Agent Skills Hub

literature-engineer

Evidence-first literature collector for automated research pipelines. Scales paper pools to 1200+ with metadata normalization, provenance tracking, and multi-source ingestion.

developer-growth-analysis

Analyzes Claude Code chat history to identify coding patterns and skill gaps, curates personalized learning resources from HackerNews, and sends progress reports to Slack.

Documentation Builder

Generates comprehensive API references, user manuals, and architectural system documentation directly from your codebase and technical specifications.

scholar-evaluation

Systematically evaluate scholarly work using the ScholarEval framework, providing structured, quantitative, and qualitative assessment across research quality dimensions with actionable feedback.

troubleshooting-docs

Automates the documentation of solved technical issues using YAML frontmatter, categorized directories, and institutional knowledge indexing for JUCE plugin development.

document-writer

A documentation-writing assistant for the Nuxt ecosystem, providing writing style guides, MDC component usage patterns, and content structure guidelines for technical blog posts and docs.

research-review

Get deep, critical, NeurIPS/ICML-style peer reviews of your research, paper drafts, and experimental setups using external LLMs via Codex MCP.

skill-creator

A framework for building modular, reusable agent skills. Provides guidelines for structuring SKILL.md, bundled scripts, references, and assets to extend Claude's capabilities.

market-sentiment-pulse

Aggregates and analyzes market sentiment for crypto and stock tickers by scanning news and social signals for quick trading vibe checks.

Test Skill A

A CLI tool that automates the discovery and symlinking of agent skills distributed via npm packages, simplifying integration for AI-powered coding agents.

p9

P9 Tech Lead mode: Manages P8 agent teams via Task Prompts (six-element) without direct coding. Orchestrates 3+ parallel agents for project management, task decomposition, and architecture.

novelty-check

Verify research idea novelty against recent literature. Use when user says '查新', 'novelty check', or needs to confirm if a method is original.