发现 Skills

Type-safe environment variable validation using Zod with a Drizzle-like schema API. Supports server/public fields, feature flags, either-or constraints, and client-side protection.

Create and edit Obsidian Bases (.base files) with views, filters, formulas, and summaries. Use when working with .base files, creating database-like views of notes, or when the user mentions Bases, table views, card views, filters, or formulas in Obsidian.

Use when adding new API surface, modifying existing APIs, or defining TypeScript types for framework features. Use when discussing method signatures, return types, decorator APIs, or module exports.

Use when making non-trivial changes, modifying public APIs, or proposing new framework features. Use when changes affect multiple files or require design decisions.

Trust and oversight layer for OpenClaw. Logs every action you take, alerts the user about risky actions, and blocks dangerous ones. Keeps your human informed and in control.

Build and operate a non-official WhatsApp Web gateway using Baileys to bridge WhatsApp chats with an AI or internal systems, in a separate server, without Meta/Twilio. Use when asked for an OpenClaw-style gateway, a WhatsApp relay, a bidirectional WhatsApp bot, or a "connect Codex chat to WhatsApp" request that must avoid the Business Platform.

Use when the user wants to process, analyze, or manipulate images using local tools — detect objects, find items by description, crop, resize, blur, overlay, draw annotations, run OCR, or inspect metadata. Trigger phrases include "detect objects", "find in image", "crop image", "resize photo", "blur area", "add text to image", "read text from image", "overlay images", "rotate image", "draw on image", "image metadata", "annotate screenshot".

Data-driven content optimization agent that reverse-engineers top-ranking pages to provide actionable content guidelines, scoring, and keyword recommendations. (Modeled after SurferSEO)

Expert in deepening ideas using iterative questioning (Why?, What If?, How Might We?). Use to transform preliminary ideas into robust insights.

Build 3D applications with React Three Fiber (R3F), the React renderer for Three.js. Use this skill when building 3D scenes with React, using declarative JSX for 3D objects, integrating Three.js with React state/lifecycle, or using Drei helpers. Covers Canvas setup, hooks, Drei utilities, performance patterns, and state management for 3D React apps.

Test-Driven Development workflow with session integration. Use when implementing features/bugfixes to enforce RED-GREEN-REFACTOR discipline. Integrates with session-management for enhanced TDD session tracking, checkpoints, and metrics.

Estimate AI-task cost and duration and calibrate over time. Trigger whenever the user gives you a non-trivial request (multi-step coding, research, writing). Output estimates in three units (human-hours, tokens, AI wall-clock seconds), then let the hook log actuals so you can learn.

This skill should be used when the user asks to "create a hookify rule", "write a hook rule", "configure hookify", "add a hookify rule", or needs guidance on hookify rule syntax and patterns.

Restrict file edits to a specific directory for the session. Blocks Edit and Write outside the allowed path. Use when debugging to prevent accidentally "fixing" unrelated code, or when you want to scope changes to one module. Use when asked to "freeze", "restrict edits", "only edit this folder", or "lock down edits". (gstack)

Land and deploy workflow. Merges the PR, waits for CI and deploy, verifies production health via canary checks. Takes over after /ship creates the PR. Use when: "merge", "land", "deploy", "merge and verify", "land it", "ship it to production". (gstack)

Use when building Next.js 14+ applications with App Router, server components, or server actions. Invoke to configure route handlers, implement middleware, set up API routes, add streaming SSR, write generateMetadata for SEO, scaffold loading.tsx/error.tsx boundaries, or deploy to Vercel. Triggers on: Next.js, Next.js 14, App Router, RSC, use server, Server Components, Server Actions, React Server Components, generateMetadata, loading.tsx, Next.js deployment, Vercel, Next.js performance.

Weekly engineering retrospective. Analyzes commit history, work patterns, and code quality metrics with persistent history and trend tracking. Team-aware: breaks down per-person contributions with praise and growth areas. Use when asked to "weekly retro", "what did we ship", or "engineering retrospective". Proactively suggest at the end of a work week or sprint. (gstack)

Guides strong, effective unit test generation using proven testing techniques. Use when writing unit tests, reviewing test quality, improving existing tests, generating test cases, checking test coverage strength, or when tests exist but may be weak. Triggers on: unit test, test quality, test coverage, write tests, improve tests, review tests, test strength, mutation testing, boundary testing.

Orchestrates a full morning sweep of pending items (Email, Tasks, Slack, WhatsApp, X). Use when the user asks for a sweep, morning routine, inbox sweep, or all pending items.

Capture images from device camera. Currently a placeholder - camera support depends on device capabilities.

Structured approach to conducting thorough web research with citations and organized output.

Guide content sync operations for X posts and YouTube videos. Use when user mentions "refresh feed", "sync posts", "update videos", "fetch latest", or asks about content pipeline.

TypeScript/JavaScript guardrails, patterns, and best practices for AI-assisted development. Use when working with TypeScript (.ts, .tsx) or JavaScript (.js, .jsx) files, package.json, or tsconfig.json. Provides strict mode conventions, async patterns, testing standards, and module system guidelines.

Add persistent learning and self-improvement to AI agents using the ACE framework