PaulRBerg/agent-skills

ai-prune

Prune agent scratch directories on macOS by moving clearly outdated `.ai/` files into `.ai/archive/YYYY-MM-DD/` and trashing clearly outdated `.cache/` entries, leaving `.ai/todos` untouched.

原文语言：英语

agents-brain

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

原文语言：英语

codex-handoff

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

原文语言：英语

chromium-browser

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.

原文语言：英语

claude-handoff

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

原文语言：英语

task-handoff

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.

原文语言：英语

node-deps-bumper

Use for dependency updates: bump npm/pnpm/yarn/bun packages, check outdated, or run taze.

原文语言：英语

evm-atlas

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…

原文语言：英语

todo-archive

Archive checked `.ai/TODO.md` tasks into `.ai/todos/YYYY-MM/DD.md`, leaving unchecked tasks.

原文语言：英语

cli-cast

Use for Foundry cast transaction actions: prepare, trace, simulate, sign, or broadcast; sign messages; or encode/decode ABI/calldata. Delegate every standalone RPC read to evm-atlas.

原文语言：英语

cli-gh

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.

原文语言：英语

repo-rename

Preview or rename a GitHub upstream repo and matching local project folder, update origin, and preserve Codex CLI and Claude Code continuity references.

原文语言：英语

yeet

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

原文语言：英语

skill-writing

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.

原文语言：英语

vitest

Use for Vitest in TypeScript projects (Node, bun, React/Next.js, Effect): write, run, or debug unit/component tests, mocks, testing utilities, and coverage.

原文语言：英语

tailwind-css

Use for Tailwind v4 styling: add/fix classes, configure or migrate Tailwind, use tailwind-variants, or tw-animate-css.

原文语言：英语

tool-finder

Use to find, compare, and recommend current tools, packages, libraries, CLIs, VSCode extensions, agent skills, databases, or infrastructure options for a development task.

原文语言：英语

cli-just

Use for just/justfile task automation: create justfiles, write recipes, configure settings, add modules/attributes, or set up command-runner workflows.

原文语言：英语

commit

Commit staged or intended changes: compose a Conventional Prefix or Natural Language message, then use ai-commit — with --all, --staged, --close, --finding, or --push.

原文语言：英语

pdf

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…

原文语言：英语

release-bumper

Cut a release: bump versions, write changelogs, commit, tag.

原文语言：英语

repo-harmonization

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

原文语言：英语

naming-refactor

Refactor naming and repository structure exhaustively while preserving behavior and external contracts.

原文语言：英语

skill-doctor

Use to audit Agent Skills catalogs or installed skill roots for metadata and doc-link issues; optionally apply conservative --fix-safe repairs.

原文语言：英语

skill-map

Use to find agent skill installs, repository skill portfolios, duplicate skills, cross-dependencies, invocations, and cross-references across the local machine.

原文语言：英语

fresh-eyes-sweep

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.

原文语言：英语

agents-docs

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…

原文语言：英语

autoresearch

Use for autoresearch or "optimize X overnight/in a loop"; plans bounded measurable experiment batches, then delegates execution through codex-handoff.

原文语言：英语

code-polish

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.

原文语言：英语

codebase-design

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 or AI-navigable, or when another skill needs the deep-module…

原文语言：英语

html-debrief

Use for interactive HTML debriefs or saved HTML findings/reports from the current task.

原文语言：英语

html-playground

Use to build interactive single-file HTML playgrounds, explorers, or tools with visual controls, live preview, and prompt copy-out.

原文语言：英语

large-file-refactor

Discover large source-file refactor candidates and propose cohesion- and risk-driven split plans using available semantic tooling.

原文语言：英语

spreadsheets

Use when CSV, TSV, or Excel (.xlsx) is the primary input/output: design or review text-table schemas; inspect, transform, validate, convert, or recalc formulas; or create/fix spreadsheets. Do not trigger when tabular data is incidental.

原文语言：英语

wrap-up

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.

原文语言：英语

effect-ts

Use for nontrivial Effect 3 work including services/layers, typed errors, Schema/JSONSchema, Config, runtime/concurrency, @effect/vitest, @effect/ai, @effect/sql, Effect Atom, or @prb/effect-next.

原文语言：英语

cli-coingecko

Use for CoinGecko/cg CLI crypto market data: prices, market cap, trending coins, top gainers/losers, coin search, or historical/OHLC data.

原文语言：英语

brainstorm

Brainstorm with the user to generate, combine, and refine non-obvious ideas into a promising concept. Use when the user wants to brainstorm, ideate, explore possibilities, escape obvious approaches, or find a creative solution.

原文语言：英语

interview-me

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…

原文语言：英语

agents-introspection

Assess recurrence risk for agent behavior using local Codex/Claude Code transcripts and recommend evidence-backed durable fixes to AGENTS.md or skills. Not for routine post-success skill-evolution or agent self-improvement reviews.

原文语言：英语