Agent Skills Hub

metacognition

Enforces structured self-assessment checkpoints to validate approach, mitigate risks, and ensure quality before, during, and after task execution.

xhs-writing-coach

AI-powered coach for Xiaohongshu (XHS) note writing. Generate viral, platform-optimized content with storytelling templates, engagement hacks, and automated compliance tagging.

legal-risk-assessment

Assess and classify legal risks using a severity-by-likelihood framework. Evaluate contract risk, deal exposure, and issue severity to determine if senior counsel or external review is required.

ReasoningBank Intelligence

Implement adaptive learning with ReasoningBank for pattern recognition, strategy optimization, and continuous improvement in AI agents.

github-copilot-agent-tips-and-tricks

Guidance and operational tips for identifying, reviewing, and managing pull requests created by the GitHub Copilot coding agent within your repository.

humanizer

Remove AI-generated patterns and inject natural human voice into your writing. Fixes robotic phrasing, overuse of AI vocabulary, and sterile structure to make text sound authentic.

gitnexus-pr-review

Automate pull request reviews with structural code analysis, blast radius assessment, and dependency impact mapping.

eval-harness

Official evaluation framework for AI agent sessions, implementing Evaluation-Driven Development (EDD) principles to ensure reliability.

reflect-appworld-failure

Analyze AppWorld task failures to extract specific API patterns and generate actionable playbook bullets with concrete code examples.

prompt-engineering-patterns

Master advanced prompt engineering techniques to maximize LLM performance, reliability, and controllability in production applications.

design-review

Designer's eye QA: detects and automates fixes for visual inconsistencies, spacing, hierarchy, and UI polish issues. Iteratively verifies with before/after screenshots.

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.