Agent Skills Hub

physics-student-focus

Teacher-focused student profiling tool: OCR answer sheets, summarize performance, and update student profiles with targeted physics learning goals.

open-source-maintainer

End-to-end GitHub repository maintenance agent. Automates triage, PR review, issue analysis, and maintenance reporting to ensure long-term repository health, stability, and growth.

glyphbox

A framework for an LLM-based NetHack agent that dynamically synthesizes Python code in a secure sandbox to perform complex dungeon exploration and gameplay actions via a high-level API.

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.

explaining-code

Explains code using visual diagrams, relatable analogies, step-by-step walkthroughs, and common pitfalls.

performance-security

Optimize React performance, implement security hardening, and ensure WCAG accessibility compliance with automated patterns and checklists.

code-quality-review

Holistic, multi-dimensional code review skill providing prioritized, actionable feedback on correctness, security, performance, design, and accessibility.

start

Initiates automated reverse engineering by discovering codebase architecture, layers, and technology stacks to facilitate system modernization or documentation.

security-testing

Automated security vulnerability scanner implementing OWASP Top 10 testing for SAST/DAST, dependency auditing, and auth/authorization validation in CI/CD pipelines.

Security Code Review

Analyze source code for security vulnerabilities based on OWASP Top 10 guidelines and suggest remediation strategies.

Verification & Quality Assurance

A robust verification and QA system for software agents featuring real-time truth scoring, automated code validation, and instant rollback capabilities to maintain high reliability.

recursive-decomposition

Handles large-scale tasks by automatically breaking them down into manageable, recursive sub-tasks to overcome context window limits and improve reasoning accuracy on large codebases and document sets.