Diagnose slow SQL and rewrite queries for safer performance. Use when handling development work that needs repeatable steps, quality gates, and practical outputs.
Control browser automation agents via the Bits MCP server. Use when running web scraping, form filling, data extraction, or any browser-based automation task. Bits agents can navigate websites, click elements, fill forms, handle OAuth flows, and extract structured data.
Fast, accurate, and incredibly inexpensive automatic speech-to-text transcription service.
Find missing tests by failure mode and business impact. Use when handling development work that needs repeatable steps, quality gates, and practical outputs.
Fetch Telegram chat message history via MTProto user API (Telethon). Use when needing to read old messages from any Telegram chat, group, or forum topic that the bot API can't access. Supports fetching by chat ID, forum topic/thread, message count, pagination, and JSON output. Requires one-time user login with phone number + 2FA.
Deterministic rule-based system for classifying clarified input into a single primary task category and assigning execution complexity. Use when the Main Agent needs to categorize user requests before task decomposition, route tasks to appropriate handlers, assess complexity and risk levels, or determine if clarification is needed. Triggers after clarification is complete and before decomposition begins.
Publish podcast episodes from RSS + Notion to Substack with reliable Apple Podcasts embedding and image extraction, then generate LinkedIn-ready companion posts. Use when asked to run or improve podcast-to-substack workflows, fix Notion image fetch failures, prevent Substack embed-as-text issues, or cross-post episode summaries to LinkedIn.
Core GOYFILES external-bot contract (endpoint-first onboarding, strict agent behavior, direct tool mode, and text-fetch contract).
Process links and content shared in the #interesting-finding Discord channel. Use when: (1) a URL or article is shared in #interesting-finding, (2) someone asks to log or analyze content from #interesting-finding, (3) performing a heartbeat check and #interesting-finding has new unread content. Workflow: fetch URL → analyze → create Discord thread → post summary to thread → save distilled notes to knowledge base (memory/kb/).