productivity▌

Purpose: Check the agent mail inbox for pending messages, HELP_REQUESTs, and inter-agent notifications.

Use the template in references/BUG-REPORT-TEMPLATE.md. Each report must include:

Apple Vision Framework for computer vision tasks: subject segmentation, pose detection, text recognition, barcode scanning, and document processing. \n \n Covers 13+ Vision APIs across subject lifting, hand/body pose, person segmentation, text OCR, barcode detection, and document scanning with decision trees for choosing the right tool \n Includes 15 production patterns: combining APIs to exclude hands from objects, real-time gesture recognition, multi-person segmentation, fitness action classif

Guidelines and validation for writing Agent Skills compliant with agentskills.io specification. \n \n Covers skill structure (SKILL.md, references/, scripts/), frontmatter constraints (name format, description limits), and token budgets (SKILL.md <5000 tokens, references <1000 each) \n Enforces metadata best practices: use WHEN: trigger phrases in descriptions, avoid DO NOT USE FOR: keywords, keep descriptions under 60 words \n Implements progressive disclosure with just-in-time refere

Text-to-speech generation for narration, voiceovers, IVR prompts, and accessibility reads via OpenAI Audio API. \n \n Supports single clips and batch processing; defaults to gpt-4o-mini-tts-2025-12-15 with built-in voices (cedar, marin, and others) \n Includes instruction augmentation for voice affect, tone, pacing, emotion, and emphasis; instructions supported only on GPT-4o mini TTS models \n Enforces 4096-character input limit per request and 50 requests/minute rate cap; splits longer text in

Use @wire decorator for reactive data binding with Lightning Data Service or Apex methods. @wire fits LWC's reactive architecture and enables Salesforce performance optimizations.

You are an expert in mobile app monetization with deep knowledge of subscription economics, paywall psychology, and pricing strategy. Your goal is to help the user maximize revenue while maintaining user satisfaction.

Retrieve completed research task results using a run ID. \n \n Polls research task status and returns results in JSON format via the parallel-cli tool \n Requires a valid run ID as input; displays setup instructions if the CLI is not installed \n Presents output in a clear, organized format for easy consumption \n

Test-Driven Development workflow guiding the RED-GREEN-REFACTOR cycle. \n \n Structured three-phase cycle: write failing tests (RED), implement minimal code to pass (GREEN), then improve code quality (REFACTOR) \n Emphasizes behavior-driven test design using the AAA pattern (Arrange, Act, Assert) with one assertion per test \n Provides test prioritization guidance (happy path, error cases, edge cases, performance) and identifies anti-patterns to avoid \n Supports multi-agent workflows where diff

Generate Drizzle ORM schemas for Cloudflare D1 with D1-specific SQLite patterns and constraints. \n \n Handles D1 quirks: enforced foreign keys, no native BOOLEAN/DATETIME types, 100 bound parameter limit, and JSON stored as TEXT \n Produces schema files, type exports, migration commands, and DATABASE_SCHEMA.md documentation \n Includes bulk insert batching logic and D1 runtime query patterns for Workers \n Reference guides cover D1 vs standard SQLite differences, column type patterns, and migra