Self-Evolving Skill – empirical results from a 5-round experiment
Five-gate validation framework prevents skill knowledge drift, but experiments limited to one domain.
A self-learning skill layer for Claude Code — distills skills from your real sessions, updates them as you work, and prunes the ones that stop getting used. No daemon, no benchmark.
Self-pruning skill layer for Claude Code that merges duplicates and updates from real usage.
Developers using Claude Code who want persistent, improving skills
Claude Code plugins · HAL
Five-gate validation framework prevents skill knowledge drift, but experiments limited to one domain.
Recursive repair loops improve skills automatically, unlike static Claude Code defaults.
Prompt library for Claude Code when AI code quality is already a known problem.
Makes agent configs first-class with 229 domain-specific rules, autofix, and LSP support — so a tiny syntax mistake stops being a silent failure. The cross-editor plugins and GitHub Action are the standout moves: lint in your IDE and enforce checks in CI. I want a clearer map of which rules target which toolchains, but the breadth of integrations is impressive.
Isolated subagent contexts mean each AI opponent truly can't see other players' cards.
Claude Code Skill pattern paper—interesting theory, but unclear if it ships as a usable tool today.