Agent Skills Hub

context-degradation

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

core-principles

Architectural governance and project standards for React 19 SPA development, ensuring consistency in stack integration, project structure, and agent execution rules.

vcad

Programmatic parametric CAD for AI agents. Create 3D models, mechanical parts, and complex geometries via MCP tools with support for boolean operations, patterns, and multi-format exports (STL, GLB, STEP).

linear

Linear issue management and synchronization for LobeHub, featuring automated PR referencing, sub-issue tree decomposition, and status tracking.

frontend-accessibility-best-practices

Accessibility best practices and patterns for React applications to ensure WCAG compliance, semantic structure, and inclusive user experiences.

session-reflection-analysis

Analyze Claude Code session history to identify inefficiencies, optimize token usage, and suggest workflow improvements.

ui-design-system

Professional UI design system toolkit for design token generation, component architecture, responsive calculations, and developer handoff documentation to ensure visual consistency.

semgrep-rule-creator

Create, test, and validate custom Semgrep rules for security vulnerabilities and code pattern detection.

frontend-design

Build distinctive, production-grade frontend interfaces and web components with high aesthetic quality, avoiding generic AI design patterns.

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.

videocut:剪口播

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

find-bugs

Perform automated security audits, bug detection, and code quality assessments on local branch diffs using a structured, checklist-driven verification process.