← Back to Skills Marketplace
Prompt Optimizer
by
371166758-qq
· GitHub ↗
· v1.0.0
· MIT-0
196
Downloads
0
Stars
1
Active Installs
1
Versions
Install in OpenClaw
/install qf-prompt-optimizer
Description
Refine vague or poorly structured prompts into clear, structured, and effective prompts using proven prompt engineering techniques for improved AI output qua...
Usage Guidance
This is an instruction-only prompt-optimizing guide and appears internally consistent. Recommended precautions before installing or using it: (1) Do not paste secrets or sensitive data into prompts you ask the skill to optimize (the skill's scope is to rewrite whatever you give it). (2) Test optimized prompts on non-sensitive inputs to verify they produce the intended behavior and to detect undesired instructions or data exposure. (3) Be aware that the skill can be invoked by the agent (platform default); if you don't want autonomous use, restrict invocation in agent settings. (4) Remember optimized prompts can still cause downstream models to hallucinate or reveal data—validate outputs before sharing or taking action.
Capability Analysis
Type: OpenClaw Skill
Name: qf-prompt-optimizer
Version: 1.0.0
The skill bundle is a purely instructional tool designed to help an AI agent optimize user prompts using a structured framework (OPTIMIZE). It contains no executable code, external network calls, or instructions to access sensitive data, and its content is entirely consistent with its stated purpose in SKILL.md.
Capability Assessment
Purpose & Capability
The name/description (prompt refinement) aligns with the SKILL.md content: techniques, templates, and examples for improving prompts. It does not request unrelated credentials, binaries, or system access.
Instruction Scope
Runtime instructions are limited to analyzing and rewriting user prompts using the OPTIMIZE framework; they do not instruct the agent to read files, environment variables, network endpoints, or other system state outside of the provided user prompt.
Install Mechanism
No install spec and no code files — instruction-only. Nothing will be downloaded or written to disk by an installer.
Credentials
The skill declares no required environment variables, credentials, or config paths; the instructions likewise do not reference any secrets or external service tokens.
Persistence & Privilege
always:false (no forced inclusion). disable-model-invocation:false is the platform default and not itself a concern. The skill does not request persistent system changes or access to other skills' configuration.
How to Use
- Make sure OpenClaw is installed (local or Docker)
- Run the install command in chat:
/install qf-prompt-optimizer - After installation, invoke the skill by name or use
/qf-prompt-optimizer - Provide required inputs per the skill's parameter spec and get structured output
Version History
v1.0.0
OPTIMIZE framework for refining vague prompts into professional-grade prompts. Covers objective, persona, task structure, input specs, constraints, ideal output.
Metadata
Frequently Asked Questions
What is Prompt Optimizer?
Refine vague or poorly structured prompts into clear, structured, and effective prompts using proven prompt engineering techniques for improved AI output qua... It is an AI Agent Skill for Claude Code / OpenClaw, with 196 downloads so far.
How do I install Prompt Optimizer?
Run "/install qf-prompt-optimizer" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.
Is Prompt Optimizer free?
Yes, Prompt Optimizer is completely free, licensed under MIT-0. You can download, install and use it at no cost.
Which platforms does Prompt Optimizer support?
Prompt Optimizer is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).
Who created Prompt Optimizer?
It is built and maintained by 371166758-qq (@371166758-qq); the current version is v1.0.0.
More Skills