paulrberg/dot-agents

1

task-handoff Create one decision-complete task handoff in its repository or on the Desktop for cross-repository work, return a com…

paulrberg/dot-agents

3

2

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

paulrberg/dot-agents

3

3

agents-brain Create or polish repo agent context: README.md, AGENTS.md/CLAUDE.md, project-installed and source-catalog skills, and…

paulrberg/dot-agents

2

4

brainstorm Brainstorm with the user to generate, combine, and refine non-obvious ideas into a promising concept. Use when the us…

paulrberg/dot-agents

2

5

chromium-browser Use Chrome DevTools through PRB's shared attach-only Chromium browser for browsing, debugging, automation, visual ins…

paulrberg/dot-agents

2

6

cli-coingecko

paulrberg/dot-agents

2

7

codex-handoff Orchestrate read-only Codex research in any mode, or one to eight Codex agents to implement approved plans from Claud…

paulrberg/dot-agents

2

8

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

paulrberg/dot-agents

2

9

interview-me Interview the user about a plan, idea, or design through a short sequence of high-leverage questions, then summarize …

paulrberg/dot-agents

2

10

node-deps-bumper Use for dependency updates: bump npm/pnpm/yarn/bun packages, check outdated, or run taze.

paulrberg/dot-agents

2

11

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

paulrberg/dot-agents

2

12

repo-harmonization Audit multiple interdependent repositories for alignment, then plan and apply surgical fixes for drift and duplicatio…

paulrberg/dot-agents

2

13

skill-harmonization Harmonize a repository's skill portfolio across catalog and user-installed skills.

paulrberg/dot-agents

2

14

skill-writing Create/scaffold/init a project-local agent skill under `.agents/skills` in an ordinary repository; defer to repositor…

paulrberg/dot-agents

2

15

stale-comments-audit Audit and fix JavaScript, TypeScript, and Go comments that are verified as stale, orphaned, misleading, or redundant.

paulrberg/dot-agents

2

16

tool-finder Use to find, compare, and recommend current tools, packages, libraries, CLIs, VSCode extensions, agent skills, databa…

paulrberg/dot-agents

2

17

web-design-guidelines Review UI code for Web Interface Guidelines compliance. Use when asked to "review my UI", "check accessibility", "aud…

paulrberg/dot-agents

2

18

wrap-up Wind down a long-running session fast when the user must leave — freeze new work, preserve active subagents, secure f…

paulrberg/dot-agents

2

19

agents-context-management Create or polish repo agent context: README.md, AGENTS.md/CLAUDE.md, installed project skills, and other Markdown con…

paulrberg/dot-agents

1

20

agents-status Report active Codex and Claude Code sessions in the current repository by default, with optional machine-wide detail.

paulrberg/dot-agents

1

21

audit-stale-comments Audit JavaScript, TypeScript, and Go comments for verified stale, orphaned, misleading, or redundant claims.

paulrberg/dot-agents

1

22

chrome-devtools Uses Chrome DevTools via MCP for efficient debugging, troubleshooting and browser automation. Use when debugging web …

paulrberg/dot-agents

1

23

coingecko-api This skill should be used when the user asks to "get crypto price", "check Bitcoin price", "query token price", "get …

paulrberg/dot-agents

1

24

coingecko-cli Use for CoinGecko/cg CLI crypto market data: prices, market cap, trending coins, top gainers/losers, coin search, or …

paulrberg/dot-agents

1

25

coingecko-open-page Open the CoinGecko historical-data page for a coin/date in Chromium via Chrome DevTools MCP.

paulrberg/dot-agents

1

26

create-skill Use to create/scaffold/init a new agent skill under `.agents/skills` in the working directory where invoked.

paulrberg/dot-agents

1

27

delayed-command This skill should be used when the user asks to "run npm test after 30 minutes", "git commit after 1 hour", "wait 2h …

paulrberg/dot-agents

1

28

evm-chains This skill should be used when the user asks to resolve an EVM chain name or chain ID, find chain metadata such as a …

paulrberg/dot-agents

1

29

find-tool Use to find, compare, and recommend current tools, packages, libraries, CLIs, VSCode extensions, agent skills, databa…

paulrberg/dot-agents

1

30

just-cli This skill should be used when the user asks to "create a justfile", "write just recipes", "configure just settings",…

paulrberg/dot-agents

1

31

notion-cli Use the Notion CLI (`ntn`) to interact with the Notion API, manage workers, and upload files. Use when the user asks …

paulrberg/dot-agents

1

32

playwright-skill Complete browser automation with Playwright. Auto-detects dev servers, writes clean test scripts to /tmp. Test pages,…

paulrberg/dot-agents

1

33

process-cleanup This skill should be used when the user asks to "find zombies", "kill zombie processes", "clean up zombies", "check f…

paulrberg/dot-agents

1

34

refine-prompt This skill should be used when the user asks to "refine a prompt", "optimize a prompt", "improve my prompt", "rewrite…

paulrberg/dot-agents

1

35

sablier-writing This skill should be used when writing content for Sablier, including "write a blog post", "create a case study", "dr…

paulrberg/dot-agents

1

36

template-ts-node This skill should be used when the user asks to "create a TypeScript project", "set up Node.js project", "scaffold ne…

paulrberg/dot-agents

1

37

typescript This skill should be used when the user asks to "apply TypeScript style conventions", "organize types alphabetically"…

paulrberg/dot-agents

1