Skip to content
cccskills
FreePublished on GitHub

rsi-phase2-learned-proposals

RSI Phase 2: Learned proposals from model

The English summary is being prepared. Showing the original description.

See how to install

Files included (1)

  • SKILL.md847 B

SKILL.md (original)

Review the instructions the agent will receive before you install.

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()

Reviews

No reviews yet. Tell others what you thought.

Comments

No login needed. Share how it worked for you, ask a question, or note where it did not run.

No comments yet. Be the first to write one.

Comments are published right away. Do not include personal information such as email addresses or phone numbers. Up to 2 URLs.

0 / 1,000 characters

This form is protected by reCAPTCHA, and the Google Privacy Policy and Terms of Service apply.

More skills from this repository

Build integrated IS/BS/CF financial workbooks in Excel.

The English summary is being prepared. Showing the original description.

openamer/openamer8Updated Oct 22, 2026

Run and grow the OpenAmer Agent-to-Agent swarm: identity, trust, node-to-node ask, signed skill/insight sharing, and the autonomous self-learning loop.

The English summary is being prepared. Showing the original description.

openamer/openamer8Updated Oct 22, 2026

Use for A/B experiments on OpenAmer configs and skills.

The English summary is being prepared. Showing the original description.

openamer/openamer8Updated Oct 22, 2026

Roleplay a hostile user to find and triage UX pain points.

The English summary is being prepared. Showing the original description.

openamer/openamer8Updated Oct 22, 2026

Agent mesh: master/worker nodes, HTTP delegation, heartbeat.

The English summary is being prepared. Showing the original description.

openamer/openamer8Updated Oct 22, 2026

Use for agentic commerce payments tasks. Candidate synthesized from trend radar; awaiting trial promotion.

The English summary is being prepared. Showing the original description.

openamer/openamer8Updated Oct 22, 2026

See all skills by openamer

Report a problem with this skill