prompt-optimizer

Name: prompt-optimizer
Availability: InStock
Author: franklee16

Structure raw user requests into outcome-focused Cowork prompts with success criteria.

203|27|Updated Apr 19, 2026

Search Tags:#prompt optimization #task planning #autonomous agent #cowork #structured instructions #safety checkpoints

Ready to run

npx skills add https://github.com/franklee16/academic-research-skills --skill prompt-optimizer-franklee16

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: prompt-optimizer
Source: https://github.com/franklee16/academic-research-skills/tree/main/brainstorming/prompt-optimizer
Command: npx skills add https://github.com/franklee16/academic-research-skills --skill prompt-optimizer-franklee16

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

It turns vague or poorly structured requests into a clear, outcome-focused Cowork prompt that an agent can execute safely and effectively.

Core Features & Use Cases

Goal-first prompt rewriting: Reformulates the user’s request into an end-state with concrete success criteria.
Context loading guidance: Instructs Cowork exactly which CLAUDE.md, MEMORY.md, and relevant Resources files to read.
Safety via constraints and checkpoints: Adds constraints and a risk-calibrated CHECKPOINT RULE so high-risk actions pause for approval.

Quick Start

Give Claude Code a messy instruction like “optimize this cowork prompt for me,” and ask it to output a structured Cowork prompt following GOAL, CONTEXT LOADING, IDENTITY, SUCCESS CRITERIA, INPUTS, CONSTRAINTS, and CHECKPOINT RULE.

Frequently Asked Questions about prompt-optimizer

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

FAQPage Schema

How do I structure a prompt for autonomous agent tasks?▼

To structure a prompt for autonomous agent tasks, you need to transform raw requests into an outcome-focused format using GOAL, CONTEXT LOADING, IDENTITY, SUCCESS CRITERIA, INPUTS, CONSTRAINTS, and CHECKPOINT RULE sections to ensure safe, effective execution.

When do I need a structured Cowork prompt for multi-step tasks?▼

You need a structured Cowork prompt when executing multi-step autonomous tasks in file- and tool-based workspaces. It reformulates vague requests into an end-state with concrete success criteria, preventing unsafe or ineffective autonomous actions.

How do I add safety checkpoints to an autonomous agent prompt?▼

You add safety checkpoints to an autonomous agent prompt by applying a risk-calibrated CHECKPOINT RULE. This mechanism pauses high-risk actions for explicit approval, ensuring the autonomous workflow respects defined constraints.

Can I use context loading to specify files for an autonomous task?▼

Yes, you can use the CONTEXT LOADING section to instruct the agent exactly which CLAUDE.md, MEMORY.md, and relevant Resources files to read. This provides the necessary workspace context for the structured task.

What is the best way to rewrite a vague instruction into an executable plan?▼

The best way to rewrite a vague instruction into an executable plan is goal-first prompt rewriting. This converts a messy instruction into an end-state with verifiable criteria, explicit constraints, and a defined identity for the agent.

Does prompt optimization work for file-based workspaces?▼

Yes, prompt optimization works for file-based workspaces by formatting instructions specifically for Claude Cowork execution. It applies structured inputs and context loading to ensure the agent interacts correctly with local files and tools.