Agent Skills Hub

structured-outputs-advisor

Expert advisor for implementing Anthropic's structured outputs. Choose between JSON mode and strict tool use for guaranteed schema compliance and validated agentic workflows.

brainwriting

Structured parallel brainstorming agent for ideation and conceptual expansion. Uses multi-agent perspectives to evolve vague ideas into practical, actionable visions. Ideation only, not for task planning.

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.

debug-mcp

Systematic debugging workflow for MCP servers and Microsoft Copilot Studio integrations, featuring common fix patterns and validation scripts.

notion

Connect to the Notion API to create, manage, and query pages, databases, and blocks for your AI-powered knowledge management.

ux-audit-walkthrough

Minimalist UX/Interaction Audit Expert that deconstructs complex interactions through cognitive load and operational efficiency lenses.

hs

Pre-execution security guardrails for AI agents. Validates shell commands and file reads against 400+ security patterns to block destructive operations, credential theft, and unauthorized system access.

roier-seo

AI-powered Technical SEO auditor that runs Lighthouse/PageSpeed tests and automatically applies code-level fixes for performance, accessibility, and structured data.

jlens-mcp

Expert-level Java codebase analysis and Maven dependency management skill. Enables deep bytecode inspection, multi-version dependency conflict resolution, and automated project building via MCP integration.

project-development

A framework for managing the end-to-end LLM project lifecycle, from evaluating task-model fit and pipeline architecture design to implementing structured output parsing and agent-assisted development.

test-automation-strategy

Implement professional-grade test automation strategy, manage test pyramids, detect anti-patterns, and integrate with CI/CD for resilient, fast, and high-quality software testing.

claude-code-mechanism-selector

A decision-support tool for Claude Code users to select the optimal extension mechanism—slash commands, skills, subagents, or hooks—based on project requirements.