assess-problem-wickedness
SkillDev toolsLets your agent judge whether a problem is tame, complex, or wicked by checking stakeholder disagreement and evidence.
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 assess-problem-wickedness skill
About this skill
Assess whether the problem is tame, complex, or wicked by examining stakeholder disagreement, moving boundaries, feedback, value conflict, and absence of a stable stopping rule.
What this skill tells your AI
The instructions your AI receives, as published by yogsoth-ai/de-anthropocentric-research-engine in skills/assess-problem-wickedness/SKILL.md and read by ahel’s review.
Purpose
Assess whether a problem is tame, complex, or wicked using disagreement, moving boundaries, feedback, value conflict, and stopping-rule evidence.
Input contract
required: [problem_statement, stakeholder_views]
optional: [boundary_history, feedback_observations, candidate_stopping_rule]
constraints: [classification must cite observed disagreement or stability indicators]
Procedure
- Compare stakeholder definitions and desired outcomes.
- Check boundary movement, feedback loops, and value conflicts.
- Assess whether a stable stopping rule and agreed solution test exist.
- Assign tame, complex, or wicked with evidence and uncertainty.
Output contract
produces: [wickedness_assessment, evidence_basis, workflow_implications]
delta_fields: [findings, uncertainties, decisions, open_questions]
Quality gates
- Classification covers all five dimensions; disagreement is distinguished from missing information.
Failure and counterexamples
Do not label a problem wicked solely because it is difficult or interdisciplinary.
Provenance map
deep-insight/wickedness-assessment: resolved.
Signals
- GitHub stars
- 501
- Forks
- 41
- Last commit
- Sep 2026
Advanced
- Catalog kind
- skill
- Key
assess-problem-wickedness- Source
- github.com/yogsoth-ai/de-anthropocentric-research-engine