ai context instruction pack compiler

The problem

Prompts and instruction documents often become bloated, repetitive, and contradictory as projects grow. This makes it difficult for AI agents to follow logic and leads to inconsistent outputs or wasted tokens.

What it does

• Extracts core goals, rules, and constraints from disorganized notes and requirements documents.
• Deduplicates redundant instructions and merges overlapping directives into a single source of truth.
• Parameterizes hardcoded values into reusable variables like [FORMAT] or [ROLE].
• Organizes messy input into a structured semantic hierarchy optimized for model consumption.
• Identifies and flags logical contradictions in rules for manual resolution.

Why this beats prompting it yourself

Manually refactoring a 2,000-word instruction set is tedious and prone to missing subtle edge cases. This skill uses a systematic four-phase analysis to ensure 100% requirement coverage while drastically reducing word count and improving logical flow.

Use cases

• Convert scattered meeting notes into a structured System Prompt for a new AI agent.
• Clean up an old, "leaky" prompt that has become too long and confusing for the model.
• Standardize instructions across a library of different automation templates.
• Turn informal client requirements into a technical specification for an LLM-based tool.

Known limitations

This tool focuses on structural clarity and organization. It assumes the source material is factually correct and does not validate the truth of the provided instructions.