docs | Fetch current official Codex and Claude Code docs, including hooks/trust |
| agents-introspection | Retrospect on Codex/Claude Code transcript history |
| autoresearch | Autonomous experiment loop |
| brainstorm | Co-create novel ideas and converge on a testable concept |
| claude-handoff | Delegate approved Claude plans to Sonnet or Opus subagents |
| chromium-browser | Shared Chromium browsing, DevTools automation, and Wayback research |
| cli-cast | Foundry cast CLI guidance |
| cli-coingecko | CoinGecko CLI for prices and market data |
| cli-gh | GitHub CLI operations |
| cli-just | Just command runner guidance |
| codebase-design | Shared vocabulary and principles for designing deep modules |
| codex-handoff | Delegate approved plans to Codex agents from Claude Code or Codex CLI |
| code-polish | Simplify and/or risk-profiled review with autofix |
| commit | Semantic commit messages with deterministic ai-commit mechanics |
| copy-transcript-path | Copy the active Claude Code or Codex CLI transcript path |
| skill-writing | Bootstrap a new agent skill |
| effect-ts | Effect 3 patterns and source-aligned guidance |
| evm-atlas | EVM lookup + DEX transaction/order interpretation |
| frontend-design | Distinctive, subject-specific frontend design |
| fresh-eyes-sweep | Meticulous whole-repository audit and verified fixes |
| git-squash | Squash PR branch with semantic commit message |
| grill-me | Relentlessly stress-test plans and designs |
| html-debrief | Interactive HTML task debriefs |
| html-playground | Interactive single-file HTML playgrounds |
| interview-me | Clarify plans and ideas through a focused, lightweight interview |
| wrap-up | Wind down a session fast: collect subagent wrap-ups and hand off the rest |
| large-file-refactor | Large source-file report and Serena split plans |
| naming-refactor | Exhaustive behavior-preserving repository naming refactor |
| node-deps-bumper | Node.js dependency updates via taze |
| Exact local PDF reading and manipulation on macOS | |
| release-bumper | Release workflow with changelog, tagging |
| repo-harmonization | Audit and align multiple interdependent repositories |
| repo-rename | Rename GitHub repo, folder, and agent thread references |
| skill-doctor | Audit Agent Skills catalogs and installed skill roots |
| skill-harmonization | Harmonize repository and user-installed skill portfolios |
| skill-map | Find skill dependencies and references across machine |
| spreadsheets | Opinionated CSV/TSV/XLSX wrangling on macOS |
| stale-comments-audit | Audit and fix stale comments in JavaScript, TypeScript, and Go |
| tailwind-css | Tailwind CSS v4 styling guidance |
| task-handoff | Create one single- or cross-repository Codex task handoff plan |
| todo-archive | Archive checked TODO.md tasks into .ai/todos |
| tool-finder | Find and compare current developer tools |
| vitest | Vitest test writing and debugging |
| yeet | GitHub contribution workflows |
Forked Skills
| Skill | Source |
|---|---|
| html-playground | anthropics/claude-plugins-official: playground |
Some mechanical skills pin model: sonnet in their frontmatter so they do not spend a more capable inherited model
where deterministic tooling already carries the workflow.
References
License
MIT
Files in the repo
Repository payload•20 top-level entries
- .agents
- .claude
- .husky
- .serena
- scripts
- skills
- tests
- .gitignore
- .lintstagedrc.mjs
- .prettierignore
- .prettierrc.yml
- .shellcheckrc
- AGENTS.md
- bun.lock
- CLAUDE.md
- justfile
- LICENSE.md
- package.json
- README.md
- tsconfig.json
Discussion (0)
Ask about usage, or say what you built with itSign in to join the discussion.
No comments yet. Be the first to say what this is good for.
More skills
Graphify-Labs/graphifySkills
Turn any codebase, with its docs, SQL schemas, configs, and PDFs, into a queryable knowledge graph. A /graphify skill for Claude Code, Cursor, Codex, and Gemini CLI: local deterministic AST parsing, every edge explained, no vector store.
117k
1 add
Vincentwei1021/
anything2explainer
Topic in, narrated explainer video out. A Claude Code / Codex skill that turns any topic into a black-canvas motion-graphics explainer video with TTS voiceover, subtitles and a chapter progress bar. Chinese or English; every frame drawn in code with Remotion.
666
anthropics/skillsSkills
Public repository for Agent Skills
176k
career-ops-hq/career-opsSkills
Open-source AI job search: scan job portals, evaluate listings into a structured A-H report with a global 1-5 score, tailor your CV, track applications — runs locally in your AI coding CLI (Claude Code, Codex, OpenCode, Antigravity…)
71k
addyosmani/agent-skillsSkills
Production-grade engineering skills for AI coding agents.
93k