prompt-optimizer

Analyzes draft prompts and generates optimized prompts matched to ECC components.

1|Updated Oct 11, 2025
One-click install
npx skills add https://github.com/ibytechaos/claude --skill prompt-optimizer-ibytechaos
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: prompt-optimizer
Source: https://github.com/ibytechaos/claude/tree/main/plugins/everything-claude-code/skills/prompt-optimizer
Command: npx skills add https://github.com/ibytechaos/claude --skill prompt-optimizer-ibytechaos

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve? Writing effective prompts for Claude Code is hard: vague prompts miss tech stack context, acceptance criteria, and the right commands or agents. This Skill diagnoses a raw prompt, detects project context, and produces a ready-to-paste optimized prompt without executing the task itself. ## Core Features & Use Cases - Six-phase analysis pipeline: Detects project tech stack from files like package.json, go.mod, or Cargo.toml, classifies intent (feature, bug fix, refactor, research), and assesses scope from TRIVIAL to EPIC. - ECC component matching: Maps intent and tech stack to specific commands (/plan, /tdd, /verify), skills (tdd-workflow, security-review), agents (code-reviewer), and model recommendations (Sonnet 4.6 vs Opus 4.6). - Gap detection and clarification: Identifies missing context such as acceptance criteria, security requirements, and testing expectations, asking up to 3 clarifying questions when needed. - Use Case: A user pastes "帮我写一个用户登录页面". The Skill detects a Next.js 15 + TypeScript project, then outputs a full optimized prompt with workflow steps, security requirements, acceptance criteria, and scope boundaries, plus a compact quick version. ## Quick Start Ask the assistant to optimize your draft prompt, for example by saying "optimize this prompt: add a REST API endpoint for user profile updates".

Frequently Asked Questions about prompt-optimizer

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

FAQPage Schema
How do I optimize a prompt for Claude Code?

Paste your draft prompt and ask to optimize it. The Skill runs a six-phase pipeline covering project detection, intent classification, scope assessment, component matching, gap analysis, and model recommendation, then outputs a ready-to-paste optimized prompt.

What ECC components does prompt optimization recommend?

It maps your intent and tech stack to specific commands like /plan, /tdd, and /verify, skills like tdd-workflow and security-review, and agents like code-reviewer. Recommendations vary by task type, from bug fixes to EPIC multi-session projects.

Does the prompt optimizer execute the task itself?

No, it is advisory only and never writes code, creates files, or runs commands. Its only output is an analysis plus an optimized prompt; if you want execution, make a normal task request instead.

How does it detect my project's tech stack?

It scans for project files such as package.json, go.mod, pyproject.toml, Cargo.toml, build.gradle, and others to infer the stack. If no project files exist, it flags the tech stack as unknown and asks you to specify it.

When should I not use prompt optimization?

Skip it when you want the task executed directly, when optimizing code or performance rather than prompts, or when configuring ECC. Those cases call for direct execution, refactoring workflows, or the configure-ecc skill instead.

How are large or multi-session tasks handled?

HIGH and EPIC scope tasks are split into sequential prompts: research and planning first, then one implementation phase per prompt with /verify gates. The blueprint skill is recommended for EPIC planning, with /save-session and /resume-session between phases.