productivity▌

通过 Bitable API 操作数据、字段、视图和权限。

Generate and edit high-quality images using FLUX and Gemini AI models via OpenRouter. \n \n Supports both image generation from text prompts and editing of existing images with instruction-based modifications \n Two primary models available: Gemini 3 Pro (high quality, supports both generation and editing) and FLUX.2 Pro (fast, high quality, supports both modes); FLUX.2 Flex available for generation-only use cases \n Requires OpenRouter API key configured via .env file or environment variable; s

Expert guide for optimizing LLM prompts through patterns, testing, and systematic refinement. \n \n Covers five core techniques: few-shot learning, chain-of-thought reasoning, prompt optimization, template systems, and system prompt design \n Includes progressive disclosure patterns that scale complexity from simple instructions to multi-example reasoning traces \n Provides practical examples for each pattern, from code review templates to bug analysis workflows \n Emphasizes testing and iterati

Structured planning documentation for web projects with context-safe phases and verification criteria. \n \n Generates IMPLEMENTATION_PHASES.md (always) plus conditional docs like DATABASE_SCHEMA.md, API_ENDPOINTS.md, ARCHITECTURE.md, and CRITICAL_WORKFLOWS.md based on project complexity \n Phases sized for single 2-4 hour sessions with ≤8 files, clear task lists, and specific verification checkpoints (HTTP status codes, form validation, CRUD operations) \n Asks 3-5 clarifying questions upfront

sentry-browser-sdk

Fetch and analyze content from one or more URLs using Gemini 2.5 Flash with URL context.

Unsafe Rust code review and FFI soundness checker for identifying memory safety violations. \n \n Triggers on 30+ unsafe patterns including raw pointers, transmute, FFI declarations, uninitialized memory, and missing SAFETY documentation \n Provides reference tables for valid unsafe use cases (FFI, low-level abstractions, performance bottlenecks) and common errors with fixes \n Covers FFI tooling recommendations (bindgen, cbindgen, PyO3, napi-rs) and deprecated patterns with modern alternatives

cli-anything

Comprehensive GitHub repository analysis through multi-round research combining API data, web search, and structured reporting. \n \n Executes four research rounds: GitHub API extraction, discovery searches, deep investigation with web fetching, and timeline analysis from commits and issues \n Produces structured markdown reports with executive summaries, chronological timelines, metrics tables, and Mermaid diagrams for architecture and comparisons \n Implements source prioritization (official d

Guides brand strategy: purpose, values, positioning, storytelling, voice, and visual identity. Companies with consistent branding see 23–33% revenue lift; people remember stories ~22× more than facts alone. Use this skill when defining a new brand, auditing consistency, or aligning messaging across touchpoints.