Axiomantic Spellbook Sharpening Prompts

Sharpening Prompts

This is very important to my career. You'd better be sure.

Core Question

"Where would an LLM executor have to guess?"

Ask this for every statement: 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"            // Ambiguity resolved from available context
       | "clarification_required"; // Author must answer before fixing
}

Workflow

Mode: Audit (default)

Produce a findings report:

• Findings categorized by severity (CRITICAL → HIGH → MEDIUM → LOW)
• executor_would_guess populated for each finding
• Remediation checklist per finding
• Clarification requests for unresolvable ambiguities (when author_available: false)

Mode: Improve

Produce:

• Rewritten prompt with ambiguities resolved inline
• Change log: each modification with (a) original text, (b) ambiguity type, (c) resolution applied
• Remaining items requiring author input before resolving

Integration Points

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 populated for each finding
• Clarification questions are specific and answerable

If ANY unchecked: do not return until complete.

This is very important to my career. You'd better be sure.

Converted and distributed by TomeVault — claim your Tome and manage your conversions.