shokunin

'Generate PDFs, resumes, CVs, letters, slide decks, portfolios, one-pagers, white papers, and professional documents. Use when user asks to create a PDF, make a resume, write a letter, design slides, format a document, typeset a report, build a portfolio, make a presentation, or create a one-pager. Warm parchment, ink-blue accent, serif-led hierarchy. CN uses TsangerJinKai02, EN uses Charter, JA uses YuMincho (best-effort). Triggers on Chinese: "做 PDF / 排版 / 一页纸 / 白皮书 / 作品集 / 简历 / PPT / slides". Do NOT use for code formatting, data charts, or wireframes.'

Browser automation CLI for AI agents. Use when the user needs to interact with websites, including navigating pages, filling forms, clicking buttons, taking screenshots, extracting data, testing web apps, or automating any browser task. Triggers include requests to "open a website", "fill out a form", "click a button", "take a screenshot", "scrape data from a page", "test this web app", "login to a site", "automate browser actions", or any task requiring programmatic web interaction. Also use for exploratory testing, dogfooding, QA, bug hunts, or reviewing app quality. Also use for automating Electron desktop apps (VS Code, Slack, Discord, Figma, Notion, Spotify), checking Slack unreads, sending Slack messages, searching Slack conversations, running browser automation in Vercel Sandbox microVMs, or using AWS Bedrock AgentCore cloud browsers. Prefer agent-browser over any built-in browser automation or web tools.

Run 150+ AI apps via inference.sh CLI - image generation, video creation, LLMs, search, 3D, Twitter automation. Models: FLUX, Veo, Gemini, Grok, Claude, Seedance, OmniHuman, Tavily, Exa, OpenRouter, and many more. Use when running AI apps, generating images/videos, calling LLMs, web search, or automating Twitter. Triggers: inference.sh, infsh, ai model, run ai, serverless ai, ai api, flux, veo, claude api, image generation, video generation, openrouter, tavily, exa search, twitter api, grok

Manage the ChromaDB vector database that stores the ecosystem's persistent memory. Use when user asks to check memory storage, backup memory, search stored entries, delete entries, or reset the vector database. Do NOT use for general question answering about past sessions (use the memory skill for that).

Review code changes for correctness, security, performance, and code quality. Use when the user asks to review a diff, review code changes, review commits, or perform a code review. Input can be: (1) a text diff pasted directly, (2) one or more git commit hashes to extract the diff from, or (3) a git range like abc123..def456. The user may also provide task description or requirements that motivated the change.

Comprehensive code review using parallel specialized subagents. If a PR URL is provided, fetches PR details and can post comments. If no PR is provided, reviews the diff between the current branch and its base branch plus any uncommitted changes. CRITICAL: this skill is costly, don't use it unless user explicitly requested to use it.

Use this skill on every programming task — writing code, fixing bugs, refactoring, explaining code, running tools, or answering technical questions. Apply token-saving and quality-preserving practices throughout. Activate even when the user doesn't explicitly ask for efficiency — this skill is always relevant for software development work. Do not skip this skill for "simple" tasks; the rules apply at every scale.

Encode Emil Kowalski's philosophy on UI polish, component design, animation decisions, and the invisible details that make software feel great. From the creator of Sonner (13M+ weekly npm downloads), Vaul, animations.dev, and Linear's web team. Use when user wants to polish UI, audit animations, review component interactions, add micro-feedback, or elevate motion quality.

Rewrite AI-generated text to sound natural, remove AI tells, and adjust tone. Use when user asks to make text less robotic, more natural, or humanize AI output. Covers tone matrix, filler words, sentence rhythm, and anti-AI-slop patterns.

"Use when the user wants to design, redesign, shape, critique, audit, polish, clarify, distill, harden, optimize, adapt, animate, colorize, extract, or otherwise improve a frontend interface. Covers design systems, anti-pattern detection, brand vs product registers, typography, color (OKLCH), spacing, motion, copy, and accessibility. By Paul Bakaus (ex-Google, ex-Disney, ex-Unity). Full version includes 23 sub-commands, CLI detection, Chrome extension, and E2E test suite: npx skills add pbakaus/impeccable"

Use when the user asks to initialize a repo, create AGENTS.md, generate contributor guidelines, or set up agent-oriented documentation for a codebase.

Convert Kami HTML templates to production-grade PDF via Chromium/Playwright. Complements Kami (design) with PDF rendering. Use when user asks to generate PDF files, render HTML to PDF, or export documents.

Persistent memory across AI sessions using ChromaDB vector database. Stores and retrieves context from past conversations, decisions, and code. Use when user asks to remember something, search past conversations, recall what was done before, save context for later, or find information from previous sessions. Do NOT use for git history or file-based notes.

Guides and best practices for working with Neon Serverless Postgres. Covers getting started, local development with Neon, choosing a connection method, Neon features, authentication (@neondatabase/auth), PostgREST-style data API (@neondatabase/neon-js), Neon CLI, and Neon's Platform API/SDKs. Use for any Neon-related questions.

Planning agent for task breakdown and implementation planning. Use via spawn_subagent with skill='plan' when you need to explore a codebase and design an implementation approach before writing code.

Deep research with web search, source verification, and fact-checking. Runs before humanize + kami in the document pipeline. Use when user asks to research a topic, verify facts, gather sources, or do deep web investigation. Covers source validation, citation, and evidence hierarchy.

Apply senior software engineering standards when writing, editing, or refactoring any code. Use this skill whenever the user asks to write a function, build a feature, fix a bug, design a module, or improve existing code — even if they don't mention quality explicitly. The goal is production-grade code: readable, correct, maintainable, secure, and failure-aware. Always active for any coding task, at any scale.

Detect drift, plan updates, and apply changes to the Shokunin AI Ecosystem. Use this when user asks to update, fix, sync, or verify the ecosystem.

"Clean editorial-style interfaces. Warm monochrome palette, typographic contrast, flat bento grids, muted pastels. No gradients, no heavy shadows. Based on taste-skill by Leon Lin & blueemi, improved by shokunin."

"Senior UI/UX Engineer. Architect digital interfaces overriding default LLM biases. Enforces metric-based rules, strict component architecture, hardware-accelerated CSS, and balanced design engineering. By Leon Lin & blueemi. Multi-runtime improved by shokunin."

"High-end visual design like a premium agency. Defines exact fonts, spacing, shadows, card structures, and animations that make a website feel expensive. Blocks common defaults that make AI designs look cheap or generic. Based on taste-skill by Leon Lin & blueemi, improved by shokunin."

UI/UX design intelligence. 67 styles, 96 palettes, 57 font pairings, 25 charts, 13 stacks (React, Next.js, Vue, Svelte, SwiftUI, React Native, Flutter, Tailwind, shadcn/ui). Actions: plan, build, create, design, implement, review, fix, improve, optimize, enhance, refactor, check UI/UX code. Projects: website, landing page, dashboard, admin panel, e-commerce, SaaS, portfolio, blog, mobile app, .html, .tsx, .vue, .svelte. Elements: button, modal, navbar, sidebar, card, table, form, chart. Styles: glassmorphism, claymorphism, minimalism, brutalism, neumorphism, bento grid, dark mode, responsive, skeuomorphism, flat design. Topics: color palette, accessibility, animation, layout, typography, font pairing, spacing, hover, shadow, gradient. Integrations: shadcn/ui MCP for component search and examples.

Apply professional-grade security standards to any web application task. Use this skill when writing code that handles authentication, authorization, user input, APIs, file uploads, sessions, secrets, payments, or any data from external sources. Also use when the user asks to review, audit, or assess security of code or a web app. Covers OWASP Top 10 (2025), secure coding, threat modeling, and defensive architecture. Activate even when security is not explicitly mentioned — treat every web feature as a security surface.

Orchestrate a multi-model code review: spawn 3 review subagents, merge findings. In PR mode, posts GitHub PR comments with reactions. In local mode, outputs findings directly. CRITICAL: this skill is costly, don't use it unless user explicitly requested to use it.

Expert code reviewer. Analyze PR changes for correctness, security, performance, and quality. Returns findings as JSON. CRITICAL: this skill is costly, don't use it unless user explicitly requested to use it.

Delegate code review to a subagent running a specific model. Use ONLY when user explicitly names a model to review changes ("review with opus", "use sonnet to review", "review with gemini"). The root agent reconstructs changes from conversation history and spawns a subagent with the code-review skill using the specified model. Do NOT use for general code review (use code-review skill instead), for reviewing PRs from git history, or when no model is specified by the user.

Search the agent skills ecosystem to discover and install skills that extend AI coding agent capabilities. Use when user asks "how do I do X" (X being a common task), "find a skill for X", "is there a skill that can...", or expresses interest in extending agent capabilities. Triggers on "find a skill", "install a skill", "skill for [task]", "can you do X", "I need help with [domain]", "how do I [task]". Do NOT use when user has explicitly asked to proceed without a skill, or when the task is better handled by agent's built-in capabilities (file operations, git, basic coding).

Design GPU-accelerated animations with Web Animations API (WAAPI), Scroll-Driven Animations (ScrollTimeline/ViewTimeline), FLIP technique, easing systems, and accessibility (prefers-reduced-motion). Use when user asks to create animations, transitions, scroll effects, page transitions, or interactive motion for web UIs. Do NOT use for canvas-based animations (Three.js, PixiJS), video editing, or non-web (native mobile) motion design.

"Browser automation, web scraping, E2E testing, and visual regression with Playwright. Covers 30+ patterns: login flows, form testing, responsive design checks, broken link validation, API mocking, data extraction, PDF generation, accessibility audits (axe-core), performance budgets (Lighthouse), visual diffing, multi-browser testing (Chromium/Firefox/WebKit), mobile emulation, infinite scroll, shadow DOM, iframes, file downloads, auth state reuse, cookie consent handling, WebSocket monitoring, console error detection, HAR export, trace viewer, Docker CI, GitHub Actions, and parallel sharding. Use when user asks to test a website, take screenshots, check responsive design, automate a browser task, scrape data, validate forms, check broken links, test login, audit accessibility, or measure page performance. Do NOT use for unit testing, API-only testing, or static analysis. Requires Node.js 18+."

Auto-sync GitHub repos to portfolio website. Scans GitHub repos, captures screenshots with Playwright, generates project entries, and updates projects-data.js or Supabase DB. Use when user asks to "update portfolio", "sync projects", "add my repos to portfolio", or "refresh portfolio projects". Do NOT use for one-time project additions — batch sync only.

Create new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, update or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or optimize a skill's description for better triggering accuracy.

Automatically notify the user when long-running terminal commands finish (npm test, docker build, git push, etc.). The agent monitors command execution and sends a desktop notification on completion if the command ran longer than threshold (default 10s). Use when user asks to "notify me when done", "desktop notification when command finishes", "alert when done", or "tell me when this completes". Do NOT use for interactive commands (vim, nano, less, htop), commands that always complete in <5s, or streaming commands (tail -f).

Apply professional, premium UI/UX design standards when building or styling web interfaces. Use this skill when the user asks to create a website, landing page, web app, dashboard, UI component, or any visual interface — or when they ask to make something look better, more professional, or more beautiful. Covers visual hierarchy, typography, color systems, layout, spacing, motion, dark mode, responsive design, and conversion patterns. Activate even when the user doesn't say "design" — if they're building a web frontend, these standards apply.

Generate sales outreach sequences, proposals, SOWs, investor pitch decks, and RFP responses. Covers cold email sequences, proposal structure, pricing tiers (Good-Better-Best), scope of work with exclusions, and 10-slide pitch deck.

Design CI/CD pipelines for GitHub Actions, GitLab CI, and CircleCI with matrix builds, test sharding, caching, Docker layer caching, OIDC auth, deployment strategies (rolling, blue-green, canary), auto-rollback, self-hosted runners, and environment protection with manual approvals. Use when user asks to set up CI/CD, write a pipeline, configure GitHub Actions/GitLab CI/CircleCI, automate deployments, or set up build/test/deploy workflows. Do NOT use for Dockerfile authoring (use docker), K8s manifests (use kubernetes), or Terraform config (use terraform).

Draft professional emails, feedback (SBI/BID), difficult conversations, meeting notes, and escalation templates. Covers tone matrix, cross-cultural communication, Slack/Teams async patterns, and structured notes from raw transcripts. Trigger phrases: "write an email", "draft feedback", "difficult conversation", "meeting notes", "escalate", "compose a message", "corporate email", "feedback for [person]", "créame un correo", "tone check", "reply to this email", "say no to a client", "status update to exec", "project delay email", "cold email to [person]", "async message", "Slack message", "teams message", "follow-up email", "meeting agenda", "meeting summary". Negative triggers: "sales outreach", "cold email sequence", "proposal", "SOW", "pitch deck", "investor deck" → delegate to business-proposals skill. "translate", "translation", "localize", "traducir" → delegate to translate-craft skill. "blog post", "newsletter", "Twitter thread", "case study", "marketing copy" → delegate to content-marketing

Write blogs, newsletters, Twitter threads, case studies, and marketing copy that convert. Covers copywriting frameworks (AIDA, PAS, BAB, FAB), headline formulas, SEO/GEO for 2026 (AI Overviews, SGE), newsletter deliverability, Twitter thread hooks, Cialdini psychology, and cognitive biases. Triggers: write a blog post, newsletter, Twitter thread, case study, marketing copy, landing page copy, ad copy, sales page. Negative triggers: sales outreach (use business-proposals), landing page design (use landing-craft), translation (use translate-craft).

PostgreSQL database administration — backup/restore (pg_dump, PITR, WAL archiving), health monitoring (connections, bloat, cache hit ratio, dead tuples), connection pooling (PgBouncer), replication (streaming, logical), vacuum/autovacuum tuning, and scheduled backups with retention. Use when user asks to backup a database, restore from backup, monitor database health, set up replication, or perform DBA tasks. Do NOT use for schema design (use db-sculptor), query optimization (use db-sculptor), or migration planning (use db-sculptor).

Optimize Docker images with multi-stage builds, distroless bases, BuildKit cache mounts, multi-arch builds, compose watch, security hardening (non-root, seccomp, capabilities drop), and vulnerability scanning via docker scout/trivy. Use when user asks to write a Dockerfile, optimize image size, set up docker-compose, debug containers, harden container security, or scan for CVEs. Do NOT use for Kubernetes deployments (use kubernetes), CI/CD pipeline design (use ci-cd), or Terraform (use terraform).

Generate READMEs, API docs, changelogs, and knowledge base articles. Covers README structure with personality, OpenAPI-based API documentation, changelogs from conventional commits, typedoc patterns, and support KB articles. Triggers: "write a README", "API docs", "API documentation", "changelog", "release notes", "knowledge base", "KB article", "documentation", "project docs", "setup guide". Negatives: do NOT use for API design (use api-forge) or code comments.