PaulRBerg/agent-skills

PRB's collection of agent skills

This repository also configures its own agents. See what agent-skills tells them →

70Stars on the repository
48Mods indexed here, across every type
yesterdayLast push, which is what freshness is scored on
MITLicence, which decides whether bodies are shown

agents-brain

01

PaulRBerg/agent-skills

Skill Claude CodeCodex

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

not rated 70 changed yesterday A 37 tokens original MIT

agents-docs

02

PaulRBerg/agent-skills

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.

not rated 70 yesterday A 55 tokens original MIT

PaulRBerg/agent-skills

Skill Claude CodeCodex

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.

not rated 70 yesterday A 46 tokens original MIT

autoresearch

04

PaulRBerg/agent-skills

Skill Claude CodeCodex

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

not rated 70 yesterday A 32 tokens original MIT

brainstorm

05

PaulRBerg/agent-skills

Skill Codex

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.

not rated 70 yesterday A 48 tokens original MIT

chromium-browser

06

PaulRBerg/agent-skills

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.

not rated 70 yesterday A 47 tokens original MIT

claude-handoff

07

PaulRBerg/agent-skills

Skill Claude CodeCodex

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

not rated 70 yesterday A 31 tokens copy · 92% MIT

cli-cast

08

PaulRBerg/agent-skills

Skill Claude CodeCodex

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.

not rated 70 yesterday A 45 tokens original MIT

cli-coingecko

09

PaulRBerg/agent-skills

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.

not rated 70 yesterday A 42 tokens original MIT

cli-gh

10

PaulRBerg/agent-skills

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.

not rated 70 yesterday A 47 tokens original MIT

cli-just

11

PaulRBerg/agent-skills

Skill Claude CodeCodex

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

not rated 70 yesterday A 36 tokens original MIT

code-polish

12

PaulRBerg/agent-skills

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.

not rated 70 yesterday A 36 tokens original MIT

codebase-design

13

PaulRBerg/agent-skills

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

not rated 70 yesterday A 57 tokens original MIT

codex-handoff

14

PaulRBerg/agent-skills

Skill Claude CodeCodex

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

not rated 70 yesterday A 36 tokens original MIT

commit

15

PaulRBerg/agent-skills

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.

not rated 70 yesterday A 41 tokens original MIT

PaulRBerg/agent-skills

Skill Claude CodeCodex

Copy the active Claude Code or Codex CLI chat transcript path to the macOS clipboard.

not rated 70 yesterday A 23 tokens original MIT

effect-ts

17

PaulRBerg/agent-skills

Skill Codex

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.

not rated 70 yesterday A 56 tokens original MIT

evm-atlas

18

PaulRBerg/agent-skills

Skill Claude CodeCodex

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 Etherscan/Blockscout/Chainscout; Across, Bungee, deBridge, Hop, Layerswap…

not rated 70 yesterday A 158 tokens original MIT

fresh-eyes-sweep

19

PaulRBerg/agent-skills

Skill Claude CodeCodex

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.

not rated 70 yesterday A 40 tokens original MIT

frontend-design

20

PaulRBerg/agent-skills

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 responsive code, and rendered visual verification.

not rated 70 yesterday A 48 tokens original MIT

git-squash

21

PaulRBerg/agent-skills

Skill Claude CodeCodex

Squash a feature branch into one commit via soft reset to the merge base, ready for a clean PR.

not rated 70 yesterday A 27 tokens original MIT

grill-me

22

PaulRBerg/agent-skills

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".

not rated 70 yesterday A 54 tokens original MIT

html-debrief

23

PaulRBerg/agent-skills

Skill Claude CodeCodex

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

not rated 70 yesterday A 22 tokens original MIT

html-playground

24

PaulRBerg/agent-skills

Skill Codex

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

not rated 70 yesterday A 30 tokens original MIT

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: