All skills
38,472 Skills
Search uses this published catalog; rankings and counts are snapshots.
china-social-research
Research any topic across China's major social platforms — Weibo, Douyin, Xiaohongshu, Bilibili, and Zhihu — simultaneously. Aggregates discussion volume, sentiment, key opinion leaders, and platform-specific trends for comprehensive China market intelligence.
apple-dev-research
Apple developer articles: search Swift, SwiftUI, Xcode, iOS, and macOS community blogs, tutorials, and write-ups, not official docs.
cometchat-a11y
Accessibility (a11y) for CometChat UI Kit integrations across all families — React, React Native, Angular, Android (V5/V6), iOS, Flutter. Covers WCAG 2.1 AA targets, keyboard navigation in chat, screen reader announcements (live regions for new messages), color contrast, focus ma
cometchat-android-v5-calls
CometChat Calls SDK v5 integration for native Android (V5 stable, Java + Kotlin Views). Covers SDK setup (Cloudsmith Maven, CallAppSettings, init), the dual-SDK ringing pattern (Chat SDK initiateCall + Calls SDK joinSession), session settings, event listeners, call logs, recordin
cometchat-android-v5-extensions
Extension architecture for CometChat Android — ExtensionsDataSource, decorators, built-in extensions, and how to create custom extensions.
cometchat-native-core
Shared rules for CometChat React Native UI Kit v5. Always loaded alongside framework (expo/bare) and placement skills. Read this first.
cometchat-native-theming
CometChatThemeProvider + CometChatI18nProvider — color tokens, typography, dark mode, per-component style overrides, and localization (18 built-in languages + custom translations). The JS theme object replaces CSS variables.
academic-slide-pragmatic-fallback
Create Chinese academic literature-report PPTs from real paper/SI figures. Use for journal-club, thesis-defense, paper-to-PPT, and slide-review tasks, especially when Image2-style full-slide generation is unavailable. Preserve the strict Image2-only route when available; otherwis

Molecular Design Toolkit
Notebook-integrated tools for molecular simulation and visualization
check-answer-consistency
Use this to get a cheap, reference-free signal that an LLM answer might be made up, by sampling the same prompt a few times and measuring agreement. Trigger on "is this answer reliable", "flag low-confidence answers", "cheap hallucination check", "confidence score without a groun
docker-agent-run
Use this skill when running a Docker Agent with `docker agent run`, choosing a safety/approval mode, using the `--sandbox` isolation flag, setting up aliases, or troubleshooting a run (missing credentials, worktrees). Even if the user just says they want to "run my agent", "make
Catalog captured:2026-11-21