Menu
SkillsMP has collected 43 skills from PaulRBerg/agent-skills. Open a skill to review its source and details.
Showing 40 of 43 collected skills.
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.
Create or polish repo agent context: README.md, AGENTS.md/CLAUDE.md, installed project skills, and other Markdown context 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; fetch the relevant official URL before…
Orchestrate read-only Explore research subagents in any mode, or one to eight Claude subagents to implement an approved plan.
Use for Foundry cast/on-chain actions: prepare, simulate, sign, or broadcast transactions; call contracts; sign messages; encode/decode ABI/calldata; or make RPC calls. For read-only balances/history, prefer evm-atlas.
Use for CoinGecko/cg CLI crypto market data: prices, market cap, trending coins, top gainers/losers, coin search, or historical/OHLC data.
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.
Orchestrate read-only Codex research in any mode, or one to eight Codex agents to implement approved plans from Claude Code or Codex CLI.
Open the CoinGecko historical-data page for a coin/date in Chromium via Chrome DevTools MCP.
Copy the active Claude Code or Codex CLI chat transcript path to the macOS clipboard.
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…
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".
Discover large source-file refactor candidates and propose cohesion- and risk-driven split plans using available semantic tooling.
Use to audit Agent Skills catalogs or installed skill roots for metadata and doc-link issues; optionally apply conservative --fix-safe repairs.
Use to find agent skill installs, repository skill portfolios, duplicate skills, cross-dependencies, invocations, and cross-references across the local machine.
Use to create/scaffold/init a new agent skill under `.agents/skills` in the working directory where invoked.
Create one decision-complete task handoff in its repository or on the Desktop for cross-repository work, and return a command for a fresh interactive Codex session.
Use to find, compare, and recommend current tools, packages, libraries, CLIs, VSCode extensions, agent skills, databases, or infrastructure options for a development task.
Wind down a long-running session fast when the user must leave — freeze new work, collect wrap-up reports from 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.
Archive checked TODO.md tasks into `.ai/todos/YYYY-MM/DD.md`, leaving unchecked tasks.
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.
Use for interactive HTML debriefs or saved HTML findings/reports from the current task.
Cut a release: bump versions, write changelogs, commit, tag.
Audit multiple interdependent repositories for alignment, then plan and apply surgical fixes for drift and duplication.
Harmonize a repository's skill portfolio across catalog and user-installed skills.
Commit staged or intended changes: compose a Conventional Prefix or Natural Language message, then use ai-commit — with --all, --staged, --close, --finding, or --push.
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…
Use Chrome DevTools through PRB's shared attach-only MCP browser for page debugging, browser automation, visual inspection, console or network analysis, performance or memory profiling, and screencasts.
Use for just/justfile task automation: create justfiles, write recipes, configure settings, add modules/attributes, or set up command-runner workflows.
Use when CSV, TSV, or Excel (.xlsx) is the primary input/output: inspect, transform, validate, convert, recalc formulas, or create/fix spreadsheets. Do not trigger when tabular data is incidental.
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.
Use for dependency updates: bump npm/pnpm/yarn/bun packages, check outdated, or run taze.
Refactor naming and repository structure exhaustively while preserving behavior and external contracts.
Use for autoresearch or "optimize X overnight/in a loop"; sets up bounded iterative trials for a measurable optimization target.
Squash a feature branch into one commit via soft reset to the merge base, ready for a clean PR.
Preview or rename a GitHub upstream repo and matching local project folder, update origin, and preserve Codex CLI and Claude Code continuity references.
Audit and fix JavaScript, TypeScript, and Go comments that are verified as stale, orphaned, misleading, or redundant.
Use to build interactive single-file HTML playgrounds, explorers, or tools with visual controls, live preview, and prompt copy-out.
Use for Vitest in TypeScript projects (Node, bun, React/Next.js, Effect): write, run, or debug unit/component tests, mocks, testing utilities, and coverage.