prompt-optimizer

Rewrite incomplete prompts into structured Claude Code ECC workflows.

Updated Mar 26, 2026
One-click install
npx skills add https://github.com/luongldptit/move-ticket --skill prompt-optimizer-luongldptit
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: prompt-optimizer
Source: https://github.com/luongldptit/move-ticket/tree/main/.agent/skills/prompt-optimizer
Command: npx skills add https://github.com/luongldptit/move-ticket --skill prompt-optimizer-luongldptit

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This Skill eliminates the frustration of writing vague, incomplete prompts for Claude Code ECC workflows that fail to leverage available ecosystem components, leading to poor task execution, incorrect component usage, or excessive back-and-forth clarification.

Core Features & Use Cases

  • Intent & Gap Analysis: Automatically identifies the user's task intent, missing context, and alignment with ECC components (commands, skills, agents) based on the draft prompt.
  • Tech Stack Alignment: Detects the current project's tech stack to recommend relevant, stack-specific ECC components and coding patterns.
  • Structured Optimized Output: Generates a ready-to-paste prompt with clear workflow steps, acceptance criteria, scope boundaries, and model recommendations tailored to the task's scope and complexity.
  • Use Case: If you write a vague prompt like "add a user login feature", this Skill will output a structured prompt with aligned /plan, /tdd, /code-review steps, security requirements, and clear "do not do" boundaries to ensure the task is executed correctly the first time.

Quick Start

Share your rough draft prompt for a Claude Code task and ask the prompt-optimizer skill to rewrite it into a complete, ECC-aligned optimized prompt ready for immediate use.

Frequently Asked Questions about prompt-optimizer

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I refine vague prompts for Claude Code ECC workflows?

Prompt optimization for ECC workflows identifies missing context in draft prompts and aligns them with specific commands, skills, and agents. It generates a ready-to-paste prompt with clear workflow steps, acceptance criteria, and scope boundaries to ensure correct task execution.

What is the best way to structure a prompt for complex feature development in Claude Code?

The best way to structure a complex feature development prompt is to apply intent and gap analysis to your draft. This detects your project's tech stack and outputs an optimized prompt with aligned ECC workflow steps, security requirements, and explicit scope boundaries to prevent incorrect component usage.

Why do my incomplete Claude Code prompts fail to leverage available ecosystem components?

Incomplete Claude Code prompts fail because they lack structured alignment with the ECC ecosystem. Without applying intent and gap analysis, the prompt misses necessary workflow steps, model recommendations, and specific component usage instructions required for successful task execution.

Can I optimize a bug fix prompt to include test-driven development steps for Claude Code?

Yes, you can optimize a bug fix prompt by rewriting it into a complete, ECC-aligned prompt. The optimization process adds structured workflow steps like /tdd and /code-review, along with clear acceptance criteria and scope boundaries tailored to your bug fix scenario.

Does prompt optimization for Claude Code work with EPIC architectural projects?

Yes, prompt optimization applies to EPIC architectural projects by delivering structured prompts with aligned ECC commands, agents, and workflow steps. It scales to handle complex research and refactoring tasks by providing model recommendations and explicit scope boundaries.

When should I not use automated prompt optimization for my AI prompting tasks?

You should not rely on automated prompt optimization if your draft prompt already contains fully structured ECC commands, explicit acceptance criteria, and defined scope boundaries. It is designed to resolve ineffective, vague prompts that fail to leverage ecosystem components, not to reprocess already optimized instructions.