Explore skills

Curates insights from reflections and critiques into CLAUDE.md using Agentic Context Engineering

Reflect on previus response and output, based on Self-refinement framework for iterative improvement with complexity triage and verification

Reflexion Plugin

Best practices for Remotion - Video creation in React

Structured deep research and investigation. ML papers, competitor analysis, market research, domain intelligence, data source discovery. Uses firecrawl for web search/scraping. Outputs actionable findings with sources and confidence levels. Use when the user says "research", "investigate", "deep dive", "analyze the market", "find papers on", "competitor analysis", or needs multi-source synthesis o

creates draft task file in .specs/tasks/draft/ with original user intent

Use when creating or developing, before writing code or implementation plans - refines rough ideas into fully-formed designs through collaborative questioning, alternative exploration, and incremental validation. Don't use during clear 'mechanical' processes

Generate ideas in one shot using creative sampling

Implement a task with automated LLM-as-Judge verification for critical steps

Refine, parallelize, and verify a draft task specification into a fully planned implementation-ready task

Spec-Driven Development (SDD) Plugin: Continuous Learning + LLM-as-Judge + Agent Swarm

Comprehensive security audit: detects insecure defaults, hardcoded secrets, sharp edges, supply chain risks, and OWASP vulnerabilities. Based on Trail of Bits methodology. Use when auditing security, reviewing config, or pre-deployment checks. For PR diffs, use /security-review instead.