ClawHub

Skill Creator

v6.1.1

Create, edit, improve, or audit AgentSkills. Use when creating a new skill from scratch, restructuring an existing skill, auditing skill quality, or making a...

⭐ 0· 109·0 current·0 all-time
by@ciklopentan
MIT-0
Download zip
LicenseMIT-0 · Free to use, modify, and redistribute. No attribution required.
Security Scan
Capability signals
CryptoCan make purchases
These labels describe what authority the skill may exercise. They are separate from suspicious or malicious moderation verdicts.
VirusTotalVirusTotal
Benign
View report →
OpenClawOpenClaw
Benign
high confidence
✓
Purpose & Capability
Name/description (skill authoring) match the included files and scripts (init, package, validate, references). All required resources (scripts, references, tests) are appropriate for a 'skill creator' tool.
✓
Instruction Scope
SKILL.md stays within the authoring domain: it instructs how to design skill structure, run included helper scripts, normalize folders, and perform validation/package steps. It does direct the agent to execute scripts that create or modify files inside skill directories (expected for this purpose).
✓
Install Mechanism
No install spec is provided (instruction-only). All code is bundled in the package; there are no external downloads or install URLs that would write arbitrary code to disk.
✓
Credentials
No environment variables, credentials, or external service tokens are requested. The scripts operate on local filesystem paths and do not attempt to access unrelated secrets.
✓
Persistence & Privilege
always is false and the skill does not request elevated or persistent platform privileges. It can be invoked autonomously (platform default), which is appropriate for an authoring tool that runs its own scripts.
Assessment
This package is internally consistent for creating and validating skills. Before running it (especially allowing autonomous invocation), inspect the included scripts (scripts/init_skill.py, scripts/package_skill.py, quick_validate.py, validate_weak_models.py) because they will create, modify, and package files under the directories you point them at. Allowing the skill to run can change files in your filesystem (init_skill writes templates; package_skill zips directories). If you will let the agent run this autonomously, restrict the target paths or run validations manually first.

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

latestvk971t8wcyanqxawe065yezwpz184j8ee

License

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

Comments