Write technical specifications that give agents enough context to implement features autonomously. Use when the user says "write a spec", "plan this feature", "create a planning doc", or when planning features, documenting architecture decisions, or creating implementation guides.
Write technical articles and blog posts with depth and honest trade-offs. Use when the user says "write a blog post", "draft an article", "write about this", or when creating articles in docs/articles/ explaining patterns, techniques, or lessons learned.
CSS and Tailwind styling guidelines for this codebase. Use when the user says "style this", "fix the CSS", "add classes", or when writing Tailwind utilities, using cn(), creating UI components, reviewing CSS code, or deciding on wrapper element structure.
Review code from the perspective of a new TypeScript developer. Use when the user asks whether code feels wrong, too indirect, too clever, hard to follow, or wants a pass focused on unnecessary abstractions, misleading names, layered type tricks, and first-read clarity.
In-code documentation, folder READMEs, and code comments. Use when the user says "document this", "add JSDoc", "write a README", "explain this code", or when writing README.md files, JSDoc comments, or code organization docs.
Draft a self-contained implementation prompt that an agent can execute with zero prior context. Use when the user says "draft a prompt", "write a handoff", "make a prompt I can copy-paste", "create a delegation brief", or wants to hand off a task to another agent, tool, or conversation.
Review UI code for Web Interface Guidelines compliance. Use when asked to "review my UI", "check accessibility", "audit design", "review UX", or "check my site against best practices".
Use this skill ALWAYS when the user asks to start a new project, initialize a repository, bootstrap a new app, or set up a codebase from scratch. It provides Paul's exact required modern stack conventions (pnpm, native node test, esbuild/vite, and buildless-types). If the user mentions "new project" or "setup", you must consult this skill before creating any files to ensure the correct architecture is used.
Use when designing, adding, or reviewing public API for the Newton physics engine — class names, method signatures, type hints, docstrings, or parameter conventions. Also use when unsure if new API conforms to project conventions.
Write a postmortem for a regression that escaped to production, broke real users, and traces back to a design flaw worth documenting for future implementors. Only invoke after confirming no existing postmortem or doc covers the same root cause.
Write JavaScript code in n8n Code nodes. Use when writing JavaScript in n8n, using $input/$json/$node syntax, making HTTP requests with $helpers, working with dates using DateTime, troubleshooting Code node errors, or choosing between Code node modes.
Write Python code in n8n Code nodes. Use when writing Python in n8n, using _input/_json/_node syntax, working with standard library, or need to understand Python limitations in n8n Code nodes.
Facilitate structured post-incident reviews to identify root causes, document what worked and failed, and produce actionable recommendations to improve future incident response.
Delegate coding tasks to Codex, Claude Code, or Pi agents via background process. Use when: (1) building/creating new features or apps, (2) reviewing PRs (spawn in temp dir), (3) refactoring large codebases, (4) iterative coding that needs file exploration. NOT for: simple one-liner fixes (just edit), reading code (use read tool), thread-bound ACP harness requests in chat (for example spawn/run Codex or Claude Code in a Discord thread; use sessions_spawn with runtime:"acp"), or any work in ~/clawd workspace (never spawn agents here). Claude Code: use --print --permission-mode bypassPermissions (no PTY). Codex/Pi/OpenCode: pty:true required.
Prepare and execute a Plannotator release — draft release notes with full contributor credit, bump versions across all package files, build in dependency order, and kick off the tag-driven release pipeline. Use this skill whenever the user mentions preparing a release, bumping versions, writing release notes, tagging a release, or publishing. Also trigger when the user says things like "let's ship", "prep a release", "what's changed since last release", or "time to cut a new version".
Use when the user wants to create a demo video, record a feature walkthrough, or generate a video for a PR description. Triggers on "record a demo", "make a video", "demo video for PR", or "generate a walkthrough".
Update the API reference documentation by downloading the latest OpenAPI spec from production and regenerating the Docusaurus API docs
SEO internal linking optimizer: improve site architecture, distribute link equity, fix orphan pages, and reduce crawl depth for better rankings. Part of a 20-skill SEO & GEO workflow suite. 内链优化/站内架构/链接权重/网站层级/站内优化
Daily triage of Wilma school notifications for Finnish parents. Fetches exams, messages, news, schedules, and homework — filters for actionable items, syncs exams to Google Calendar, and reports via chat. Requires the `wilma` skill and `gog` CLI (or `gog` skill from ClawHub) for calendar access.
Управление задачами WEEEK через Public API (Task Manager): получать список задач, создавать/обновлять/завершать задачи, перемещать между досками/колонками, получать список досок и колонок. Использовать при интеграции с WEEEK API и работе с задачами/досками/колонками.
Generate professional resumes that conform to the Reactive Resume schema. Use when the user wants to create, build, or generate a resume through conversational AI, or asks about resume structure, sections, or content. This skill guides the agent to ask clarifying questions, avoid hallucination, and produce valid JSON output for https://rxresu.me.
Smart memory search with automatic vector fallback. Uses semantic embeddings when available, falls back to built-in search otherwise. Zero configuration - works immediately after ClawHub install. No setup required - just install and memory_search works immediately, gets better after optional sync.
