PRB's collection of agent skills
This repository also configures its own agents. See what agent-skills tells them →
Skill Claude CodeCodex
Maintain README.md, AGENTS.md/CLAUDE.md, skills, and repo context. Create, scaffold, or initialize AGENTS.md files and project-local agent skills. Use task evidence to delete obsolete skills, merge overlapping skills, and capture recurring workflows.
Skill Codex
Use for current official documentation about Codex, Codex CLI, or Claude Code behavior, configuration, prompting, skills, permissions, tools, surfaces, capabilities, troubleshooting, hooks, app-server, or hook trust. Consult the relevant official source before answering.
Skill Claude CodeCodex
Use local Codex/Claude Code transcripts to assess recurrence risk for agent behavior. Recommend durable fixes to AGENTS.md or skills from that evidence. Not for routine post-success skill-evolution or agent self-improvement reviews.
Skill Codex
Use Chrome DevTools through PRB's shared attach-only Chromium browser for browsing, debugging, automation, visual inspection, console or network analysis, performance or memory profiling, screencasts, and Wayback Machine research.
Skill Claude CodeCodex
Use for Foundry cast transaction actions: prepare, trace, simulate, sign, or broadcast. Also use to sign messages or encode/decode ABI/calldata. Delegate every standalone RPC read to evm-atlas.
Skill Claude CodeCodex
Use for CoinGecko/cg CLI crypto market data: prices, market cap, trending coins, top gainers/losers, coin search, or historical/OHLC data.
Skill Claude CodeCodex
Use for GitHub CLI automation: repository reads, workflow runs, search, codespaces, releases, configuration, or gh command syntax. Use yeet for contribution writes to PRs, issues, comments, or discussions.
Skill Claude CodeCodex
Use for just/justfile task automation: create justfiles, write recipes, configure settings, add modules/attributes, or set up command-runner workflows.
Skill Claude CodeCodex
Polish changed code when the user explicitly asks, or when an active workflow requests post-implementation simplification and risk-profiled review over a fixed file scope.
Skill Codex
Shared vocabulary for designing deep modules. Use when the user wants to design or improve a module's interface, find deepening opportunities, decide where a seam goes, make code more testable, AI-navigable, or agent-legible, choose which invariants to enforce mechanically, or when another skill needs the deep-module…
Skill Claude CodeCodex
Commit staged or intended changes: compose a Conventional Prefix or Natural Language message, then use ai-commit — with --all, --staged, --close, --finding, or --push. Also squash a branch into one commit with --squash.
Skill Claude CodeCodex
Copy the active Claude Code or Codex CLI chat transcript path to the macOS clipboard.
Skill Codex
Use for nontrivial Effect 4 work including services/layers, typed errors, Schema/JsonSchema, Config, runtime/concurrency, @effect/vitest, effect/ai and @effect/ai-, effect/sql and @effect/sql-, Effect Atom (@effect/atom-), or @prb/effect-next.
Skill Claude CodeCodex
Use for targeted EVM chain, account, transaction, RPC, explorer, bridge, and DEX evidence: chain name/ID, native symbol, RouteMesh, wallet balances and DeFi positions via DeBank/Blockscan in Chromium, cross-chain USD portfolio value or net worth, token/NFT holdings/transfers, tx history, funding origin via…
Skill Claude CodeCodex
Audit an entire repository with fresh eyes for correctness errors, bugs, omissions, duplication, inconsistencies, stale, duplicate, or tautological tests, stale comments, and other mistakes supported by evidence. Fix every safe issue and verify the result.
Skill Codex
Use when creating or substantially redesigning web interfaces, landing pages, dashboards, components, or other frontend UI where visual direction and implementation quality matter. Produces subject-specific art direction, accessible code, and rendered visual verification.
Skill Codex
Interview the user relentlessly about a plan or design until every branch of the decision tree has an explicit recorded decision and no open questions remain. Use when user wants to stress-test a plan, get grilled on their design, or mentions "grill me".
Skill Claude CodeCodex
Use to build interactive single-file HTML playgrounds, explorers, or tools with visual controls, live preview, and prompt copy-out, or to save the current task's findings as an interactive HTML debrief/report.
Skill Codex
Interview the user about a plan, idea, or design through a short sequence of high-leverage questions, then summarize the direction and next step. Use when the user wants a relaxed interview, lightweight clarification, or says "interview me", without exhaustive grilling.
Skill Claude CodeCodex
Discover large source-file refactor candidates and propose split plans based on cohesion and risk, using available semantic tooling.
Skill Claude CodeCodex
Refactor naming and repository structure exhaustively while preserving behavior and external contracts.
Skill Claude CodeCodex
Use for dependency updates: bump npm/pnpm/yarn/bun packages, check outdated, or run taze.
Skill Claude CodeCodex
Use when PDF files are the primary input or output: read, compare, reconcile, extract text/tables/images, OCR scans, fill forms, split, merge, rotate, rename, compress, or convert between PDF and images. Optimized for private financial, tax, legal, and health documents on macOS.
Skill Claude CodeCodex
Cut a release: bump versions, write changelogs, commit, tag.
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: