Loading...
Loading...
Found 16 Skills
After solving a non-trivial problem, detect generalizable learnings and propose skill updates. Always active — applies to every interaction.
Evolves skills based on usage patterns. Use when improving or rolling back skill definitions.
Help teams continuously improve skills, automatically identify skill optimization opportunities (such as missing essential information, format issues, version update needs, etc.), execute secure update processes (backup, modification, testing, restoration), and ensure skill quality keeps improving as the project progresses
Framework for collective skill evolution in multi-user LLM agent ecosystems — automatically distills session experience into reusable SKILL.md files and shares them across agent clusters.
After solving a non-trivial problem, detect generalizable learnings and propose skill updates so future interactions benefit automatically. Always active — applies to every interaction.
Global evolution system for ship-faster skills. Uses hooks to capture context, failures, and session summaries, then generates patch suggestions (no auto edits) via skill-improver. Use when you want the skills to self-improve safely and continuously.
Intelligent Code Debugging Assistant that helps you visualize how your code runs. When you say things like "I want to see why this function is so slow", "The code throws an error halfway through execution and I don't know where the problem is", or "This business logic is too complex and I can't figure out the execution order", I will help you trace the code execution path, identify slow-performing sections, and locate the root cause of errors. When skill optimization points are identified, I will ask if you want to call the skill-evolution-driver for optimization
Self-improve AI Factory skills based on project context, accumulated patches, and codebase patterns. Analyzes what went wrong, what works, and enhances skills to prevent future issues. Use when you want to make AI smarter for your project.
Instinct-based learning system that observes sessions via hooks, creates atomic instincts with confidence scoring, and evolves them into skills/commands/agents.
Refine, create, or retire your own skills based on recurring patterns from past sessions
Detect whether Claude Code evolution hooks are installed/enabled, and print a copy-paste fix. Use when you expect runs/evolution artifacts but nothing is being written. Triggers: hooks, evolution, runs/evolution, settings.json, PreToolUse, PostToolUse.
Hermes Agent framework by Nous Research - self-improving AI agent with built-in learning loop, three-layer memory, and automatic skill evolution