Agent Skills Hub

paper-reproduce

Systematic methodology for reproducing published academic papers using provided data, including sample selection, statistical verification, and automated reporting.

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.

customer-research

Multi-source research tool for customer inquiries, bug investigations, and account history synthesis with source attribution and confidence scoring.

academic-researcher

Academic research assistant for literature reviews, paper analysis, methodology critique, and scholarly writing support.

gh-ticket

Create and update comprehensive GitHub issues with full technical context to prevent requirement loss and reduce implementation friction.

statistical-analysis

Guided statistical analysis with test selection, assumption checking, power analysis, and APA-formatted reporting for academic and experimental research.

peer-review

Structured manuscript and grant review assistant utilizing checklist-based evaluation for methodology, statistical validity, and compliance with reporting standards like CONSORT and STROBE.

ai-collaboration-standards

Prevents AI hallucination and ensures evidence-based, verifiable outputs when analyzing code, reviewing technical documents, or providing recommendations.

performance-correlation

Correlate content attributes with GA4 and GSC metrics to identify performance drivers and optimization opportunities.

clinical-trial-protocol-skill

Generate clinical trial protocols for medical devices and drugs. Supports modular, waypoint-based design, research integration, and regulatory documentation alignment.

translate

Translate research papers (markdown) while preserving LaTeX formulas, code blocks, and images, with support for batch processing, retries, and portable bundles.

agent-canvas

Orchestrate visual communication by drawing diagrams, flowcharts, and annotations on a TLDraw canvas via CLI. Ideal for architectural planning, PR reviews, and logging agent output.