evaluate-optionality
SkillDev toolsLets your agent weigh whether to act now, wait, or stage a decision when outcomes are uncertain.
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 evaluate-optionality skill
About this skill
Evaluate the value of staging, deferral, reversible commitment, and information-gathering options under uncertainty; return decision-relevant option value and trigger conditions.
What this skill tells your AI
The instructions your AI receives, as published by yogsoth-ai/de-anthropocentric-research-engine in skills/evaluate-optionality/SKILL.md and read by ahel’s review.
Purpose
Evaluate staging, deferral, reversible commitment, and information-gathering options under uncertainty.
Input contract
required: [decision_options, uncertainty_register, time_horizon, consequence_model]
optional: [irreversibility_costs, information_actions, trigger_conditions]
constraints: [each option states timing, reversibility, information gained, and consequence range]
Procedure
- Represent immediate, deferred, staged, and information-gathering actions on a common timeline.
- Estimate each action's reversible value, delay cost, information gain, and downside exposure.
- Identify trigger conditions that would justify advancing, pausing, or abandoning each staged option.
- Emit an option-value comparison and the conditions under which deferral is preferable to commitment.
Output contract
produces: [option_value_table, timing_policy, trigger_conditions, uncertainty_notes]
delta_fields: [findings, evidence_updates, uncertainties, decisions, recommended_jumps]
Quality gates
- Each option includes at least one consequence of acting now and one consequence of waiting.
- Information value is not counted unless it can change a downstream decision.
Failure and counterexamples
Do not call delay optionality when waiting only postpones an irreversible loss. If trigger conditions are unobservable, mark the option unresolved.
Provenance map
- resolved: temporal-sequencing
Signals
- GitHub stars
- 501
- Forks
- 41
- Last commit
- Sep 2026
Advanced
- Catalog kind
- skill
- Key
evaluate-optionality- Source
- github.com/yogsoth-ai/de-anthropocentric-research-engine