Is the Prompt Optimization skill free?

Yes. The skill itself is free from shinpr/rashomon. SkillProof publishes the install command and an independent test verdict at no cost.

What is the Prompt Optimization SkillProof Score?

9.2/10 — installs cleanly 5/5, triggers reliably 5/5, output vs. baseline 8/10, docs & honesty 5/5.

How do I install Prompt Optimization?

Copy the install command from this page, run it in your terminal, and restart Claude Code. Skills live in ~/.claude/skills/ (global) or .claude/skills/ inside a project.

Can I use Prompt Optimization with Cursor, Copilot, Gemini CLI, Codex or other AI tools?

The SKILL.md format is native to Claude (Claude Code, Desktop, claude.ai). The instructions inside adapt to other assistants: Cursor rules, GitHub Copilot instructions, Windsurf rules, Custom GPTs, AGENTS.md for OpenAI Codex, and GEMINI.md for Google Gemini CLI — our conversion guides cover each, and the free converter on the tools page does the wrapping for you.

Prompt Optimization

Gated 3-step BP-001~008 prompt analysis that blocks and asks for missing scope instead of guessing.

by shinpr · shinpr/rashomon

Tested · Works

Install — copy the command Download source ↗

Test report

Verdict: Tested · Works
Score: 9.2/10
Tested: Jul 16, 2026
Environment: Claude Code 2.x (agent harness)
Upstream re-checked: Jul 18, 2026 · 35875f0

Fed it a deliberately vague prompt ('Don't write bad code. Make it good. Fix the bugs in my app.'); a freehand baseline rewrite silently invented which app/bugs were meant, but the skill's gated flow correctly flagged the missing repo/bug-description as an unresolved input and returned a 'Required Input' block instead of guessing.

Scored on four weighted criteria — install, triggering, output vs. baseline, docs. How scoring works

Installs cleanly 5/5
Triggers reliably 5/5
Output vs. baseline 8/10
Docs & honesty 5/5

What Prompt Optimization does

Runs a procedurally-gated analysis/optimization/balance flow against 8 named bad-prompt patterns (negative instructions, vagueness, missing format, etc.), tracing every change to a specific finding and refusing to fabricate missing project context. Triggers on 'optimize this prompt', 'review prompt quality', or when creating/reviewing a rashomon-style skill.

How to install Prompt Optimization

git clone https://github.com/shinpr/rashomon
mkdir -p ~/.claude/skills
cp -r rashomon/skills/prompt-optimization ~/.claude/skills/prompt-optimization

Skills live in ~/.claude/skills/ (global) or .claude/skills/ (per-project). Restart Claude Code after installing.

Commands — how to trigger Prompt Optimization

/prompt-optimization Gated 3-step BP-001~008 prompt analysis that blocks and asks for missing scope instead of guessing.

It also activates on plain-language prompts like these:

Can you optimize this prompt, it feels vague and keeps confusing the model?
Review the quality of this system prompt and point out what's wrong
I'm writing a new skill, check my SKILL.md prompt for clarity issues

Frequently asked questions

Is the Prompt Optimization skill free?: Yes. The skill itself is free from shinpr/rashomon. SkillProof publishes the install command and an independent test verdict at no cost.
Does Prompt Optimization work with Claude Code?: We tested it with Claude Code 2.x (agent harness) on Jul 16, 2026. Verdict: Tested · Works. Fed it a deliberately vague prompt ('Don't write bad code. Make it good. Fix the bugs in my app.'); a freehand baseline rewrite silently invented which app/bugs were meant, but the skill's gated flow correctly flagged the missing repo/bug-description as an unresolved input and returned a 'Required Input' block instead of guessing.
What is the Prompt Optimization SkillProof Score?: 9.2/10 — installs cleanly 5/5, triggers reliably 5/5, output vs. baseline 8/10, docs & honesty 5/5.
How do I install Prompt Optimization?: Copy the install command from this page, run it in your terminal, and restart Claude Code. Skills live in ~/.claude/skills/ (global) or .claude/skills/ inside a project.
Can I use Prompt Optimization with Cursor, Copilot, Gemini CLI, Codex or other AI tools?: The SKILL.md format is native to Claude (Claude Code, Desktop, claude.ai). The instructions inside adapt to other assistants: Cursor rules, GitHub Copilot instructions, Windsurf rules, Custom GPTs, AGENTS.md for OpenAI Codex, and GEMINI.md for Google Gemini CLI — our conversion guides cover each, and the free converter on the tools page does the wrapping for you.