Prompt Optimizer
- Updated April 1, 2026
- ats-kinoshita-iso/agent-workshop
prompt-optimizer analyzes and rewrites prompts for Claude Code, applying structured prompt-engineering patterns to produce clearer and more effective instructions. It is an agent-tooling skill for developers crafting the prompts that drive LLM agents and automations.
Key points
- Analyzes existing prompts
- Applies structured prompt patterns
- Targets Claude Code
- Produces clearer instructions
Prompt Optimizer by the numbers
- Data as of Jul 7, 2026 (Skillselion catalog sync)
/plugin marketplace add ats-kinoshita-iso/agent-workshop/plugin install prompt-optimizer@agent-workshopAdd your badge
Show developers this skill is listed on Skillselion. Paste this into your README.
| Last updated | April 1, 2026 |
|---|---|
| Repository | ats-kinoshita-iso/agent-workshop ↗ |
What it does
Rewrite and tighten Claude Code prompts using structured prompt-engineering patterns for clearer, more effective agent instructions.
README.md
prompt-optimizer
A Claude Code plugin that analyzes and rewrites prompts using structured prompt engineering patterns, tailored to your project context.
What it does
The /optimize skill takes a raw idea or draft prompt and transforms it into a
well-structured prompt optimized for Claude Code. It:
- Scans your project for relevant files, conventions, and patterns
- Evaluates your prompt against a 7-dimension rubric (goal clarity, scope, success criteria, context references, output format, complexity, Claude Code-specific patterns)
- Rewrites the prompt with specific file references, explicit constraints, and verifiable success criteria
- Explains every change so you learn the patterns over time
- Recommends decomposition via
/research-plan-implementwhen the task is too complex for a single prompt
Usage
/optimize Add caching to the API endpoints
Or describe your idea in conversation:
I want to optimize this prompt: "refactor the auth module to use JWT"
Complexity-adaptive
- Simple tasks: keeps the prompt lean (2-4 sentences, no unnecessary structure)
- Moderate tasks: adds scope boundaries, success criteria, and file references
- Complex tasks: recommends the
planningplugin's research-plan-implement workflow for better results
Skills
| Skill | Description |
|---|---|
optimize |
Analyze and rewrite a prompt for Claude Code |
Related skills
Setup Matt Pocock SkillsScaffold the per-repo configuration that Matt Pocock’s engineering agent skills rely on so they understand the issue tracker, triage labels, and domain documentation la495k196k
Lark AppsConnect Claude, Cursor or custom agents directly to Lark (Feishu) for messaging, document automation, approval workflows and enterprise data access.402k
CavemanSlash token usage by roughly 75% while keeping every technical detail intact when working with Claude Code, Cursor or similar agents.391k94.7k
Lark Skill MakerQuickly turn any Lark/Feishu OpenAPI call or multi-step workflow into a reusable agent skill with its own SKILL.md.386k16k
Running Claude Code Via Litellm CopilotRun Claude Code at a fraction of the cost by routing requests through LiteLLM to the GitHub Copilot Chat API.270k72
Codex PetGenerate a complete Codex Pet spritesheet and metadata from one reference image without needing an OpenAI key or Codex Pro.246k10