Claude Reflect
A self-learning system for Claude Code that captures corrections, positive feedback, and preferences — then syncs them to CLAUDE.md and AGENTS.md.
Install
npx skills add BayramAnnakov/claude-reflect -a claude-code
npx skills add BayramAnnakov/claude-reflect -a claude-code -g
Or copy the skill folder into .claude/skills/ (project) or ~/.claude/skills/ (all projects).
See the repository README for installation instructions.
When to use
Use it if you keep repeating the same corrections to Claude and want them written into your project memory files.
claude-reflect is a self-learning system for Claude Code. When you correct Claude, for example "no, use gpt-5.1 not gpt-5," it captures the correction, along with positive feedback and preferences, and syncs them to CLAUDE.md and AGENTS.md. It also discovers workflow patterns and turns them into reusable skills.
There are two ways to run it. The plugin, in Python, queues corrections with a hook and you review them later with /reflect. The newer mod, reflect-mod, uses a model check that spots corrections immediately in any language and shows them in a band above the prompt. Pick one of the two. Review each proposed memory before you accept it.
Related skills
-
rea
Lets your agent reverse engineer an app from the outside, down to native binaries, and then build its own version.
-
superpowers
A set of development habits for your agent: test first, debug systematically, and plan before you code.
-
skills
The skills Matt Pocock uses in his own day-to-day engineering work.
-
ECC
A ready-made setup for coding agents that adds skills, persistent memory and security checks.