productivity▌

Manage Google Groups settings via CLI with get, patch, and update operations. \n \n Provides three methods for the groups resource: get to retrieve settings, patch for incremental updates, and update for full replacements \n Requires the gws binary and authentication setup documented in the shared skill prerequisites \n Use gws schema to inspect method signatures, required parameters, and data types before constructing API calls \n Supports --params and --json flags for passing configuration dat

你是 dontbesilent 的执行力诊断 AI。你的任务是帮用户搞清楚：为什么他知道该做什么，但就是不做。

Spec-driven autonomous AI coding with fresh context per task using iterative bash loops. \n \n Implements Geoffrey Huntley's methodology where each loop iteration starts a new agent process with a clean context window, preventing degradation over long sessions \n Requires clear, testable acceptance criteria in specification files; agent outputs <promise>DONE</promise> only when all criteria are verified and tests pass \n Maintains shared state on disk via specs/ , ralph_history.txt , a

When analysis requires computation (statistics, data processing, scoring, enrichment), write and run Python code via Bash. Don't describe what you would do — execute it and report actual results. Use ToolUniverse tools to retrieve data, then Python (pandas, scipy, statsmodels, matplotlib) to analyze it.

CLI wrapper for MCP servers, OpenAPI specs, and GraphQL endpoints without code generation. \n \n Supports three source types: MCP over HTTP/stdio, OpenAPI (JSON/YAML, local or remote), and GraphQL endpoints \n Dynamic command discovery with --list and --search filtering; inspect any command with --help before execution \n Built-in authentication: API key headers, OAuth (authorization code + PKCE), environment variables, and file-based secrets \n Output control via --jq for JSON filtering, --head

Convert text to natural-sounding speech with single or multi-speaker audio generation. \n \n Two modes: Quick mode for instant single-voice MP3 output, and Script mode for multi-speaker dialogue with per-character voice assignment \n Automatic mode detection based on input structure; supports both plain text and structured scripts with character markers \n Built-in speaker selection with language support (Chinese and English) and preference saving to local config \n Configurable output modes: in

PRの変更内容を分析し、後続のコードレビューフェーズに必要な情報を構造化して出力するスキルです。 軽量モデル（Haiku）での実行を想定しており、CI環境でのコスト最適化に寄与します。

Derivatives-trading-portfolio-margin request on Binance using authenticated API endpoints. Requires API key and secret key for certain endpoints. Return the result in JSON format.

Battle-tested Mapbox style patterns and layer configurations for six common mapping scenarios. \n \n Includes ready-to-use JSON layer configurations for restaurant finders, real estate, data visualization, navigation, dark mode, and delivery/logistics maps \n Provides decision tree for selecting the right pattern based on content type, environment, user action, and platform \n Covers performance optimization techniques including zoom-based filtering, data-driven styling, and clustering for dense

Guidance for selecting, integrating, and managing Rust crates and ecosystem dependencies. \n \n Provides decision tables for common needs (serialization, async runtimes, HTTP, databases, CLI parsing) with recommended crates and evaluation criteria \n Covers language interop patterns including C/C++ bindings via bindgen / cbindgen , Python extensions with pyo3 , Node.js addons via napi-rs , and WebAssembly with wasm-bindgen \n Includes error code reference (E0433, E0603) with fixes, cargo feature