Decide whether to use one analysis
SkillDev toolsDecide whether the evidence for one analysis supports acting, investigating, abstaining, or marking the review incomplete. Use after reliability, provenance, query, or triangulation checks.
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 Decide whether to use one analysis skill
What this skill tells your AI
The instructions your AI receives, as published by ai-analyst-lab/ai-analyst in .claude/skills/score-analysis/SKILL.md and read by ahel’s review.
Keep the evidence dimensions separate:
- task and metric meaning;
- source and freshness;
- execution and query checks;
- repeated behavior;
- independent analytical support;
- interpretation;
- safety and authorization; and
- unresolved evidence.
Mark each criterion as pass, fail, flag, unknown, error, blocked, or not applicable. Mark it as blocking when failure makes the analysis unsafe to use for the stated decision. Otherwise mark it diagnostic.
Use helpers.evals.scorecard.decide. Never average the criteria into one confidence number. A clean receipt cannot cancel a wrong result. A stable result cannot substitute for ground truth.
Return one recommendation:
actwhen all required evidence passes for the stated consequence;investigatewhen a specific unresolved issue could change the answer;abstainwhen a blocking correctness or safety criterion fails; orincompletewhen too little evidence exists to decide.
Signals
- GitHub stars
- 298
- Forks
- 137
- Last commit
- Sep 2026
Advanced
- Catalog kind
- skill
- Gateway key
score-analysis- Source
- github.com/ai-analyst-lab/ai-analyst