From herow-dev
(herow) Analyze raw prompts, identify intent and gaps, match claude-config components (skills/commands/agents/hooks), and output a ready-to-paste optimized prompt. Advisory role only — never executes the task itself. TRIGGER when: user says "optimize prompt", "improve my prompt", "how to write a prompt for", "help me prompt", "rewrite this prompt", or explicitly asks to enhance prompt quality. DO NOT TRIGGER when: user wants the task executed directly, or says "just do it". DO NOT TRIGGER when user says "optimize performance" or "optimize this code" — those are refactoring/performance tasks, not prompt optimization.
How this skill is triggered — by the user, by Claude, or both
Slash command
/herow-dev:prompt-optimizerThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
Analyze a draft prompt, critique it, match it to available components, and output a
Analyze a draft prompt, critique it, match it to available components, and output a complete optimized prompt the user can paste and run.
Detection tables, component-matching tables, the full output-format spec, and worked examples live in
reference.mdin this skill's directory — read it before producing output. It lists herow components; the installed plugin set varies, so verify a component exists in the current session before recommending it.
Advisory only — do not execute the user's task. Do NOT write code, create files, run commands, or take any implementation action. Your ONLY output is an analysis plus an optimized prompt. If the user asks for execution, tell them to make a normal task request instead.
Run this pipeline sequentially, then present results in the Output Format below.
CLAUDE.md if present; detect the tech
stack from project files (signal table in reference.md). No project files →
flag "tech stack unknown".reference.md).reference.md, validated against what
actually exists in the session.reference.md).Respond in the same language as the user's input, with these sections (full spec and
examples in reference.md):
Guides creation, editing, and verification of skills for AI coding agents using test-driven development with subagent scenarios. Use when authoring or debugging skills.
npx claudepluginhub judsonjuniorr/claude-config --plugin herow-dev