Hi @noahshinn,
I built an installable Agent Skill that implements persistent self-reflection memory based on your Reflexion paper, combined with Self-Refine (Madaan et al.) as a plug-and-play skill for AI coding assistants.
What it does:
- Core GENERATE→CRITIQUE→REFINE loop (from Self-Refine)
- Cross-session Reflexion memory — your pattern of storing verbal self-reflections for future improvement
- 6 reflection dimensions, 4 depth levels (auto-selected)
- Works with Claude Code, Cursor, Copilot, Codex CLI, and 10+ more platforms
- Zero API cost — host AI acts as its own critic
Benchmark: +21.2% average improvement across 20 test cases (5 categories).
Repo: https://github.com/Thomaszhou22/self-refine-skill
The Reflexion memory component stores error patterns discovered during self-review and carries them forward — exactly your approach of verbal reinforcement learning without parameter updates.
Would love your thoughts!
Best,
Thomas
Hi @noahshinn,
I built an installable Agent Skill that implements persistent self-reflection memory based on your Reflexion paper, combined with Self-Refine (Madaan et al.) as a plug-and-play skill for AI coding assistants.
What it does:
Benchmark: +21.2% average improvement across 20 test cases (5 categories).
Repo: https://github.com/Thomaszhou22/self-refine-skill
The Reflexion memory component stores error patterns discovered during self-review and carries them forward — exactly your approach of verbal reinforcement learning without parameter updates.
Would love your thoughts!
Best,
Thomas