productivity▌

Build robust integrations with external services using standardized patterns for API calls, error handling, authentication, and data transformation.

Query Google NotebookLM notebooks directly from Claude for source-grounded, citation-backed answers. \n \n Automates browser-based interaction with NotebookLM to retrieve answers exclusively from your uploaded documents, with each query opening a fresh session \n Manages notebook library locally with metadata tagging, search, and activation; supports smart discovery of notebook content when adding new sources \n Requires one-time Google authentication via visible browser login; handles virtual e

Generate a single comprehensive weekly briefing that covers every external customer or prospect call in the next 7 days, with per-meeting account and contact research from Common Room.

camsnap \n Use camsnap to grab snapshots, clips, or motion events from configured cameras. \n Setup \n \n Config file: ~/.config/camsnap/config.yaml \n Add camera: camsnap add --name kitchen --host 192.168.0.10 --user user --pass pass \n \n Common commands \n \n Discover: camsnap discover --info \n Snapshot: camsnap snap kitchen --out shot.jpg \n Clip: camsnap clip kitchen --dur 5s --out clip.mp4 \n Motion watch: camsnap watch kitchen --threshold 0.2 --action '...' \n Doctor: camsnap doctor --pr

Verify that fix commits properly address audit findings without introducing new bugs or security vulnerabilities.

The CLI uses Chrome/Chromium via CDP directly. Install via npm i -g agent-browser, brew install agent-browser, or cargo install agent-browser. Run agent-browser install to download Chrome. Run agent-browser upgrade to update to the latest version.

本技能文档包含小红书创作者平台的详细发布流程、DOM选择器和操作步骤。

When this skill is triggered, you MUST follow this workflow before writing any code.

Real-time weather and forecast data for locations across China. \n \n Provides two core endpoints: real-time weather (temperature, humidity, wind, air quality) and multi-day forecasts with daily highs and lows \n Accepts Chinese location names (cities or districts) as query parameters; supports major cities and most districts nationwide \n Includes practical helper patterns for weather-based recommendations, multi-city comparisons, and travel suitability checks \n Returns structured JSON respons

Advanced prompt patterns for few-shot learning, chain-of-thought reasoning, optimization, templates, and system prompt design. \n \n Covers five core pattern categories: few-shot example selection with semantic diversity, chain-of-thought reasoning traces, iterative optimization workflows with A/B testing, modular template systems with variable interpolation, and comprehensive system prompt architecture \n Includes structured implementation workflows for creating new prompts, optimizing existing