enumeration-protocol-execution

Enforce a Divergent-Convergent Scan loop to overcome 'Prevalent Noun Bias' and statistical probability reflexes (System 1).

⭐5stars🔀1forks📁View on GitHub🕐Updated Jan 11, 2026

When & Why to Use This Skill

The Enumeration Protocol Execution skill is a sophisticated cognitive framework designed to enhance AI reasoning by mitigating 'Prevalent Noun Bias' and impulsive 'System 1' responses. By enforcing a structured Divergent-Convergent Scan loop, it compels the agent to explore low-probability alternatives and perform rigorous inversion tests, ensuring high-precision outcomes in complex problem-solving and analytical tasks where the 'obvious' answer might be incorrect.

Use Cases

  • Complex Debugging: Identifying non-obvious root causes in code by bypassing standard library assumptions and exploring low-probability edge cases.
  • Visual Pattern Recognition: Analyzing complex visual data to identify background objects or structural elements that standard models often overlook due to saliency bias.
  • System Log Analysis: Investigating ambiguous error logs where the most frequent or 'obvious' error message might mask a more subtle, underlying system failure.
  • Strategic Option Analysis: Evaluating business or technical proposals by intentionally challenging the 'statistically default' choice through an inversion test to uncover hidden risks or superior alternatives.
nameenumeration-protocol-execution
descriptionEnforce a Divergent-Convergent Scan loop to overcome 'Prevalent Noun Bias' and statistical probability reflexes (System 1).
version1.0.0

Description

This protocol serves as a "Cognitive Brake." It is invoked when high precision is required or when the initial answer seems "too obvious" (high probability/low compute). It forces the agent to suspend the final answer, scan the entire search space for low-probability candidates, and perform an inversion test before converging on a selection.

Instructions

Step 1: Divergent Scan (The Silent Survey)

Before formulating the final response, generate an internal list of 3-5 distinct candidates that fit the user's criteria.

  • Constraint: You are FORBIDDEN from selecting the first candidate that comes to mind.
  • Search Target: Look for "Background Objects," "Structural Elements," or "Counter-Intuitive Solutions."

Step 2: Bias Identification

Review the generated list and identify the "Statistical Default."

  • Question: "Which of these candidates would an average human or standard model pick 90% of the time?"
  • Action: Flag this candidate as [BIAS_DEFAULT].

Step 3: The Inversion Test

Challenge the [BIAS_DEFAULT].

  • Question: "Why might this obvious answer be a decoy or incorrect?"
  • Action: Check for exclusion criteria (e.g., user said 'Nope', context implies a trick, visual obstruction).

Step 4: Convergence & Selection

Select the final answer based on Contextual Fit rather than Saliency.

  • If the [BIAS_DEFAULT] survives the Inversion Test, output it.
  • If it fails, promote the highest-ranked alternative (e.g., the 'Dolly' instead of the 'Hat').

Examples

  • "Engage enumeration protocol for this visual puzzle."
  • "Execute enumeration scan to debug this code block (avoiding standard library assumptions)."
  • "Run enumeration-protocol-execution on the error logs."