construct-scenario

SkillMonitoring & ops

Lets your agent build structured what-if scenarios with explicit assumptions, from baseline to worst-case.

Use construct-scenario in Claude, ChatGPT or Ahel Desktop

Free. Sign in, add construct-scenario and connect your AI. About a minute.

Also: Claude Code · Cursor · Codex

Then ask your AI: use the construct-scenario skill

Details

Instructions available. Your AI can read the instructions. Execution depends on the setup they require.

Add Ahel to your AI once: Claude, ChatGPT, Cursor, Claude Code or Codex. Then ask it to use this.

construct-scenarioStart free
About this skill

Construct a scenario across key uncertainties with explicit assumptions and plausibility. Modes include baseline/narrative, counterfactual, and extreme-but-plausible worst-case with breaking point, failure cascade, recovery assumptions, and distinguishing observables.

What this skill tells your AI

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

Purpose

Construct scenarios across key uncertainties with explicit assumptions and plausibility, including baseline, counterfactual, and extreme-but-plausible modes.

Input contract

required: [context, uncertainty_set, scenario_mode]
optional: [drivers, dependency_model, probability_method, recovery_assumptions]
constraints: [scenario assumptions and distinguishing observables must be explicit]

Procedure

  1. Select uncertainty axes and record their state space.
  2. Generate distinct combinations appropriate to the mode.
  3. Propagate interactions, breaking points, failure cascades, and recovery assumptions where applicable.
  4. Attach plausibility rationale, distinguishing observables, and outcome implications.

Output contract

produces: [scenario_set, assumptions, plausibility_rationales, observables, outcome_implications]
delta_fields: [findings, hypothesis_updates, uncertainties, open_questions]

Quality gates

  • At least 3 scenarios span different combinations of key uncertainties.
  • Scenarios are internally consistent and materially distinct.
  • Worst-case mode includes breaking point, cascade, recovery, and observables.

Parameterization

Caller supplies context schema, uncertainty axes, mode, distinctness rule, plausibility/probability method, and worst-case fields.

Failure and counterexamples

Reject decorative narratives that do not vary an uncertainty or expose a testable implication.

Provenance map

  • resolved: scenario-construction
  • resolved: counterfactual-scenario-construction
  • resolved: worst-case-construction
  • resolved: stress-scenario

Preserved source criteria ledger

sourcecriterion
scenario-constructionOutput contains at least 3 distinct scenarios spanning different combinations of key uncertainties.
scenario-constructionEach scenario includes a narrative, key assumptions, and probability estimate.
worst-case-constructionExtreme-but-plausible mode includes breaking points, failure cascades, and recovery assessment.

Signals

GitHub stars
503
Forks
42
Last commit
Sep 2026
Advanced
Item type
skill
Key
construct-scenario
Source
github.com/yogsoth-ai/de-anthropocentric-research-engine