Agent Skills Hub

design-md

Analyze Stitch projects and synthesize a semantic design system into DESIGN.md files to serve as a source of truth for AI-driven UI generation.

skill-vetter

Security-first vetting protocol for AI agent skills. Detects red flags like credential theft, obfuscated code, and unauthorized data exfiltration before installation.

problem-mapping

Structured problem-framing tool for design sprints and product strategy. Facilitates collaborative or individual sessions to define goals, stakeholders, constraints, and pain points before solution generation.

always-works-testing

Mandatory execution-based validation for all software implementation tasks. Ensures code works through empirical verification before confirmation.

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.

context-degradation

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

skill-code-review

Multi-LLM code review pipeline using consensus-based analysis to detect security, architectural, and quality issues.

deep-thinking

A deep reasoning protocol that ensures systematic analysis, multi-hypothesis generation, and rigorous verification for complex architectural, debugging, and high-stakes tasks.

visual-creative

AI-powered creative visual prompt generator for posters, banners, product shots, and social media content.

swarm-advanced

Orchestrate complex multi-agent swarms with topologies like mesh, hierarchical, and star for research, development, and testing workflows.

sequential-thinking

Structured reasoning tool for complex problem decomposition, step-by-step analysis, consistency verification, and evidence-based synthesis with confidence scoring.

code-quality-review

Holistic, multi-dimensional code review skill providing prioritized, actionable feedback on correctness, security, performance, design, and accessibility.