All Skills

为复杂任务建立三层执行墙：先做任务理解与计划，再做工具选择与风险控制，最后输出成品级交付。适用于调研、诊断、代码修改、系统排障、方案撰写、多工具联动等 3 步以上任务。

Monitor blogs and RSS/Atom feeds via blogwatcher-cli tool.

Add MCP Server mode to Hermes — expose Hermes tools to external AI clients via Model Context Protocol

Passive domain reconnaissance using Python stdlib. Subdomain discovery, SSL certificate inspection, WHOIS lookups, DNS records, domain availability checks, and bulk multi-domain analysis. No API keys required.

极简编辑风预设 — 基于 taste-anti-slop 的低 VARIANCE 配置。克制、留白、排版驱动。适用于作品集、文档站、编辑类产品。

GSAP animation for HTML/React — core tweens, timelines, ScrollTrigger, React useGSAP hooks, performance best practices. Use when building animated web pages, scroll-driven effects, React/Next.js animations, or any HTML/CSS animation beyond simple transitions. Pairs with claude-design / guizang-ppt / html-to-video.

Maps user flows and journey maps with decision points, error states, and optimization suggestions

Analyzes application logs to identify errors, performance issues, and security incidents

Generate realistic test data with proper relationships, constraints, and edge cases

Parses documents with OCR including table extraction, handwriting recognition, and layout analysis

Creates display advertising banners in multiple sizes with A/B testing variants and CTR optimization

Designs data-driven infographics with charts, statistics, and visual storytelling elements

Builds Retrieval-Augmented Generation pipelines with vector stores, chunking strategies, and reranking

Generates low-fidelity wireframes from feature descriptions with layout suggestions and component placement

Generates spaced repetition flashcards from textbooks, notes, or lectures with multimedia support

Conducts keyword research with search volume estimates, difficulty scores, and content gap analysis

Automates podcast video editing with speaker detection, highlight clips, and social media cuts

Matches events with venues based on capacity, amenities, budget, and location requirements

Optimizes DAW workflows with template creation, keyboard shortcuts, and session organization strategies

Generates personalized workout plans with progressive overload, periodization, and exercise variations

Creates consistent icon sets in multiple sizes and formats for web and mobile applications

Searches automotive parts catalogs with VIN decoding, compatibility checking, and price comparison

Designs Redis caching strategies with key patterns, TTL policies, and eviction configurations

Creates visual storyboards from scripts with shot composition, camera angles, and timing notes

Assists with visual effects compositing workflows including green screen, particle effects, and color matching

Map career development paths with skill gap analysis and learning recommendations

When the user wants to create or optimize popups, modals, overlays, slide-ins, or banners for conversion purposes. Also use when the user mentions "exit intent," "popup conversions," "modal optimization," "lead capture popup," "email popup," "announcement banner," "overlay," "collect emails with a popup," "exit popup," "scroll trigger," "sticky bar," or "notification bar." Use this for any overlay or interrupt-style conversion element. For forms outside of popups, see cro. For general page conversion optimization, see cro.

Comprehensive design skill: brand identity, design tokens, UI styling, logo generation (55 styles, Gemini AI), corporate identity program (50 deliverables, CIP mockups), HTML presentations (Chart.js), banner design (22 styles, social/ads/web/print), icon design (15 styles, SVG, Gemini 3.1 Pro), social photos (HTML→screenshot, multi-platform). Actions: design logo, create CIP, generate mockups, build slides, design banner, generate icon, create social photos, social media images, brand identity, design system. Platforms: Facebook, Twitter, LinkedIn, YouTube, Instagram, Pinterest, TikTok, Threads, Google Ads.

Use when designing AI product first-run or blank-slate UX — chat empty state, example prompts, capability discovery, templates, nudges, or follow-ups. Trigger on "users don't know what to ask", onboarding, suggestion chips, or discoverability.

Use when building or debugging interactive 3D scenes on the web with Three.js (scene/camera/renderer, lights/materials, GLTF loading, controls, performance). Helpful for designers shipping 3D UI moments.

When the user wants to write, rewrite, or improve marketing copy for any page — including homepage, landing pages, pricing pages, feature pages, about pages, or product pages. Also use when the user says "write copy for," "improve this copy," "rewrite this page," "marketing copy," "headline help," "CTA copy," "value proposition," "tagline," "subheadline," "hero section copy," "above the fold," "this copy is weak," "make this more compelling," or "help me describe my product." Use this whenever someone is working on website text that needs to persuade or convert. For email copy, see emails. For popup copy, see popups. For editing existing copy, see copy-editing. For the offer underneath the copy (bonuses, guarantees, value framing), see offers.

Analyze Stitch projects and synthesize a semantic design system into DESIGN.md files

Use when designing AI product trust, privacy, or honesty UX — cloud disclosure, voice/mic consent, transcript retention, memory ownership, AI labeling, caveats, or audit footprints. Trigger on disclose cloud, recording consent, watermark, incognito, or data-ownership settings.

Use when designing/implementing UI with Tailwind CSS (layout, typography, responsive, theming, component patterns). Includes quick recipes and conventions for clean, consistent web design.

Use when designing or rewriting a high-converting landing page (single-offer page) for SaaS/apps/services. Covers structure, layout patterns, conversion strategies, copywriting, SEO/AEO, and common pitfalls.

Three.js interaction - raycasting, controls, mouse/touch input, object selection. Use when handling user input, implementing click detection, adding camera controls, or creating interactive 3D experiences.