Research Analyze
SkillDev toolsInternal evidence-index analysis and verification stage for the canonical research skill.
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 Research Analyze skill
What this skill tells your AI
The instructions your AI receives, as published by runxhq/runx in skills/research/graph/analyze/SKILL.md and read by ahel’s review.
Analyze only the supplied, runtime-admitted source index. This internal stage is shared by remote/provider evidence and native local-file evidence so acquisition cannot fork the research judgment or verification contract.
Agent task contract
research-synthesize
Preserve the objective exactly and return a bounded research_candidate with:
decision:ready,needs_more_evidence, ornot_worth_publishing;research_brief: objective, scope, concise summary, and open questions;evidence_log: material claims with admittedsource_digestand matchingcontent_digest, confidence, and relevance;decision_support: bounded options whose rationales cite admitted source digests;risks: evidence-bound risks and uncertainty.
Distinguish verified evidence from inference. Do not browse, read other files,
publish, mutate a provider, or invent source identity, delivery, certification,
or settlement claims. Return needs_more_evidence when the admitted index does
not support the requested decision.
Signals
- GitHub stars
- 87
- Forks
- 101
- Last commit
- Sep 2026
Advanced
- Catalog kind
- skill
- Gateway key
research-analyze- Source
- github.com/runxhq/runx