Sharpening Prompts

This is very important to my career. You'd better be sure. </ROLE>

Core Question

"Where would an LLM executor have to guess?"

For every statement in the prompt, ask: If an LLM reads this with no additional context, what would it invent to fill the gaps?

Reasoning Schema

Invariant Principles

1. Ambiguity compounds: One vague instruction becomes many guessed decisions downstream.
2. LLMs fill gaps confidently: They won't ask - they'll invent plausible-sounding specifics.
3. Context is not telepathy: The executor has only what's written, not what you meant.
4. Clarification beats inference: When you can't resolve ambiguity from context, ask the author.
5. Specificity enables verification: Vague success criteria can't be tested.

Inputs / Outputs

Ambiguity Categories

Severity Levels

Finding Schema

interface Finding {
  id: string;                    // F1, F2, etc.
  category: AmbiguityCategory;
  severity: "CRITICAL" | "HIGH" | "MEDIUM" | "LOW";
  location: string;              // Line number, section name, or quote context
  original_text: string;         // Exact quoted problematic text
  problem: string;               // Why this is ambiguous
  executor_would_guess: string;  // What an LLM would likely invent
  clarification_needed: string;  // Specific question to resolve
  suggested_fix?: string;        // If context allows inference
  source: "inference" | "clarification_required";
}

Workflow

Mode: Audit

Execute /sharpen-audit command.

Produces findings report with:

• Categorized findings by severity
• Executor guess predictions
• Remediation checklist
• Clarification requests (if author unavailable)

Mode: Improve

Execute /sharpen-improve command.

Produces:

• Rewritten prompt with clarifications embedded
• Change log explaining each modification
• Remaining ambiguities that need author input

Integration Points

This skill is invoked by:

Quick Reference: Sharpening Patterns

Self-Check

Before completing:

• Every statement evaluated for ambiguity
• All weasel words flagged
• All TBD markers flagged as CRITICAL
• All magic values questioned
• All implicit interfaces verified or flagged
• All conditional statements have both branches
• Success criteria are testable
• Executor-would-guess field populated for each finding
• Clarification questions are specific and answerable

If ANY unchecked: complete before returning.

<FINAL_EMPHASIS> LLMs don't ask for clarification. They guess confidently. Every ambiguity you miss becomes a hallucinated assumption that compounds through implementation. Find where they would guess. Sharpen until there's nothing left to invent.

This is very important to my career. You'd better be sure. </FINAL_EMPHASIS>