agent-skills

Decides what an interface should do before UI is built or audited: interaction choice, action scope and consequence, reachable states, resilience, and accessibility as task completion. Works from a brief, spec, mockup, intent, or existing UI. Use when asked "is this the right interaction", "design the flow", "what control should this use", "what should this action affect", "which states should this have", "make this resilient", or "what breaks here". For building or styling use ui-design; for built-code audits use ui-audit; for copy wording use copywriting.

Writes messages, emails, posts, comments, and tickets in the user's own tone of voice, with per-platform voice profiles for Slack, email, WhatsApp, LinkedIn, and Linear built from the user's real message and ticket history, plus a strategy layer (asks, declines, delicate framing, bad news) for messages that need to land. Routes to the right register and enforces an anti-AI-tells self-check. Ships a fictional demo persona so it works out of the box; the user swaps in their own voice files. Use when asked to "write this in my voice", "draft a Slack message", "reply to this email as me", "write a LinkedIn post", "send a WhatsApp message", "write a Linear ticket", "turn this into Linear issues", "make this sound like me", "ghostwrite this", "critique my draft", "will this land", or "help me say no to this". For marketing or product copy in a brand voice, use copywriting; for long-form articles and essays, use blog-post.

Audits the developer-facing surface of a library, CLI, SDK, or npm package across API and SDK ergonomics, the error messages developers see, CLI UX, type ergonomics, install and first-run onboarding, and config ergonomics. 35 prefix-dispatched rules; reports findings by file and location with impact tiers and concrete fixes. Use when asked to "audit my CLI", "make a CLI agent-friendly", "is this API ergonomic", "review the developer experience", "improve these error messages", "is this SDK easy to adopt", "is this package easy to install", or "review my library's DX". For end-user UI quality and React/Next UX use ui-audit, for agentic-app UX use ax-audit, for documentation prose use docs-writing, for a README use readme-creator, for AGENTS.md use agents-md, and for repo structure use define-architecture.

Scaffolds a production-ready TypeScript CLI and npm package with ESM, a dual tsdown build (CLI binary plus typed library), vitest, oxlint and oxfmt via ultracite, changesets, GitHub Actions CI with OIDC npm publishing, AGENTS.md, and a bundled agent skill definition. Use when creating a new CLI tool, bootstrapping a TypeScript package, scaffolding a node CLI, starting a new npm package, or asking "scaffold a CLI project" or "set up a new TypeScript CLI". For a Next.js web app use scaffold-nextjs; for structuring an existing codebase use define-architecture; for releasing an already-built package use autoship.

Audits built React and Next.js frontends for user-facing defects in code and rendered UI: state gaps, data loss, double submits, focus and keyboard failures, rollback gaps, stale async, accessibility markup, layout resilience, performance setup, typography, motion hazards, and microcopy. Returns file:line findings and a ship verdict. Use when asked to "review this PR for UX bugs", "audit this component", "check my UI", "is this accessible", "design QA this page", or "is this ready to ship". For product decisions use product-design; for agentic apps use ax-audit; for deep type or motion use typography-audit or ui-animation.

Designs, implements, reviews, debugs, and reverse-engineers UI motion: CSS transitions, keyframes, springs, gestures, drag, easing, timing, framer-motion, and animation curves from screen recordings. Use when asked to "add animations", "make this feel smooth", "review my animations", "add a swipe gesture", "match this easing", "reverse engineer this animation", "extract the animation curve", or "what's it called when..." to name a motion effect from a vague description. For visual direction use ui-design; for page-level UI audit use ui-audit.

Designs and builds UI: visual direction, Tailwind implementation, browser-comparable variants, screenshot-to-markup scaffolds, dark-mode and responsive retrofits, component extraction, and Tailwind cleanup. Use when asked to "build a landing page", "create a dashboard", "make this look premium", "pick a visual style", "design the UI", "show me 3 options", "create a brand kit", "turn this screenshot into markup", "add dark mode", "make this responsive", or "clean up the Tailwind". For product behavior use product-design; for UI audits use ui-audit; for motion use ui-animation; for copy use copywriting.

Monitors an open PR, detects it from the current branch, polls for conflicts, CI failures, review comments, and merge readiness, fixes safe issues, and reports only state changes. Monitor mode uses the Monitor tool when available, falling back to CronCreate/CronDelete; without either, run one-shot modes only. Use when asked to "babysit a PR", "watch this PR", "keep a PR green", "fix CI", "why is CI red", "resolve conflicts", "triage review comments", or "address PR comments". For PR creation use pr-creator; for diff review use pr-reviewer; for npm releases use autoship.

Builds and stress-tests implementation plans in two modes. Create mode scans code and docs, asks one question at a time with a recommended answer, runs a blindspot pass when the user is new to the area, then writes a plan file. Review mode scores completeness, feasibility, scope, testability, risk, and assumptions, verifies checkable claims, and writes resolutions back until every dimension reaches 5/5. Use when asked to "create a plan", "plan this feature", "I want to build X", "grill me", "think this through", "blindspot pass", "unknown unknowns", "this is new to me", "review my plan", "rubber duck this", "stress test this plan", "is this plan ready", "get this plan to 5/5", "what am I missing", "verify this claim", "prove this plan", "fact-check this plan", or when the user explicitly wants a plan artifact before implementation. For code review use pr-reviewer; for architecture briefs use define-architecture.

Reviews the local diff or branch and returns a read-only, severity-tiered findings report. Modes cover standard bugs, structural quality, AI slop, and security audit. Use when asked to run /pr-reviewer, "review my changes", "code review", "thermo-nuclear review", "structural review", "deslop this", "clean up AI code", "security audit", "find vulnerabilities", or before commit, push, or handoff. For fixes use tidy; for PR creation use pr-creator; for CI or review comments use pr-babysitter; for frontend UX, accessibility, layout, state coverage, or rendered quality use ui-audit; for plans use planning.

Fans out four concurrent review agents over the current diff, then APPLIES fixes directly to the working tree and verifies the build. Mutates code; it does not produce a report. Covers reuse (duplicate logic, hand-rolled stdlib, reinvented platform features), quality (hacky patterns, React/TypeScript hygiene, over-memoisation, exhaustive-deps, `any`, dead code, `CLAUDE.md`/`AGENTS.md` violations), efficiency (unnecessary work, missed concurrency, hot-path bloat), and test discipline (bug fixes without a repro test, useless tests to delete, missing tests only when they prevent a named failure). Use when the user says "tidy this up", "simplify", "clean up this diff", "polish my changes", "check for duplication", or "any reuse opportunities?", i.e. when the intent is to have the changes made automatically. For a read-only report that lists findings without touching files, use `pr-reviewer` instead.

Generates folder structures, module contracts, middleware pipelines, and frontend/backend boundaries for TypeScript full-stack applications, and finds domain-informed deepening opportunities in existing codebases. Use when setting up project structure, organizing a monorepo, defining folder layout, designing backend modules, establishing team conventions, improving architecture outside a local diff, writing an architecture brief, or asking "how should I structure this app", "design the folder structure", "set up the architecture", "find architecture improvements", "make this codebase agent-friendly", or "set up guardrails for coding agents". For scaffolding a new Next.js repo use scaffold-nextjs, for a new TypeScript CLI use scaffold-cli, for multi-tenant domain or isolation strategy use multi-tenant-architecture, and for structural review of a local diff use pr-reviewer.

Writes and edits short product and marketing copy, including landing pages, CTAs, onboarding strings, product descriptions, email subjects, UI state copy, and AI-ism cleanup. Use when asked to "write copy", "fix the copy", "make this shorter", "improve the CTA", "rewrite from first principles", "remove AI-isms", "clean up AI writing", or "flag AI patterns". For blog posts use blog-post; for slide copy use presentation-creator; for docs use docs-writing; for product behavior decisions use product-design.

Guides creation and improvement of best-practice agent skills following the open format specification. Covers frontmatter, directory structure, progressive disclosure, reference files, rules folders, degrees of freedom, content patterns, executable scripts, MCP tool references, evaluations, cross-model testing, and a ten-dimension audit protocol for existing skills. Use when creating a new skill, authoring SKILL.md, setting up a rules-based audit skill, structuring a skill bundle, writing scripts inside a skill, evaluating a skill, improving or rewriting an existing skill, or asking "how to write a skill", "improve this skill", "audit my skill", or "review this SKILL.md".

Audits, scores, and refactors AGENTS.md and CLAUDE.md agent instruction files using execution-first standards: working commands, real-failure gotchas, signal-to-noise, and @import progressive disclosure. Runs a 10-check quick triage or a 45-check full audit with letter grades, then proposes minimal diffs. Use when asked to audit, review, score, refactor, or improve agent instruction files, fix stale commands, reduce bloat, write a new AGENTS.md, or when asking "my AGENTS.md is bad", "help me write a CLAUDE.md", or "improve my agent instructions". For SKILL.md skill files use agent-skills-creator; for general docs use docs-writing; for mining session history into instruction suggestions use the external cadence-advise skill where installed.

Runs the npm release flow for an existing changesets package: create a changeset, fix lint/type/test/format failures, push, watch CI, merge the Version Packages PR, watch publish, and verify npm. Use when asked to "release this", "publish this package", "autoship", "cut a release", or fix build failures inside a release flow. For feature PRs use pr-creator; for PR monitoring use pr-babysitter; for new packages use scaffold-cli.

Audits agentic applications for architecture and trust: tool parity, tool granularity, context injection, completion signals, approval gates, confidence cues, escape hatches, intent handshakes, memory visibility, and adaptive canvases. Produces a ship-readiness verdict plus an AX Relationship Summary. Use when reviewing agentic feature PRs or asking "is this agent-native", "AX review", "critique this AI feature", "does this earn user trust", or "audit this for AX". For traditional frontend UX use ui-audit.

Generates engaging long-form blog posts from source materials or a topic brief. Supports listicles, editorial tutorials, how-to articles, narrative essays, and thought leadership. Handles research, outlining, drafting, on-page SEO, and polishing. Use when "write a blog post about this", "create a listicle", "turn this research into an article", "write an editorial tutorial", "draft a thought leadership piece", or "write a how-to article". For short product or marketing copy (headlines, CTAs, landing pages, onboarding strings) use copywriting; for slide decks use presentation-creator; for API references, READMEs, or how-to docs in a documentation site use docs-writing.

Writes and audits technical documentation using the Diataxis framework and Stripe-style clarity. 52 rules across 9 categories covering voice, structure, clarity, code examples, formatting, navigation, scanability, content hygiene, and review. Use when writing docs, documenting APIs, writing documentation-site tutorials or how-to guides, auditing an existing README or docs site, or asking "review my docs", "improve this documentation", or "write docs for this". For editorial blog tutorials use blog-post; for creating a README from scratch use readme-creator; for AGENTS.md or CLAUDE.md files use agents-md; for marketing copy use copywriting.

Provides architecture guidance for multi-tenant SaaS platforms on Cloudflare or Vercel. Covers platform choice, domain strategy, tenant identification and isolation, subdomain routing, custom domains and SSL, white-label setup, tenant context propagation, PSL submission, and mapping platform limits to pricing plans. Use when building a multi-tenant application or asking "how do I support multiple tenants", "build a white-label platform", "add custom domains", "route tenants by subdomain", or "map limits to plans". For general app folder structure use define-architecture; for scaffolding a new Next.js repo use scaffold-nextjs.

Optimises SEO and technical foundations for Next.js App Router apps, covering sitemaps, robots, meta tags, structured data, canonical URLs, redirects, indexing policy, hreflang and internationalisation, Core Web Vitals, programmatic SEO, security headers, privacy/consent, and error-page resilience. Use when asked to "improve SEO", "add a sitemap", "fix meta tags", "add structured data", "set canonical URLs", "set up redirects", "fix soft 404s", "add hreflang", "add security headers", "add cookie consent", "improve Core Web Vitals", "audit SEO", or "build SEO pages at scale". Performs no visual redesigns; for visual direction use ui-design, for page-level UI quality use ui-audit. Does not cover llms.txt or AI-agent readability; research current specs for that work.

Creates GitHub pull requests with short, human-sounding descriptions. Adds a Linear issue ID prefix when available, keeps titles under 60 chars, and defaults to one short paragraph instead of generated summaries or test-plan sections. Restructures noisy commit history into reviewable order and adds reviewer guidance for large diffs. Also updates an existing open PR's title and description in place with gh pr edit instead of erroring. Use when "create a PR", "make a PR", "open a pull request", "PR this", "ship it", "update the PR description", "update the PR title", "make this PR easy to review", "polish this PR", "tidy the PR", "clean up commits", "restructure commits", or "split this PR". For reviewing a diff for bugs, use pr-reviewer. For monitoring a PR after creation, use pr-babysitter. For npm releases, use autoship.

Creates bold, minimal, dark-first presentations with structured narrative arcs, punchy slide copy, high-contrast visual design, and conversational speaker notes. Covers live talks, async/recorded decks, and 10-slide investor pitch decks. Use when creating a presentation, structuring a deck, writing slides, building a pitch deck for investors, or asking "outline a presentation about...", "write slides for...", "design a deck for...", or "turn this doc into a deck". For long-form articles use blog-post; for marketing copy outside slides use copywriting; for product UI design systems use ui-design.

Writes or rewrites a project's README.md tailored to its type (CLI, library, app, framework, monorepo, or skill bundle). Discovers project context from manifests, dispatches on the detected type, writes section by section, and validates against a quality checklist. Use when "write a README for this project", "create a README", "write a README from scratch", "rewrite this bad README", "bootstrap project documentation", or "the create-next-app README is still here". For auditing or improving an existing README or a docs site, use docs-writing. For AGENTS.md or CLAUDE.md agent-instruction files, use agents-md.

Scaffolds a production-ready Next.js turborepo end to end. Runs create-next-app with TypeScript, Tailwind CSS, and React Compiler, sets up shadcn/ui with Blode UI components from the ui.blode.co registry, blode-icons-react icons, Agentation, and Ultracite (Oxlint, Oxfmt, Lefthook), converts the app into a turborepo, then creates the GitHub repo and deploys to Vercel with a pre-launch checklist. Use when creating a brand-new Next.js app, bootstrapping a turborepo, scaffolding a web project, starting a new repo for a website or marketing site, or asking "create a Next.js project", "set up a turborepo", or "start a new web app". For a TypeScript CLI or npm package, use scaffold-cli. For folder structure and module contracts in an existing app, use define-architecture. For building a page inside an existing app, visual direction, palettes, and theming, use ui-design.

Audits web typography against 90 rules in 10 categories: punctuation, font selection and @font-face setup, sizing and measure, spacing and rhythm, OpenType features, hierarchy, alignment and layout, typeface pairing, brand identity, and display type. Reports file:line findings with concrete CSS/HTML fixes ordered by impact. Use when writing or reviewing CSS/HTML for text, selecting or pairing typefaces, configuring font-feature-settings or @font-face, building a type scale, or asking "audit my typography", "fix the fonts", "review my type system", "why does this text look off". Triggers on font-family, font-size, line-height, letter-spacing, smart quotes, em dashes, faux bold or italic, variable fonts, widows and orphans. For whole-UI audits beyond type (accessibility, forms, navigation), use ui-audit; for choosing a visual direction or designing a new type system, use ui-design.