productivity▌

Adopt better-result incrementally in existing codebases without rewriting everything at once.

Comprehensive assistance with ccxt development, generated from official documentation.

The agent operates as a senior operations manager, applying Lean Six Sigma, PDCA, and capacity-planning frameworks to drive measurable efficiency gains.

Quick Ref: One command, full lifecycle. /discovery → /crank → /validation. Thin wrapper that delegates to phase orchestrators. YOU MUST EXECUTE THIS WORKFLOW. Do not just describe it. THREE-PHASE RULE + FULLY AUTONOMOUS. Read references/autonomous-execution.md — it defines the mandatory 3-phase lifecycle, autonomous execution rules, anti-patterns, and phase completion logging. Unless --interactive is set, RPI runs hands-free. Do NOT stop after Phase 2. Do NOT ask the user anything between phases

Native home screen widgets for Flutter apps on iOS and Android with cross-platform data sharing. \n \n Establishes data sharing between Dart and native platforms via App Groups (iOS) and SharedPreferences (Android), enabling widget updates from your Flutter app \n Supports simple text-based widgets and complex Flutter UI rendered as static images for native display \n Requires native setup in Xcode (Widget Extension target with Swift TimelineProvider) and Android Studio (AppWidgetProvider with X

当用户没有明确指定时间范围时，根据用户意图推断合适的 relative_time，确保返回的消息能完整覆盖用户关心的内容。用户明确指定时间时直接使用用户的值。

Generate or edit images via OpenAI's API with a bundled CLI for deterministic, reproducible runs. \n \n Supports three workflows: generate new images, edit existing images (inpainting, masking, background replacement, object removal), and batch runs across multiple prompts or variants \n Defaults to gpt-image-1.5 and requires OPENAI_API_KEY for live API calls; uses the bundled scripts/image_gen.py CLI for all operations \n Includes a structured decision tree and prompt augmentation template to c

Draft personalized, low-friction investor communications for cold outreach, warm intros, follow-ups, and updates. \n \n Structures cold emails with specific personalization hooks (portfolio companies, public thesis, mutual connections) and a single concrete ask \n Provides templates for warm intro requests with forwardable blurbs under 100 words, follow-up cadence (day 4–5 and day 10–12), and post-meeting updates \n Enforces core rules: proof over adjectives, no generic copy, explicit asks, and

YouTube video search, download, and subtitle extraction with advanced filtering and sorting. \n \n Search across YouTube with keyword filtering, channel browsing, and sorting by date, view count, or relevance; supports duration and publish date filters \n Download videos at specified quality, extract audio as MP3, and retrieve subtitles in multiple languages (SRT and timestamped TXT formats) \n Browse channel videos with optional keyword search within channels, sorted by time, views, or duration

Apply SOLID design principles for maintainable, flexible code architecture.