Agent Skills Hub

audit-skills

Audit AI skills for security vulnerabilities including prompt injection, hidden instructions, tool misuse, and data exfiltration risks.

code-review-specialist

A specialized code review agent that performs multi-dimensional analysis covering security vulnerabilities, performance optimization, code quality, and maintainability standards.

training-data-curation

Guidelines for curating high-quality datasets for LLM post-training (SFT/DPO/RLHF), covering data formats, quality filtering, and collection strategies.

metacognition

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

ui-ux-reviewer

Analyze UI/UX quality against 4 authoritative standards (NNg, Laws of UX, Apple HIG, WCAG) to receive actionable design and accessibility improvements for mobile and web components.

parallel-agents

Orchestrate complex workflows by coordinating multiple specialized AI agents for multi-perspective code analysis, feature implementation, and system-wide reviews.

speckit-workflow

A constitution-driven, spec-first development workflow for Claude Code and Codex, automating feature planning, implementation, and quality assurance through structured agentic loops.

文档分析器

Deep document structure analysis and intelligent content extraction for knowledge bases.

spec-miner

Reverse-engineering specialist for codebase analysis, dependency mapping, and specification extraction from legacy or undocumented systems.

hegelion

Dialectical reasoning and adversarial coding agent for MCP-enabled editors, forcing LLMs to resolve internal contradictions for higher quality outputs.

with-context-agent

Lints, validates, and auto-fixes AI agent configuration files like SKILL.md, CLAUDE.md, and MCP configs.

dyad:swarm-pr-review

Collaborative PR review using a swarm of three specialized AI agents (Correctness, Health, UX) that discuss findings and reach consensus before posting a structured summary with inline comments.