ClawHub

Skill Creator 0.1.0

v1.0.1

Guide for creating effective skills. This skill should be used when users want to create a new skill (or update an existing skill) that extends Claude's capa...

⭐ 0· 91·0 current·0 all-time
byRaidan Pro@raidan-ai·duplicate of @yixinli867/skill-creator-2
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 (a guide for creating skills) matches the content of SKILL.md. The skill requests no binaries, env vars, or config paths — consistent with an instruction-only authoring guide.
✓
Instruction Scope
SKILL.md contains authoring guidance, file layout, and best practices. It does not instruct the agent to read unrelated local files, exfiltrate data, call external endpoints, or access credentials. The instructions are scoped to authoring skills and related resources.
✓
Install Mechanism
No install spec and no code files are present. This is the lowest-risk form (instruction-only); nothing will be written to disk or executed automatically by an installer.
✓
Credentials
The skill declares no environment variables, credentials, or config paths. There is no disproportionate or unexplained credential request.
✓
Persistence & Privilege
The skill does not request permanent presence (always:false) and is user-invocable. It does not modify other skills or system settings in the provided instructions.
Assessment
This is an instruction-only authoring guide and is internally consistent. Before installing or using any skill: (1) confirm there are no bundled scripts or assets you didn't expect — if the skill later includes a scripts/ or assets/ directory, review those files before allowing execution; (2) note the SKILL.md references a LICENSE.txt and there is no homepage/source listed — if you need licensing or provenance guarantees, request the publisher info; (3) because instruction-only skills can still influence agent behavior, review the instructions for any future changes that would instruct the agent to read local files or use credentials. Overall this particular skill appears benign.

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

latestvk97bbjqn79znft6qwsw5aazxhh83j6we

License

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

Comments