PaulRBerg

Prune agent scratch directories on macOS by moving clearly outdated `.ai/` files into `.ai/archive/YYYY-MM-DD/` and trashing clearly outdated `.cache/` entries, leaving `.ai/todos` untouched.

Create or polish repo agent context: README.md, AGENTS.md/CLAUDE.md, project-installed and source-catalog skills, and other Markdown context docs.

Orchestrate read-only Codex research in any mode, or one to eight Codex agents to implement approved plans from Claude Code or Codex CLI.

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.

Orchestrate read-only Explore research subagents in any mode, or one to eight Claude subagents to implement an approved plan.

Create one decision-complete task handoff in its repository or on the Desktop for cross-repository work, return a command for a fresh interactive Codex session, and recommend Codex subagent delegation for complex tasks.

Use for dependency updates: bump npm/pnpm/yarn/bun packages, check outdated, or run taze.

Use for targeted EVM chain, account, transaction, RPC, explorer, bridge, and DEX evidence: chain name/ID, native symbol, RouteMesh, wallet balances via Blockscan in Chromium, token/NFT holdings/transfers, tx history, funding origin via…

Create or polish repo agent context: README.md, AGENTS.md/CLAUDE.md, project-installed and source-catalog skills, and other Markdown context docs.

Orchestrate read-only Codex research in any mode, or one to eight Codex agents to implement approved plans from Claude Code or Codex CLI.

Audit an entire repository with fresh eyes for correctness errors, bugs, omissions, duplication, inconsistencies, and other evidenced mistakes; fix every safe issue and verify the result.

Audit multiple interdependent repositories for alignment, then plan and apply surgical fixes for drift and duplication.

Wind down a long-running session fast when the user must leave — freeze new work, preserve active subagents, secure finished work, and hand off the remainder via task-handoff.

Use for GitHub PR/issue/discussion workflows: create/update PRs, issues, or discussions and post issue or discussion comments; triggers include yeet.

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.

Create/scaffold/init a project-local agent skill under `.agents/skills` in an ordinary repository; defer to repository instructions that define a source catalog and lifecycle.

Add, remove, or list permanent Caddy-based named localhost apps backed by macOS LaunchAgents. Use for always-on local servers, *.localhost proxies, Caddy routes, or launchd-managed development apps on this machine.

Audit macOS efficiency, background load, cache sprawl, Homebrew cleanup, login items, LaunchAgents, and safe developer cache cleanup. Use for Mac performance, disk cleanup, cache cleanup, background process, launch daemon, or login item audits.

Capture global dotfile changes made by a CLI installer into the chezmoi source, then commit. Use after an installer (curl pipe to sh, npm -g, brew, etc.) edits shell rc files or PATH. Pass the install command as the argument; the skill runs it, diffs what…

Refresh stale CLI-backed skills in PaulRBerg/agent-skills after installed CLI versions advance; update docs from official upstream release docs and set references/version.txt.

Add a new dependency to tool installation scripts

Add custom zsh completions for a tool.

Ignored description

Alpha description

Beta description

Write and debug Foundry tests and Solidity scripts. Use when writing unit, fuzz, fork, or invariant tests, writing bulloak BTT .tree specs (Branching Tree Technique), using cheatcodes, benchmarking gas, measuring coverage, writing deploy scripts, or working…

Write and modify production Solidity contracts in Foundry projects. Use when writing a contract, implementing a function, adding errors, events, or structs, designing contract architecture, optimizing gas, hardening security, planning upgrades, or working in…

Orchestrate read-only Explore research subagents in any mode, or one to eight Claude subagents to implement an approved plan.

This skill should be used when the user asks to "bump version", "release a new version", "bump the version", "prepare a release", "update version numbers", "what version should this be", or mentions version bumping, semver analysis, or release preparation.

This skill should be used when the user asks to "release and bump", "publish and bump", "release to npm and update new-ui", "release and update consumer", "publish and migrate", or mentions releasing a @prb/effect-* package and bumping it in new-ui.

Use when adding a new EVM chain to @prb/crypto-registry and propagating it to the evm-atlas skill in ~/projects/agent-skills, including Chainlist/Chrome DevTools research, wrapped-native enrichment, verification, commits, and surgical skill publication.