ClawHub

Clear Prompt Engineering

v1.0.0

Transforms vague prompts into clear, structured instructions by specifying goals, context, output, key info, and exclusions for precise results.

⭐ 0· 78·0 current·0 all-time
by@371166758-qq
MIT-0
Download zip
LicenseMIT-0 · Free to use, modify, and redistribute. No attribution required.
Security Scan
VirusTotalVirusTotal
Benign
View report →
OpenClawOpenClaw
Benign
high confidence
✓
Purpose & Capability
The name/description (transform vague prompts into structured instructions) matches the SKILL.md content. The skill requires no binaries, env vars, or config paths — appropriate for a text-only prompt-engineering helper.
✓
Instruction Scope
Runtime instructions are limited to analyzing user prompts and producing refined prompt templates and before/after examples. The SKILL.md does not instruct the agent to read files, access environment variables, transmit data to external endpoints, or perform actions outside text transformation.
✓
Install Mechanism
No install specification or code files are present (instruction-only). Nothing will be written to disk or downloaded by the skill itself.
✓
Credentials
The skill requests no credentials, secrets, or config paths. Declared requirements are minimal and proportionate to a prompt-refinement capability.
✓
Persistence & Privilege
The skill does not request always:true and makes no changes to other skills or system-wide settings. It states it 'activates automatically when detecting vague input' — this is a behavioral preference but does not by itself grant elevated system privileges.
Assessment
This skill is internally consistent and low-risk: it only contains instructions for rewriting prompts and does not request secrets or install software. Two practical cautions: (1) the SKILL.md says it will 'activate automatically' on vague input — if you prefer manual control, check your agent/platform settings for per-skill invocation controls before enabling it; (2) some templates ask for ready-to-run CLI commands or troubleshooting steps — always review any generated commands or instructions carefully before executing them. If you want greater assurance, ask the publisher for a homepage/source or request example inputs/outputs to validate behavior.

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

communicationvk9752xq2069yc00nby4kaz00rh83p23gengineeringvk9752xq2069yc00nby4kaz00rh83p23glatestvk9752xq2069yc00nby4kaz00rh83p23gproductivityvk9752xq2069yc00nby4kaz00rh83p23gpromptvk9752xq2069yc00nby4kaz00rh83p23gwritingvk9752xq2069yc00nby4kaz00rh83p23g

License

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

Comments