Skill UI

Acts as a collaborative writing partner, helping you build outlines, research with citations, improve hooks, and review each section so blogs, tutorials, thought leadership, and docs get polished without losing your voice.

Dispatch parallel agents to tackle independent failures concurrently so each investigator stays focused on one domain; review their summaries, check for conflicts, and run the full suite to integrate fixes faster than sequential debugging.

A comprehensive guide to optimizing Fireflies.ai subscription costs. Learn how to reduce expenses by auditing user utilization, configuring selective recording policies, managing storage retention, and accurately right-sizing your plan (Pro, Business, Enterprise). Ideal for teams reviewing billing or implementing cost-saving measures.

Dispatching parallel agents lets you split independent investigations into focused prompts, coordinate isolated fixes concurrently, and review summaries for integration once each agent finishes.

Guides an agent to critically review a written implementation plan, execute every outlined step with required verifications, and hand off completion via finishing-a-development-branch procedures, ensuring blockers prompt clarification.

This skill transforms flawed writing — whether pasted text or uploaded documents — into publication-ready prose. It eliminates grammatical, spelling, punctuation, clarity, and tone issues while strictly preserving the author’s original intent and unique voice. Use it for professional document refinement, academic paper polishing, or general text review, ensuring the corrected version maintains your authentic style.

Analyzes research papers to break down structure and summarize key points, offering citation highlights and insights for desk research or literature review planning.

This skill aggregates a user's entire year's work—including GitHub PRs, Notion documents, and Linear tickets—into a single, structured Notion document. It automatically groups these artifacts by project, providing a comprehensive and organized summary ideal for professional reviews or annual performance documentation (e.g., SRED preparation).

Batch-categorize uncategorized transactions by clustering similar descriptions, researching unknown merchants, and creating rules or annotations so future payments auto-classify with minimal manual review.

This skill automatically drafts professional email replies for multiple corporate accounts. It handles various communication intents, including intro acceptances, scheduling follow-ups, acknowledgments, and positive replies. It operates strictly in draft-only mode, ensuring drafts are ready for user review but never sent automatically. It is ideal for automating responses triggered by new emails, webhooks, or action item follow-ups.

Autonomously improve a generated paper through multiple review-fix-recompile rounds with fresh LLM reviewer feedback, fixing inconsistencies and polishing presentation.

A robust internal utility for integrating system status updates with Feishu/Lark. It allows other skills to send structured notifications (e.g., experiment complete, checkpoint waiting, review scores) via webhooks. Supports both 'Push only' (fire-and-forget) and 'Interactive' (bidirectional polling) modes, guaranteeing zero side effects if configuration is missing.