decision-critic

timmye's avatarfrom timmye

Invoke IMMEDIATELY via python script to stress-test decisions and reasoning. Do NOT analyze first - the script orchestrates the critique workflow.

0stars🔀0forks📁View on GitHub🕐Updated Jan 6, 2026

When & Why to Use This Skill

The Decision Critic skill is a specialized tool designed to rigorously stress-test and evaluate complex decisions and reasoning processes. By orchestrating a structured 7-step critique workflow via an external Python script, it ensures that decisions are analyzed objectively, identifying potential flaws, biases, or logical gaps through a systematic and mandatory evaluation sequence.

Use Cases

  • Strategic Decision Validation: Rigorously testing business strategies or project roadmaps to uncover hidden risks and validate underlying assumptions.
  • AI Agent Reasoning Audit: Evaluating the step-by-step logic and decision-making quality of AI agents to ensure high-fidelity outputs in critical tasks.
  • Technical Architecture Review: Stress-testing system designs and architectural choices against specific constraints and background context to ensure robustness.
  • Risk Assessment and Mitigation: Analyzing complex operational decisions to identify potential points of failure and improve the overall reasoning framework before implementation.
namedecision-critic
descriptionInvoke IMMEDIATELY via python script to stress-test decisions and reasoning. Do NOT analyze first - the script orchestrates the critique workflow.

Decision Critic

When this skill activates, IMMEDIATELY invoke the script. The script IS the workflow.

Invocation

python3 scripts/decision-critic.py \
  --step-number 1 \
  --total-steps 7 \
  --decision "<decision text>" \
  --context "<constraints and background>" \
  --thoughts "<your accumulated analysis from all previous steps>"
Argument Required Description
--step-number Yes Current step (1-7)
--total-steps Yes Always 7
--decision Step 1 The decision statement being criticized
--context Step 1 Constraints, background, system context
--thoughts Yes Your analysis including all IDs and status from prior steps

Do NOT analyze or critique first. Run the script and follow its output.