Triangulate an analysis
SkillDev toolsAnalyze one decision through independent methods or sources, compare the paths, rerun them, and reconcile disagreement. Use when a novel analysis needs corroboration and no single answer key is available.
Available today. Use it from your connected AI after setup.
No other account needed.
Connect ahel once, and every AI you use reads what you have installed.
Then ask your AI: use the Triangulate an analysis skill
What this skill tells your AI
The instructions your AI receives, as published by ai-analyst-lab/ai-analyst in .claude/skills/triangulation/SKILL.md and read by ahel’s review.
Select paths deliberately
First determine what the available data can support. Choose paths that differ in method, source, population, assumptions, or counterfactual. Opening more sessions that repeat the same method is not meaningful triangulation.
Each path must work without seeing the other paths' conclusions. Record:
- path ID;
- method;
- source;
- population;
- assumptions;
- direction as
yes,no, orunclear; and - the evidence supporting that direction.
Compare and rerun
Use helpers.evals.triangulation.build_grid to assemble the first grid. Run the same paths a second time under the same configuration. Use compare_rounds to separate run noise from persistent disagreement.
When paths disagree, locate the difference in their populations, assumptions, sources, or counterfactuals. Reconcile the difference only when the evidence supports it. Otherwise preserve the disagreement and escalate it.
When paths agree, state what their independence adds and what it still cannot establish. Convergence is not proof of correctness.
Signals
- GitHub stars
- 298
- Forks
- 137
- Last commit
- Sep 2026
Advanced
- Catalog kind
- skill
- Gateway key
triangulation- Source
- github.com/ai-analyst-lab/ai-analyst