mthines

64 mods across 1 repository, 10 stars between them.

create-skill

25

mthines/agent-skills

Skill Claude CodeCodex

Scaffold, review, upgrade, or diagnose agent skills against best-practice frontmatter, progressive disclosure, token-aware structure, and the agent-skills.git symlink + inventory wiring. Modes: scaffold (default — new skill), review (audit existing skill), upgrade (split a single-file skill into multi-file), diagnose…

10 2d ago A 160 tokens original MIT

docs

26

mthines/agent-skills

Skill Claude CodeCodex

Authors, audits, and maintains project documentation across CLAUDE.md / .claude/rules/, AGENTS.md, README.md, and Diátaxis docs/ trees (root + nested for monorepos). Four modes: init scaffolds a tiered docs setup from scratch; update detects drift (dead @imports, renamed commands, stale narrative) and incrementally…

10 2d ago A 208 tokens original MIT

optimize-claude-md

27

mthines/agent-skills

Skill Claude CodeCodex

Audits CLAUDE.md files (root, nested, .claude/rules/.md) for context bloat and emits ranked suggestions across two levers — (1) shrink inventory entries, (2) flag rarely-used agent-invokable skills that should become slash-only to drop their description from the always-on available-skills list. Triggers on Claude…

10 2d ago A 239 tokens original MIT

persistent-memory

28

mthines/agent-skills

Skill Claude CodeCodex

Persists context across conversations as plain markdown so every future session can enrich a topic-scoped memory (e.g. parenting, relationship-anna, work-history, project-acme). Four operations: write (extract candidates, resolve as ADD / UPDATE / DELETE / NOOP per Mem0), read (load a ≤ 200-line INDEX; fetch detail…

10 2d ago A 375 tokens original MIT

changelog

29

mthines/agent-skills

Skill Claude CodeCodex

Generates a personal markdown changelog of merged or closed pull requests authored by the current user and Linear tickets the user closed or worked on, over a configurable window (default 7 days), grouped by feature area (e.g. Dashboards, Agent0). Inputs sourced from gh search prs --author=@me and the Linear MCP. Use…

10 2d ago A 123 tokens original MIT

ci-auto-fix

30

mthines/agent-skills

Skill Claude CodeCodex

Diagnoses a failed CI check, classifies it with an explicit verdict (code-bug | workflow-bug | dep-bug | env-bug | flaky | unsure), confidence-gates the fix (>=90 auto, 80-89 ask, <80 escalate), applies it, pushes, and iteratively verifies until CI passes — reverting the last commit if a brand-new failure appears.…

10 2d ago A 154 tokens original MIT

create-pr

31

mthines/agent-skills

Skill Claude CodeCodex

Generate a short, narrative GitHub pull request description (≤ 25 lines, hard ceiling 40), push the branch, open the PR as a draft, then run the review-loop skill for a bounded review-apply-simplify convergence before finalizing. The review-loop (pr-reviewer → implement-suggestion → polish simplify, up to 5…

10 2d ago A 260 tokens original MIT

mthines/agent-skills

Skill Claude CodeCodex

Authors fast, cheap, maintainable GitHub Actions workflows applying 2026 best practices: caching with hashFiles + restore-keys, parallelization via matrix + artifacts, reusability (composite actions for steps, reusable workflows for jobs), security (SHA-pinned actions, least-privilege GITHUBTOKEN, concurrency)…

10 2d ago A 220 tokens original MIT

resolve-conflicts

33

mthines/agent-skills

Skill Claude CodeCodex

Analyze and resolve Git merge/rebase conflicts intelligently, showing diffs and asking clarifying questions when needed. Invoke with /resolve-conflicts.

10 2d ago A 32 tokens original MIT

animations-native

34

mthines/agent-skills

Skill Claude CodeCodex

Authors performant React Native / Expo animations with Reanimated and gesture handling with react-native-gesture-handler, running motion on the UI thread so it stays at 60/120 fps. Covers worklets, shared values, useAnimatedStyle, withTiming/withSpring, layout animations, the Gesture API (pan/pinch/drag/swipe), Moti…

10 2d ago A 182 tokens original MIT

animations

35

mthines/agent-skills

Skill Claude CodeCodex

Authors performant web animations CSS-first AND brainstorms the right feedback for an interaction via a verb-to-motion catalog. Covers GPU-safe properties, modern primitives (@starting-style, interpolate-size), View Transitions, scroll-driven timelines, state-choreography morphs, React state (Motion, AnimatePresence)…

10 2d ago A 213 tokens original MIT

charting

36

mthines/agent-skills

Skill Claude CodeCodex

Selects the right chart type and visualization library for React/Next.js (web) and Expo/React Native (mobile) data visualization tasks, then applies accessibility and anti-pattern guardrails. Maps data shape and intent (comparison, composition, distribution, relationship, evolution, flow, geographic, hierarchical) to…

10 2d ago A 158 tokens original MIT

storybook

37

mthines/agent-skills

Skill Claude CodeCodex

Scaffolds, audits, and tests Storybook stories for React (web) and React Native / Expo (native) component libraries. Generates three artefacts in two files per invocation: a visual regression .stories.tsx file containing a Default story (variants grouped into a single snapshot) and a Playground story (interactive args…

10 2d ago A 233 tokens original MIT

ux

38

mthines/agent-skills

Skill Claude CodeCodex

Reviews UX, accessibility, and microcopy for web and React Native (Expo) applications. Analyzes UI code against established UX principles, WCAG 2.2 accessibility standards, platform guidelines (Apple HIG, Material Design 3), and UX writing best practices. Triggers on: "ux review", "review ux", "check accessibility"…

10 2d ago A 147 tokens original MIT

visual-design

39

mthines/agent-skills

Skill Claude CodeCodex

Guides and reviews the visual design and brand identity of UI components for web and React Native — color systems, typography pairing, visual hierarchy, signature details, and named style directions (minimal, swiss, editorial, brutalist, neo-brutalist, glass, soft-UI, terminal, playful, retro). Owns the generative…

10 2d ago A 177 tokens original MIT

ai-engineering

40

mthines/agent-skills

Skill Claude CodeCodex

Reviews and guides LLM/AI application engineering: prompt design, prompt caching, multimodal inputs, RAG, agent loops and tool design, resilience (rate limits, retries, fallbacks), memory, model migration, evals, testing, prompt-injection defence, and observability. Synthesises practices from Anthropic, OpenAI…

10 2d ago A 161 tokens original MIT

code-quality

41

mthines/agent-skills

Skill Claude CodeCodex

Language-agnostic skill for authoring and reviewing code with low cognitive complexity, readability, and long-term maintainability. Covers guard clauses, single-responsibility functions, type-driven design (illegal states unrepresentable, branded primitives, discriminated unions), schema-first validation, single…

10 2d ago A 183 tokens original MIT

confidence

42

mthines/agent-skills

Skill Claude CodeCodex

Rates confidence that the current work fully solves the stated requirement. Supports plan validation, code review, and analysis (root-cause, refactor, diagnose) modes. Plan mode combines LLM judgment with deterministic rule checks (multi-signal gate); a failed rule caps the gate at 89% regardless of LLM score. Use…

10 2d ago A 103 tokens original MIT

critical

43

mthines/agent-skills

Skill Claude CodeCodex

Adversarially challenges a proposed plan, code change, or bug diagnosis from a hostile pre-mortem perspective. Walks a fixed taxonomy of failure modes, blast radius, rollback, hidden coupling, and maintainability; every finding must cite a file, line, or named assumption; forces a steelman of at least one alternative.…

10 2d ago A 165 tokens original MIT

dx

44

mthines/agent-skills

Skill Claude CodeCodex

Developer Experience (DX) review and advisory skill for CLI tools, shell scripts, developer tooling, and automation. Analyzes code against established CLI design guidelines (clig.dev, Heroku CLI Style Guide, 12 Factor CLI), composability principles, error handling best practices, and developer ergonomics. Triggers on…

10 2d ago A 155 tokens original MIT

measurable

45

mthines/agent-skills

Skill Claude CodeCodex

Ensures every delivery ships with the telemetry needed to prove its impact and catch its own regressions: RUM/analytics events for user-facing web changes (delegates to rum-tracking), OpenTelemetry traces/metrics/structured logs for new or changed API endpoints, and explicit error/warning signal paths so failures…

10 2d ago A 172 tokens original MIT

optimize-approach

46

mthines/agent-skills

Skill Claude CodeCodex

Reviews whether a change takes the most optimal approach for its stated intent and, when it does not, researches the code, validates a concretely better approach via holistic analysis, and either proposes it (report mode) or applies it behind a confidence gate (apply mode). Judges four axes — codebase-fit, simplicity…

10 2d ago A 209 tokens original MIT

polish

47

mthines/agent-skills

Skill Claude CodeCodex

Re-runnable pre-PR quality gate for the current branch. Composes two existing passes over the branch diff: a broad pr-reviewer pass (read-only review via the branch's open PR, which pr-reviewer requires) and a code-quality simplify pass (applies Class M mechanical refactors behind a confidence ≥ 90 % gate, reverting…

10 2d ago A 217 tokens original MIT

review-changes

48

mthines/agent-skills

Skill Claude CodeCodex

Review branch changes or a PR for code quality, tests, documentation, and commit hygiene. Routes to the review-loop skill for a bounded review-apply-simplify convergence loop, or to pr-reviewer directly for a one-shot read-only review. Invoke with /review-changes.

10 2d ago A 65 tokens original MIT