Conformance loop

SkillDev tools

Lets your agent iteratively improve Fallow analysis accuracy by comparing results against competing tools and verified sources.

Available today. Use it from your connected AI after setup.

Connect ahel once, and every AI you use reads what you have installed.

Then ask your AI: use the Conformance loop skill

About this capability

Iteratively improve Fallow analysis accuracy by comparing it with competing tools and verified source truth across a stable real-world corpus.

What this skill tells your AI

The instructions your AI receives, as published by fallow-rs/fallow in .agents/skills/conformance-loop/SKILL.md and read by ahel’s review.

  1. Define the capability and stable project corpus.
  2. Run Fallow and comparison tools with documented equivalent settings.
  3. Manually verify disagreements against source.
  4. Classify true positive, false positive, false negative, or model difference.
  5. Implement one general correction with a regression fixture.
  6. Re-run the full corpus and retain only net improvements.
  7. Run review.

Competitor output is a lead, not ground truth.

Signals

GitHub stars
4k
Forks
155
Last commit
Sep 2026
Advanced
Catalog kind
skill
Gateway key
conformance-loop
Source
github.com/fallow-rs/fallow