By yorrick
Automatically extracts learnings from session transcripts and updates CLAUDE.md, README.md, and memory files to keep project documentation current with corrections, discoveries, and pain points.
A collection of Claude Code plugins by Yorrick Jansen.
Add this repository as a marketplace:
claude plugin marketplace add yorrick/claude-code-plugins
Then install any plugin:
claude plugin install <plugin-name>@yorrick
Automated development loop that composes existing Claude Code commands into a full lifecycle: brainstorm, plan, implement, create PR, then iteratively review (simplify + code review + security review) until clean.
Commands:
/dev-loop — Full lifecycle: interactive brainstorming and planning, then automated implementation and review loop/review-loop — Review loop only on an existing PR (skip brainstorm + implementation)Prerequisites:
/code-review:code-review)/simplify and /security-review (built-in)gh CLI (for creating PRs)claude plugin install dev-loop@yorrick
Automatically reflects on skills used during sessions and proposes improvements.
claude plugin install self-improve-skill@yorrick
For testing or development, load a plugin directly:
claude --plugin-dir ./dev-loop
claude --plugin-dir ./self-improve-skill
Own this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimOwn this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimBased on adoption, maintenance, documentation, and repository signals. Not a security audit or endorsement.
npx claudepluginhub yorrick/claude-code-plugins --plugin self-improve-skillAutomated development loop and ad-hoc workflow generation for orchestrating AI coding agents
Self-learning system for Claude Code that captures corrections and updates CLAUDE.md automatically
Automated development loop and ad-hoc workflow generation for orchestrating AI coding agents
Self-improving learning system that detects friction signals (corrections, repetitions, tool failures), extracts improvement candidates, and proposes rule/skill updates with explicit approval workflow.
Capture repeatable session workflows into reusable SKILL.md files. An open-source reimplementation of the internal /skillify skill.
Auto-captures Claude Code sessions as narrative worklogs and detects user steering patterns
Tools to maintain and improve CLAUDE.md files - audit quality, capture session learnings, and keep project memory current.