jonmumm/skills

1

dont-use-use-effect Avoid unnecessary useEffect in React components. Most uses of useEffect are anti-patterns — derived state, event-driv…

jonmumm/skills

67

2

react-composable-components Write and refactor React components to be small, composable, and customizable, doing one thing well. Improve renderin…

jonmumm/skills

44

3

grill-me Invoke this skill anytime you are creating a plan—such as crafting an RFC, writing a PRD, starting a new app, or pro…

jonmumm/skills

43

4

expo-testing Build, install, and test Expo/React Native apps on simulators and physical devices. Use when asked to "run on simulat…

jonmumm/skills

40

5

offensive-typesafety Invoke this skill when setting up new tech stacks, configuring project architecture, or replacing untyped boundaries …

jonmumm/skills

34

6

mutation-testing Run and interpret Stryker mutation testing; kill survivors to reach ≥95% score. Use when running mutation tests, sett…

jonmumm/skills

33

7

vsdd Verified Spec-Driven Development (VSDD) — a rigorous AI-native engineering methodology that fuses Spec-Driven Develop…

jonmumm/skills

32

8

wide-events-logging Implement observability using the Wide Events (Canonical Log Lines) pattern. Instead of scattering logs throughout a…

jonmumm/skills

32

9

react-render-performance Minimize unnecessary React re-renders when consuming external state (XState, @xstate/store, Zustand, Redux, Nanostore…

jonmumm/skills

30

10

create-agents-md Bootstrap AGENTS.md as a short table-of-contents plus a structured docs/ directory (architecture, product specs, acce…

jonmumm/skills

28

11

swarm A multi-agent AI development workflow. Front-loads planning questions (grill-me), then launches parallel agents in Gi…

jonmumm/skills

27

12

design-principle-enforcer Relentlessly critiques code against classic software engineering principles (SOLID, separation of concerns) to preven…

jonmumm/skills

26

13

autoresearch A hypothesis-generating loop that validates itself, run entirely inside Claude Code. Claude proposes a change, runs a…

jonmumm/skills

24

14

deploy-verify Deploy Cloudflare Workers and verify changes work in staging/preview. Use when asked to "deploy", "ship", "push to st…

jonmumm/skills

23

15

seam-tester Focuses exclusively on writing robust integration tests at system boundaries (seams) rather than writing brittle, sha…

jonmumm/skills

22

16

adr-keeper Create and maintain Architectural Decision Records (ADRs) with date-named files sorted like migrations. Use when maki…

jonmumm/skills

18

17

nightshift Autonomous AFK development loop. Sequentially works through a specs/bugs backlog: grill-me preflight → evals-first su…

jonmumm/skills

15

18

ralph-tdd Ralph TDD loop — autonomous coding with TDD and mutation testing. Use when running autonomous coding loops, implement…

jonmumm/skills

14

19

tlaplus Formal verification of system designs using TLA+ and the TLC model checker. Models concurrent state machines, finds r…

jonmumm/skills

14

20

ralph-creator Create AFK Ralph loop scripts for any task. Interrogates the user to nail down requirements, then generates a complet…

jonmumm/skills

13

21

ralph-dogfooding Ralph dogfooding loop — autonomous exploratory QA using Playwright MCP and Linear. Use when asked to "dogfood", "bug …

jonmumm/skills

12

22

parse-at-boundary Enforce the "parse, don't validate" discipline at every system edge. Data crossing a trust boundary must be parsed th…

jonmumm/skills

11

23

cmux Manage cmux terminal workspaces and browser surfaces for parallel AI agent sessions. Create, switch, monitor, and com…

jonmumm/skills

10

24

testing-trophy Kent C. Dodds' Testing Trophy: write more integration tests, fewer unit tests, confidence over coverage. Covers React…

jonmumm/skills

10

25

workers-integration-testing Write integration tests for Cloudflare Workers using vitest-pool-workers and cloudflare:test. Tests the full HTTP cyc…

jonmumm/skills

10

26

ai-sdk-testing Test code that uses the Vercel AI SDK (generateText, streamText, generateObject, streamObject) without calling real L…

jonmumm/skills

9

27

babysit-pr Monitor a PR through CI, diagnose and fix test failures, resolve merge conflicts, post QR codes for mobile preview bu…

jonmumm/skills

7

28

debug-runbook Structured debugging for production and staging issues. Maps symptoms to tools, queries, and data sources (Sentry, Po…

jonmumm/skills

7

29

mcp-setup Configure and troubleshoot MCP servers in Claude Code. Quick reference for installing, verifying, and debugging MCP c…

jonmumm/skills

7

30

codex-review Cross-agent code review: run OpenAI Codex to review your changes, then address its feedback. Use when asked to "codex…

jonmumm/skills

5

31

task-planner Pull all Jira tickets assigned to me that aren't done and help create copy-pasteable prompts to kick them off in othe…

jonmumm/skills

5

32

evals-first Evals-first development: write evaluations before specs, code, or designs. Evals become the guardrails that condition…

jonmumm/skills

3

33

storybook-play-testing Storybook play function integration testing for TanStack Start/Router apps. Covers Vite config for blocking server co…

jonmumm/skills

3

34

actorkit-storybook-testing Test actor-kit state machines in Storybook using mock clients and play functions. Covers static snapshots, interactiv…

jonmumm/skills

2

35

actorkit-tanstack-start Integrate actor-kit with TanStack Start/Router for server-rendered, real-time stateful apps on Cloudflare Workers. Co…

jonmumm/skills

2

36

agent-teams Spawn and coordinate Claude Code Agent Teams — multiple Claude sessions sharing a task list and mailbox, with one lea…

jonmumm/skills

2

37

autodesign Two-phase design loop like /swarm but for visual design. EXPLORE: launches N parallel subagents in Figma — each desig…

jonmumm/skills

2

38

chrome-cdp Interact with local Chrome browser session (only on explicit user approval after being asked to inspect, debug, or in…

jonmumm/skills

2

39

crap Measure and lower CRAP (Change Risk Anti-Patterns) — a metric that fuses cyclomatic complexity and test coverage to s…

jonmumm/skills

2

40

create-claude-md Bootstrap CLAUDE.md as a short table-of-contents plus a structured docs/ directory (agent guidance, architecture, pro…

jonmumm/skills

2

41

emulate Set up and use the `emulate` package for local API emulation in tests and CI. Covers CLI usage, programmatic API (`cr…

jonmumm/skills

2

42

game-qa Automated QA for WebGL/Three.js/R3F multiplayer games built with actor-kit. Playwright visual regression, game state …

jonmumm/skills

2

43

hard-cut Enforce a hard-cut cleanup policy: keep one canonical implementation and delete compatibility, migration, fallback, a…

jonmumm/skills

2

44

missions Multi-milestone autonomous development for large goals. Decomposes a big objective into milestones with validation ga…

jonmumm/skills

2

45

product-design-critic Sharpen product design judgment for software UI/UX, interaction flows, jobs-to-be-done, hierarchy, trust, governance …

jonmumm/skills

2

46

test-brainstorm After finding a bug caused by insufficient test coverage, brainstorm test cases across the entire feature area that c…

jonmumm/skills

2

47

verify-ui Verify UI changes visually using browser automation before telling the user it's done. Use when making CSS, layout, o…

jonmumm/skills

2

48

auto-grill-me Continue an in-progress /grill-me session in auto-pilot — the agent keeps asking the same relentless questions, but a…

jonmumm/skills

1

49

codex-goal Hand a goal-maker board off to Codex (gpt-5.5, low reasoning by default) — Claude validates the board, runs `codex ex…

jonmumm/skills

1

50

goal-maker Set up a rolling Scout/Judge/Worker task board with a charter, machine-truth state.yaml, and durable receipts for lon…

jonmumm/skills

1