adjudicate-exchange
SkillDev toolsLets your agent weigh competing arguments against criteria you set and return a verdict with stated uncertainty.
Available today. Use it from your connected AI after setup.
No other account needed.
Add ahel to your AI once: Claude, ChatGPT, Cursor, Claude Code or Codex. Then ask it to use this.
Then ask your AI: use the adjudicate-exchange skill
About this skill
Evaluate competing arguments against stated criteria and produce a reasoned verdict with uncertainty.
What this skill tells your AI
The instructions your AI receives, as published by yogsoth-ai/de-anthropocentric-research-engine in skills/adjudicate-exchange/SKILL.md and read by ahel’s review.
Purpose
Evaluate competing arguments against stated criteria and produce a reasoned verdict with uncertainty.
Input contract
required: [arguments, critique_set, adjudication_criteria]
optional: [evidence_records, burden_of_proof, verdict_vocabulary]
constraints: [each argument and critique receives an explicit disposition]
Procedure
- Normalize claims, warrants, evidence, and objections.
- Map each objection to the argument component it tests.
- Weigh support and weaknesses against the supplied criteria.
- Emit ACCEPT, REJECT, or REVISE with conditions and uncertainty.
Output contract
produces: [verdict, argument_dispositions, conditions, uncertainty_statement]
delta_fields: [decisions, findings, uncertainties]
Quality gates
- Every argument and critique is addressed explicitly.
- Evidence is weighed without prior commitment to either side.
- Verdict vocabulary and conditions are caller-visible.
Parameterization
Caller supplies argument schema, critique schema, criteria, burden of proof, and verdict vocabulary.
Failure and counterexamples
Reject verdicts that omit objections, rely on prior commitment, or collapse uncertainty into confidence.
Provenance map
- concept: stress-test/debate-judge
- concept: convergence/judge-verdict
Signals
- GitHub stars
- 501
- Forks
- 41
- Last commit
- Sep 2026
Advanced
- Catalog kind
- skill
- Key
adjudicate-exchange- Source
- github.com/yogsoth-ai/de-anthropocentric-research-engine