All Skills

Create custom tools for Vapi voice assistants including function tools, API request tools, transfer call tools, end call tools, and integrations with Google Calendar, Sheets, Slack, and more. Use when adding capabilities to voice agents, building tool servers, or integrating external APIs.

Proactively detect and execute code refactoring to maintain DDD architecture and code quality. Triggers: RF, refactor, 重構, 拆分, split, 模組化, modularize, 太長, cleanup, 整理, clean, 優化, optimize, extract, 提取, simplify, 簡化, 複雜度, complexity, 重組, reorganize, 改善, improve.

This skill should be used when user asks to "query Supabase", "list Supabase tables", "get Supabase schema", "search Supabase records", "check Supabase database", "Supabase auth", "Supabase authentication", "RLS policy", "row level security", "Supabase foreign key", "table relationships", "Supabase join", "Supabase filter", "Supabase pagination", or needs guidance on Supabase database patterns, auth flows, RLS policies, or query best practices.

Generate or edit images using Google Gemini API via nanobanana. Triggers: "nanobanana", "generate image", "create image", "edit image", "AI drawing", "图片生成", "AI绘图", "图片编辑", "生成图片".

Configures the Unlayer editor — feature flags, appearance, theming, merge tags, design tags, display conditions, special links, HMAC security, file storage, image uploads, localization, custom fonts, validation.

Use when user wants to execute long-running tasks that require multiple sessions to complete. This skill manages task decomposition, progress tracking, and autonomous execution using Claude Code headless mode with auto-continuation. Trigger phrases: "autonomous", "long-running task", "multi-session", "自主执行", "长时任务", "autonomous skill".

Generate architecture artifacts from confirmed TML primitives. Produces three outputs: The Map (plain-language architecture document), The Changelog (provenance trail), and The Agent Brief (operational instructions for AI). No jargon. No TML terminology in output. Part of the TML capture pipeline — runs after tml-infer, feeds into tml-so-what.

Show epic dependency graph and execution order. Use when asking 'what's blocking what', 'execution order', 'dependency graph', 'what order should epics run', 'critical path', 'which epics can run in parallel'.

Reviews code for quality, best practices, and potential issues. Use when asked to review, audit, or check code for problems.

John Carmack-level implementation review via RepoPrompt or Codex. Use when reviewing code changes, PRs, or implementations. Triggers on /flow-next:impl-review.

Comprehensive codebase assessment for agent and production readiness. Scans 8 pillars (48 criteria), verifies commands work, checks GitHub settings. Reports everything, fixes agent readiness only. Triggers on /flow-next:prime.

Scaffold repo-local Ralph autonomous harness under scripts/ralph/. Use when user runs /flow-next:ralph-init.

Decomposes large Markdown documentation into an optimized .agent context structure. Use this skill when: (1) Starting a new project with a large requirements document, (2) Migrating legacy docs to .agent structure, (3) Refactoring existing context files for better organization, (4) Converting PDFs or long READMEs into agent-friendly files, or (5) Optimizing context window usage by splitting monolithic docs into Tasks, Memories, Workflows, and References.

Create structured build plans from feature requests or Flow IDs. Use when planning features or designing implementation. Triggers on /flow-next:plan with text descriptions or Flow IDs (fn-1-add-oauth, fn-1-add-oauth.2, or legacy fn-1, fn-1.2, fn-1-xxx, fn-1-xxx.2).

Use this skill when the user wants to interact with Google NotebookLM (notebooklm.google.com). Triggers on requests to query notebooks, search documents, add sources (URLs, GDrive, PDFs), generate audio podcasts/videos from documents, share notebooks, or manage the NotebookLM library. Use this skill for source-grounded answers without hallucination.

Optional local install of flowctl CLI and CLAUDE.md/AGENTS.md instructions. Use when user runs /flow-next:setup.

A skill with references, metadata, and all optional fields.

Carmack-level plan review via rp-cli context builder + chat. Use when reviewing implementation plans, architecture docs, or design specs. Triggers on mentions of plan review, design review, or architecture review.

High-performance data manipulation and transformation using Pandas, Numpy, and DuckDB. Use when Claude needs to: (1) Clean or transform structured data (CSV, Parquet, JSON), (2) Perform large-scale aggregations or analytics, (3) Optimize analysis for performance and memory, (4) Implement the 'Tidy Data' (Wide-to-Long) strategy for reporting.

Create structured build plans from feature requests, bug reports, or Beads issue IDs. Use when planning features, designing implementation, preparing work breakdown, or when given a bead/issue ID to plan. Triggers on /flow:plan with text descriptions or issue IDs (e.g., bd-123, gno-45, app-12).

This skill should be used when the user asks to "understand context", "explain context windows", "design agent architecture", "debug context issues", "optimize context usage", or discusses context components, attention mechanics, progressive disclosure, or context budgeting. Provides foundational understanding of context engineering for AI agent systems.

Comprehensive web quality audit covering performance, accessibility, SEO, and best practices. Use when asked to "audit my site", "review web quality", "run lighthouse audit", "check page quality", or "optimize my website".

Enforce clean separation between core openskills-runtime and optional WASM build plugins so plugin compilation does not break runtime consumers or language bindings.

Interact with Obsidian vaults using the Obsidian CLI to read, create, search, and manage notes, tasks, properties, and more. Also supports plugin and theme development with commands to reload plugins, run JavaScript, capture errors, take screenshots, and inspect the DOM. Use when the user asks to interact with their Obsidian vault, manage notes, search vault content, perform vault operations from the command line, or develop and debug Obsidian plugins and themes.