enrich prompt

Vague prompts lead to hallucinated outputs and failed executions. This skill transforms thin, ambiguous user instructions into high-precision, context-aware prompts that ensure your LLM delivers the exact technical result you need on the first try. It acts as a middleware for your thoughts, expanding intent into actionable directives without you doing the heavy lifting.

What it does

• Automatic enrichment converts loose ideas into structured, professional-grade prompts with clear constraints.
• Dual-mode processing provides a single-block cohesive rewrite by default or a multi-section structured breakdown for complex architecture.
• Context gap analysis identifies missing technical details like file paths or tech stacks and prompts for clarification before generation.
• Strict language mirroring detects the input language and ensures the entire output—including headings—matches it perfectly.
• Constraint injection embeds quality guardrails and success criteria to prevent common AI anti-patterns and logic errors.

How it works

1. Input detection: The skill analyzes your raw instruction to determine the natural language and the appropriate complexity mode.
2. Contextual audit: It scans for missing parameters across roles, tasks, inputs, and constraints.
3. Prompt synthesis: The agent generates a refined, execution-ready version of your request in either a fluid block or a structured template.
4. Zero-execution gate: The skill delivers only the rewritten prompt text, ensuring no tools are called or commands run prematurely.

Frameworks & tools

Works with any LLM environment including Claude, ChatGPT, and Cursor. Supports all programming languages and technical domains.

Why this beats prompting it yourself

Writing perfect prompts is a manual chore that requires constant mental context-switching. This skill automates prompt engineering best practices, ensuring every request has the necessary role-play, constraints, and success criteria without you typing them every time.

Use cases

• Refining bug reports into actionable fix-it instructions for coding agents.
• Converting architecture notes into detailed implementation plans with strict technical rules.
• Standardizing team prompts to ensure consistent output quality across different developers.

Known limitations

Output is strictly text-based and will not execute the resulting prompt or interact with your workspace files directly. It relies on user-provided data for workspace-specific context.