define-objective

SkillDev tools

Lets your agent turn a decision into measurable objectives, constraints, and tradeoffs before optimizing.

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 define-objective skill

About this skill

Formalize objectives, constraints, and tradeoff preferences for optimization.

What this skill tells your AI

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

Purpose

Formalize objectives, constraints, and tradeoff preferences before an optimization or selection decision.

Input contract

required: [decision_context, candidate_set, stakeholder_preferences]
optional: [hard_constraints, utility_scale, priority_weights]
constraints: [objectives are measurable or operationalized; tradeoffs and constraint direction are explicit]

Procedure

  1. Elicit the desired outcome, affected scope, stakeholders, and time horizon.
  2. Separate objectives from constraints and preferences, then define each objective's direction and measurement.
  3. Record conflicts, permissible tradeoffs, and any weights or lexicographic priorities with their rationale.
  4. Emit an objective schema suitable for comparison, optimization, and later audit.

Output contract

produces: [objective_schema, constraint_schema, tradeoff_policy, unresolved_preferences]
delta_fields: [findings, assumption_updates, uncertainties, decisions, open_questions]

Quality gates

  • A-class gate: declared universe = all stakeholder objectives and hard constraints in scope; numerator = items operationalized with direction, measurement, and source; batch increment = one objective or constraint formalized; stopping reason = all items formalized or unresolved conflicts are explicit; source references = stakeholder, requirement, and decision IDs; direction/threshold reason = an objective enters optimization only when its direction and acceptable tradeoff boundary are explicit.
  • At least two distinct objectives and one constraint are required unless the decision record justifies a narrower scope.

Failure and counterexamples

Do not encode a preferred solution as an objective. If two stakeholders use the same word for different outcomes, preserve separate definitions.

Provenance map

  • resolved: objective-definition

Signals

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