Agent Skills Hub

agentdb-state-manager

Persistent state management and workflow analytics using DuckDB for task dependency tracking, historical metrics, and context checkpointing.

linkedin-sales-navigator-alt

Build targeted prospect lists by analyzing public LinkedIn profiles and business data to identify decision-makers, track career moves, and enrich leads for outreach.

training-data-curation

Guidelines for curating high-quality datasets for LLM post-training (SFT/DPO/RLHF), covering data formats, quality filtering, and collection strategies.

deep-research

A systematic, multi-angle web research agent. Use for deep investigation, complex queries, and as a mandatory pre-research step before content generation to ensure evidence-backed, high-quality results.

MigrationBox-v4

MIKE-FIRST v6.0: An enterprise multi-cloud resilience platform for compliance auditing, security intelligence, and zero-downtime cloud migration.

ring:testing-skills-with-subagents

A meta-skill for building robust AI agent skills using a TDD approach: define failure (RED), implement the skill (GREEN), and plug rationalization loopholes (REFACTOR).

gdoc

Reliably read and extract content from publicly shared Google Docs using curl for full document retrieval.

market-debrief-cn

A deep analysis tool for A-share markets generating interactive, FT-style HTML daily reports using multi-agent parallel architecture, AkShare data, and Tavily news.

video-watcher

Fetch and parse transcripts from YouTube and Bilibili videos for summarization, QA, and content extraction using yt-dlp.

literature-review

Conduct systematic literature reviews across PubMed, arXiv, and Semantic Scholar with AI-driven synthesis, verified citations, and mandatory schematic visualization.

invoice-organizer

Automates invoice and receipt organization for tax preparation by parsing files, extracting financial data, renaming documents, and filing them into a structured directory system.

batch-coordinator

Validates and coordinates batch study guide operations, preventing errors by enforcing template compatibility, file availability, and source-only policies before agent execution.