RSI Phase 2: Learned proposals from model
Scanned 10/4/2026
npx -y skills add openamer/openamer --skill rsi-phase2-learned-proposals --agent claude-codeInstalls into .claude/skills of the current project.
Are you the author of Rsi Phase2 Learned Proposals?
Add the live security badge to your README — it updates automatically with every re-scan.
[](https://www.skillsdirectory.com/skills/openamer-rsi-phase2-learned-proposals)More formats (shields.io, HTML) on the badges page. Keep it an A: scan every change in CI with Pro.
---
name: rsi-phase2-learned-proposals
description: "RSI Phase 2: Learned proposals from model"
---
## RSI Phase 2: Learned Proposals
Goal: Replace rule-based proposals with model-learned patterns validated by safety rails.
Current: Rule-only (CYCLE_SECONDS, max_tokens, imports, except, stale comments)
Phase 2: Add learned proposals from 2B model with validation gates
Architecture: propose_improvement(target, content, model=None) runs rules ALWAYS, then learned proposals IF model provided and validated.
Safety: Pattern must exist in content, bindings must be preserved, kind must be in allowed set, reason must be non-empty.
Output: Logged to improvements.jsonl, acceptance rate tracked over 50 cycles.
---
RSI Phase 2 design: learned proposals from 2B model, validated by safety rails, optional integration with existing improve_once()Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.
No comments yet. Be the first to comment!