Agent Skills

UI audits, typography, docs, PR review, and releases, loaded on demand by your coding agent

26 skills for the parts of shipping that code review never covers: the loading states, the type scale, and whether half the diff is AI slop.

Install

npx skills add mblode/agent-skills -g --agent claude-code codex cursor -y

--agent takes a space-separated list. A comma-separated one is rejected whole as a single invalid name.

The bundle is listed at skills.sh.

Agents: these skills. Humans: Taste Training, a course on spotting and fixing AI slop. First unit free.

Skills

Architecture

• codebase-architecture: Design a structure, deepen an existing one, or harden it with guardrails.
• scaffold-nextjs: Next.js turborepo with Blode UI, Ultracite, GitHub, and Vercel.
• scaffold-cli: TypeScript CLI package: ESM, tsdown, vitest, changesets, CI.
• multi-tenant-architecture: Tenant isolation, routing, and custom domains on Cloudflare or Vercel.

Design

• product-design: What the interface should do, before anyone builds it.
• ui-design: Visual direction, design-system extraction, Tailwind builds, screenshot to markup, dark mode, responsive, and a React and Next.js UX audit with a ship verdict.
• ui-verification: Boots the app in a headless browser and runs nine probes that turn inferred UI defects into measured ones, then proves the fix cleared.
• ui-animation: Springs, gestures, easing, and curves pulled from a screen recording.
• presentation-creator: Decks with a story spine, speaker notes, and a contrast-checked QA pass, as Marp markdown, a web app, or a handoff to pptx.

Writing

• eli5: Session talk in plain language: optional analogy, exact technical terms, and house vocabulary without forced templates.
• docs-writing: Diataxis doc types, 51 rules, audit and writing modes, agent-readable docs.
• readme-creator: Type-aware README from the manifests: one install, a runnable quickstart, badges only where published.

Personal voice, blog posts, and voice evaluation live in ghostwriter.

Quality

• ax-audit: Agentic experience audit: 27 rules for tool parity, approval gates, and escape hatches, ship verdict.
• dx-audit: Libraries, CLIs, SDKs, npm packages: 38 rules, agent-friendly checks, root-cause findings.
• typography-audit: 78 rules: punctuation, fonts, sizing, spacing, hierarchy, pairing.
• seo: SEO/AEO audits and fixes, search-demand research, writer briefs, and search, AI visibility, and conversion measurement.

Shipping

• planning: Writes and reviews executable plans with repository evidence, vertical slices, and explicit acceptance criteria.
• pr-reviewer: Read-only diff review: bugs, structure, AI slop, security.
• tidy: Applies diff-scoped simplifications, preserving necessary guards and existing edits.
• pr-creator: PRs with short human descriptions, Linear IDs, templates, drafts, tidied commits.
• pr-babysitter: Watches an open PR: conflicts, CI, comments. Fixes what it can.
• autoship: npm releases with changesets: fix loop, CI watch, Version Packages merge, OIDC publish verify.

Authoring

• chat-history: Recover decisions, previous fixes, and context from past AI conversations with fast local search and source evidence.

• agents-md: Wires a repo so Claude Code, Codex and Cursor read the same instructions, then audits and refactors AGENTS.md and CLAUDE.md, with grades.

• agent-skills-creator: Creates and audits skills by their added value, with portable workflows, a validator, and regression scenarios.

• save-md: Writes a named source as a markdown file the next turn can reread.

License

MIT

---

Crafted by Matthew Blode