Audit and fix transactional/marketing deliverability — SPF, DKIM, DMARC, reputation, bounce/complaint handling, list hygiene, unsubscribe compliance — so mail lands in the inbox. Use when "emails go to spam", "set up SPF/DKIM", or "check deliverability". Templates stay on design-email.
Audit an existing app's design system and motion, then apply a coherent, performant, reduced-motion-safe pass. Use when "motion pass", "animate the app", or "add micro-interactions across the app". One new isolated animation → design-motion.
Add/upgrade PWA capabilities: manifest, service worker, offline mode, install prompt, push notifications, background sync. Use when "make it a PWA", "offline support", "install prompt", "service worker", or "add to home screen". Native Capacitor → mobile-capacitor-platform.
Audit and fix how easily content is UNDERSTOOD: CPL/reading level, Gestalt grouping, deadspace, icons or a table that cuts verbosity. Use when "hard to read", "too dense", "reading level", "cognitive load", or "turn this prose into a table". Looks-good → enhance-web-ui. Breakpoints → audit-responsive.
Enhance an existing README with a theme-aware hero, feature tour, screenshots/GIF, accurate badges, and synced content. Use when "enhance README", "make README prettier", "add screenshots", or "showcase the app". Content-only docs → docs-writer. Drift audit/plan → plan-docs-sync.
Upgrade an existing SKILL.md prompt (not its behavior) to 2026 practice: degrees of freedom, structured CoT, one worked example, self-critique rubric, term consistency. Use when "enhance this skill's prompts", "upgrade skill authoring", or "apply the prompt playbook". New skill from scratch → meta-skill-creator.
Build or upgrade web forms to production quality: accessible structure, schema-driven validation, client↔server parity. Use when "improve this form", "form validation", "accessible form", "multi-step form", "form error handling", or "the form UX is bad".
Build landing pages, portfolios, and marketing sites that don't look AI-generated. Use when asked for "landing page", "portfolio", "marketing site", "anti-slop", "Awwwards-style", "premium frontend", or when design needs a strong point of view.
Upgrade an existing site/app to premium quality. Use when "redesign this app" or "upgrade UI to premium". One-page polish → enhance-web-ui. Plan-only slop audit → plan-antislop. New UI from scratch → design-frontend.
Audit and fix SEO for any web app. Use when asked to "improve SEO", "add meta tags", "fix search ranking", "add structured data", "sitemap", "canonical URLs", "Open Graph", "Google indexing", "rich results", "SEO audit", or "why is my site not ranking".
NN/g-grounded enhancement of an existing page's flows — not a repo-wide slop audit. Use when "fix UX of /xxx" or "improve information density". Repo-wide authenticity plan → plan-antislop. Composition/type → enhance-web-ui. Dense prose / CPL / reading level → enhance-readability. Heuristics-only → audit-ux.
Add purposeful 3D/WebGL and scroll choreography to an existing site with Three.js/R3F, GSAP, or Motion. Use when "add 3D", "WebGL hero", "React Three Fiber", or "scroll-driven 3D". General UI polish → enhance-web-ui. Motion without 3D → enhance-motion.
Compact the current conversation into a handoff document a fresh agent can pick up. User-invoked via /handoff; an optional argument describes what the next session will focus on.
Apply-now inventory of parked work — unfinished plans, deferred phases, TODO/FIXME, skipped tests, open findings — into a living BACKLOG.md that diffs new/done/stale. Use when "what's left behind", "inventory TODOs", "consolidate the backlog". Execute → complete-everything. Decisions → docs-adr.
Apply-now consolidation of a drifted design system into one token/component SSOT. Use after an approved plan-uiux-unification pass, or when "clean up the design system now", "migrate to one button", or "resolve token conflicts". Plan-only burndown → plan-uiux-unification.
Apply-now consolidation of accreted CI gates, ratchets, and hooks into one aggregator required check. Use after audit-gate-logic, or when "clean up our CI checks", "we have three lint jobs", "make one quality gate". Audit-only → audit-gate-logic. Rule content → audit-doctrine. Pipeline cost → audit-cicd.
Turn an agent failure—premature stop, false completion, gamed check, missed file, broken handoff—into a durable rule/skill/hook/CI guard plus regression test. Use when "the agent stopped early again", "it gamed the test", or "add a guard so this doesn't recur". App bugs → workflow-fix-and-ship.
Close the feedback loop for an already-live app: inspect production signals, prioritize top issues, fix, verify live, repeat. Use when "post-launch polish", "fix the top production issues", "iterate on feedback", or "what should I fix next after launch?". One named bug → workflow-fix-and-ship.
Scaffold and implement Model Context Protocol (MCP) servers that expose external services, APIs, and data sources as typed tools and resources for LLM agents. Use when the user says "build an MCP server", "give Claude access to X", "create an MCP tool", "expose my API to an agent", or "AI agent integration".
Create or update a pack SKILL.md (frontmatter, house limits, T1–T6). Use when authoring a cursor-kenji skill. Prompt-only upgrade → enhance-skill-prompts. Cursor skill wizard → create-skill.
Handle Capacitor platform depth beyond UI: plugins, OTA, deep links, push, offline, native CI/CD, App Store / Play Store submission, Apple preflight, security scan, Cordova migration. Use for "add push notifications", "deep linking", "OTA update", "native build CI", "App Store rejection", "migrate to Capacitor".
Boot Android emulator + Metro (Expo / bare RN) in order: inspect IDE terminals, kill stale ports, pick an AVD. Use when "start Metro", "start emulator", "Cannot connect to Expo", or a stuck dev loop. QA on the running emulator → mobile-emulator-test.
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: