23 tagged self improving agent, measured the same way as everything else here.
Browse within: self-improvement 22self-improving-ai 22self-learning 22
Skill Claude CodeCodex
Captures user facts and procedural corrections into .reflexio/ so the agent learns across sessions. Use when: (1) user states a preference, fact, config, or constraint; (2) user corrects the agent and confirms the fix with an explicit 'good'/'perfect' or by moving on without re-correcting for 1-2 turns; (3) at start…
Skill Claude CodeCodex
Run a full-sweep consolidation over all .reflexio/ files — TTL sweep + n-way cluster merge. Use when the user asks to 'clean up reflexio', 'consolidate memory', 'deduplicate playbooks', or suspects drift across sessions.
Skill Claude CodeCodex
When to use: Always active. This skill is the contract between you and the reflexio cross-session memory plugin.
Skill Claude CodeCodex
Build a phase-aware capability-evolution runtime for OpenClaw and coding agents. Use when the agent should classify work into tasklight, taskfull, agendareview, or promotionreview mode; retrieve only the most relevant prior records; write canonical evidence into .evolution/records; maintain a capability map and…