ClawHub

Ro Prompt Optimizer

v1.0.0

基于R-O框架（角色&现实情况、对象&输出）优化用户提示词，将普通需求转化为专业、结构化的AI提示词，以激发AI最大潜力。当用户需要优化提示词、改善与AI的交互效果、创建更有效的指令时使用此技能。

⭐ 0· 87·1 current·1 all-time
by@dukeacco
MIT-0
Download zip
LicenseMIT-0 · Free to use, modify, and redistribute. No attribution required.
Security Scan
VirusTotalVirusTotal
Benign
View report →
OpenClawOpenClaw
Benign
medium confidence
✓
Purpose & Capability
Name, description, SKILL.md, and the reference templates all describe an R-O prompt optimization tool. The presence of a scripts/auto-optimizer.py helper is expected and consistent with the stated purpose; nothing in the manifest asks for unrelated credentials, binaries, or system paths.
✓
Instruction Scope
SKILL.md only instructs generating structured prompt text from user requirements and provides templates and examples. It does not instruct reading system files, scanning environment variables, or sending data to external endpoints. The script is described as optional and the documentation does not direct the agent to exfiltrate data or access unrelated system state.
✓
Install Mechanism
There is no install spec (instruction-only skill with an optional script file). No packages, downloads, or external installers are declared. This is low-risk from an installation perspective.
✓
Credentials
The skill requests no environment variables, credentials, or config paths. The SKILL.md and other files do not reference secrets or external APIs, so the level of access requested is proportional to the stated functionality.
✓
Persistence & Privilege
always:false and default invocation settings are used. The skill does not request permanent presence or modifications to other skills or system-wide agent settings.
Assessment
This skill appears to do what it says: produce structured, industry-aware prompt templates. There are no credential or network requests in the manifest or docs. However, the included Python script is not fully polished: it references a nonexistent TaskType.GENERAL default and the generate_optimized_prompt function appears truncated in the provided file—these are coding bugs that could cause runtime errors. If you plan to run the script, review it first (or run it in a sandbox) and avoid feeding sensitive data into it until you confirm it behaves as expected. If you only use the SKILL.md templates (no code execution), the risk is low. If you want higher confidence, request a full, fixed version of scripts/auto-optimizer.py or ask the author for source verification and tests.

Like a lobster shell, security has layers — review code before you run it.

latestvk97cj5aqyn6c8ahg38b62t67f183jfb5

License

MIT-0
Free to use, modify, and redistribute. No attribution required.
Termshttps://spdx.org/licenses/MIT-0.html

Comments