apply-veto-filter

SkillDev tools

Lets your agent filter out options that break hard limits and show exactly which rule each one violated.

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

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 apply-veto-filter skill

About this skill

Eliminate alternatives that violate any hard threshold and report the exact violation.

What this skill tells your AI

The instructions your AI receives, as published by yogsoth-ai/de-anthropocentric-research-engine in skills/apply-veto-filter/SKILL.md and read by ahel’s review.

Purpose

Eliminate alternatives that violate any declared hard threshold and expose the exact veto condition for each removal.

Input contract

required: [alternatives, hard_constraints, measured_values]
optional: [constraint_priorities, missing_value_policy]
constraints: [each alternative is tested against every hard constraint; missing measurements cannot silently pass]

Procedure

  1. Bind each hard constraint to its direction, threshold, unit, and evidence source.
  2. Check every alternative against every constraint and record pass, fail, or unknown per cell.
  3. Veto an alternative when any hard constraint fails; keep unknowns separate from passes.
  4. Return survivors, vetoed alternatives, violated constraints, and unresolved checks.

Output contract

produces: [survivor_set, veto_log, unresolved_checks]
delta_fields: [findings, evidence_updates, uncertainties, decisions]

Quality gates

  • Every veto names one alternative, one hard constraint, the observed value, threshold, direction, and source.
  • A survivor has no failed or silently unresolved hard constraint.

Failure and counterexamples

Do not replace a hard veto with a weighted average. If a value is missing, report unknown rather than treating it as compliant.

Provenance map

  • resolved: conjunctive-filter

Signals

GitHub stars
501
Forks
41
Last commit
Sep 2026
Advanced
Catalog kind
skill
Key
apply-veto-filter
Source
github.com/yogsoth-ai/de-anthropocentric-research-engine