Agent Skills Hub

metacognition

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

massive-context-mcp

Process massive files and large codebases (10M+ tokens) by recursively chunking, sub-querying, and aggregating results to overcome LLM context limits.

videocut:剪口播

AI-powered video editing agent for talking head videos, featuring speech-to-text, disfluency detection, and browser-based review workflows.

cloudscape-codegen

Generate production-ready Cloudscape Design System React + TypeScript UI code, components, and scaffolds with accessibility, responsive patterns, and robust state handling.

java-dev

Standardized Java development guidelines including naming conventions, exception handling, Spring Boot best practices, and concurrency patterns.

auto-trading-strategy

Professional trading strategy and risk management toolkit for prediction markets and crypto, featuring trend analysis, position sizing, and stop-loss frameworks.

unity

Control the Unity Editor via Claude Code to run tests, compile scripts, manage play mode, and retrieve console logs using a file-based bridge.

qa

Browser-based QA automation for web applications. Performs automated site audits, visual regression testing, user flow verification, and issue tracking with real-time browser snapshots.

test-design-techniques

Expert systematic test design using BVA, equivalence partitioning, decision tables, and combinatorial testing to maximize coverage and minimize redundancy.

context-degradation

Diagnose, isolate, and mitigate LLM context failures like lost-in-middle, poisoning, distraction, and context clash to improve agent reliability.

gsc-assistant

Manage Google Search Console indexing: track status, sync sitemaps with GSC data, handle indexing lag, and process false positives with prioritized markdown reports.

fix

Automated code maintenance tool for React developers to resolve linting, formatting, and CI validation errors.