mthines/agent-skills

1

ux Reviews UX, accessibility, and microcopy for web and React Native (Expo) applications. Analyzes UI code against estab…

mthines/agent-skills

34

2

holistic-analysis Forces a full holistic re-analysis when a fix or refactor isn't working. Instead of continuing to patch in isolation,…

mthines/agent-skills

32

3

confidence Rates confidence that the current work fully solves the stated requirement. Supports plan validation, code review, an…

mthines/agent-skills

31

4

tdd Enforces strict Test-Driven Development with RED-GREEN-REFACTOR cycles. Writes one failing test at a time, implements…

mthines/agent-skills

31

5

review-changes Review branch changes or a PR for code quality, tests, documentation, and commit hygiene. Routes to the `review-loop`…

mthines/agent-skills

30

6

code-quality Language-agnostic skill for authoring and reviewing code with low cognitive complexity, readability, and long-term ma…

mthines/agent-skills

29

7

autonomous-workflow The phase-based machinery (0–7) behind the `aw` dispatcher — task intake through tested PR delivery in an isolated Gi…

mthines/agent-skills

28

8

ci-auto-fix Diagnoses a failed CI check, classifies it with an explicit verdict (code-bug | workflow-bug | dep-bug | env-bug | fl…

mthines/agent-skills

26

9

create-pr Generates a short, narrative GitHub pull request description (≤ 25 lines, hard ceiling 40), pushes the branch, opens …

mthines/agent-skills

26

10

fix-bug Resolves a single bug from any starting evidence — Dash0 telemetry (span / log / web event / RUM error link), raw sta…

mthines/agent-skills

25

11

dx Developer Experience (DX) review and advisory skill for CLI tools, shell scripts, developer tooling, and automation. …

mthines/agent-skills

24

12

resolve-conflicts Analyze and resolve Git merge/rebase conflicts intelligently, showing diffs and asking clarifying questions when need…

mthines/agent-skills

24

13

implement-suggestion Implements review-comment suggestions across one or more PRs. Multi-PR mode (default when $ARGUMENTS contains PR URLs…

mthines/agent-skills

23

14

profile-optimizer Analyzes React DevTools Profiler exports, Chrome DevTools Performance traces, and Chrome heap snapshots / heap-timeli…

mthines/agent-skills

23

15

aw-create-plan Create the plan artifact (plan.md + checks.yaml executable acceptance checks) in `.agent/{branch}/` from the current …

mthines/agent-skills

22

16

aw-create-walkthrough Generate a walkthrough artifact (walkthrough.md) in `.agent/{branch}/` summarizing completed work for PR delivery. Ga…

mthines/agent-skills

22

17

video-analyser Analyse a video file — primarily a screen recording of a bug — to extract errors, UI state, and reproduction steps. R…

mthines/agent-skills

22

18

batch-linear-tickets Batch-analyze and resolve multiple Linear tickets — bug fixes and feature work. For each ticket: classifies as bug or…

mthines/agent-skills

21

19

create-skill Scaffold, review, upgrade, or diagnose agent skills against best-practice frontmatter, progressive disclosure, token-…

mthines/agent-skills

21

20

aw-review-quality-gate Self-check quality gate for review findings. Validates that each finding is actionable, evidence-backed, correctly lo…

mthines/agent-skills

20

21

e2e-testing Plans, generates, runs, and heals end-to-end tests using Playwright Test Agents (Planner, Generator, Healer) and the …

mthines/agent-skills

20

22

animations Authors performant web animations CSS-first AND brainstorms the right feedback for an interaction via a verb-to-motio…

mthines/agent-skills

19

23

charting Selects the right chart type and visualization library for React/Next.js (web) and Expo/React Native (mobile) data vi…

mthines/agent-skills

19

24

e2e-pr-stabilizer Stabilizes or optimizes Playwright E2E tests on one PR via a local-first loop, then ratifies with a single CI run. Pu…

mthines/agent-skills

19

25

screen-recorder Records short videos of specific page sections using Playwright's `recordVideo` API, plays scripted interactions (hov…

mthines/agent-skills

19

26

visual-design Guides and reviews the visual design and brand identity of UI components for web and React Native — color systems, ty…

mthines/agent-skills

19

27

critical Adversarially challenges a proposed plan, code change, or bug diagnosis from a hostile pre-mortem perspective. Walks …

mthines/agent-skills

18

28

storybook Scaffolds, audits, and tests Storybook stories for React (web) and React Native / Expo (native) component libraries. …

mthines/agent-skills

18

29

test-provenance-guard Detects tests that pass by construction — tests that define a private copy of the function under test instead of impo…

mthines/agent-skills

18

30

ai-engineering Reviews and guides LLM/AI application engineering: prompt design, prompt caching, multimodal inputs, RAG, agent loops…

mthines/agent-skills

17

31

persistent-memory Persists context across conversations as plain markdown so every future session can enrich a topic-scoped memory (e.g…

mthines/agent-skills

17

32

playwright-trace-analyzer Analyzes Playwright E2E `trace.zip` archives (and bare trace JSONL when unpacked). Extracts the action timeline, netw…

mthines/agent-skills

17

33

e2e-testing-mobile Plans, generates, runs, and heals end-to-end tests for Expo and React Native mobile apps using Maestro (the 2026 stan…

mthines/agent-skills

16

34

github-actions-author Authors fast, cheap, maintainable GitHub Actions workflows applying 2026 best practices: caching with `hashFiles` + `…

mthines/agent-skills

16

35

optimize-claude-md Audits CLAUDE.md files (root, nested, `.claude/rules/*.md`) for context bloat and emits ranked suggestions across two…

mthines/agent-skills

16

36

optimize-mock-data Optimizes a directory of structurally-related JSON / JSONL mock fixtures by inferring a shared schema, detecting stru…

mthines/agent-skills

16

37

changelog Generates a personal markdown changelog of merged or closed pull requests authored by the current user and Linear tic…

mthines/agent-skills

15

38

docs Authors, audits, and maintains project documentation across CLAUDE.md / .claude/rules/, AGENTS.md, README.md, and Diá…

mthines/agent-skills

14

39

rum-tracking Guides product analytics and RUM (Real User Monitoring) event tracking in web (React/Next.js) and mobile (React Nativ…

mthines/agent-skills

14

40

ideate Generates, stress-tests, and iteratively evolves ideas for a stated problem — product concepts, features, solution op…

mthines/agent-skills

12

41

animations-native Authors performant React Native / Expo animations with Reanimated and gesture handling with react-native-gesture-hand…

mthines/agent-skills

11

42

interview Aligns on the scope of a request before any plan or implementation begins — the requirements-elicitation interview a …

mthines/agent-skills

11

43

optimize-approach Reviews whether a change takes the most optimal approach for its stated intent and, when it does not, researches the …

mthines/agent-skills

11

44

polish Re-runnable pre-PR quality gate for the current branch. Composes two existing passes over the branch diff: a broad pr…

mthines/agent-skills

11

45

review-loop Bounded review-apply-resolve convergence loop for a GitHub PR (draft PRs are fine). Runs up to N=5 iterations of pr-r…

mthines/agent-skills

11

46

test-auto-fix Diagnoses failing tests across any project, classifies each failure as a test-bug, prod-bug, or unsure, confidence-ga…

mthines/agent-skills

11

47

measurable Ensures every delivery ships with the telemetry needed to prove its impact and catch its own regressions: RUM/analyti…

mthines/agent-skills

10

48

severity Rates how severe a finding or bug is if it is real — the blast-radius axis, complementary to confidence's is-it-real …

mthines/agent-skills

10

49

update-claude Analyze code changes and update CLAUDE.md and .claude/rules/ documentation to stay in sync with the codebase. Uses gi…

mthines/agent-skills

10

50

verify-behavior Owns a cheapest-first three-tier verification ladder — Tier 1 syntactic (grep / ast-grep / read), Tier 2 semantic-no-…

mthines/agent-skills

10