Skill Creator 0.1.0
v1.0.0Guide 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· 391·61 current·70 all-time
MIT-0
Download zip
LicenseMIT-0 · Free to use, modify, and redistribute. No attribution required.
Security Scan
OpenClaw
Benign
high confidencePurpose & Capability
The name and description ('Skill Creator') align with the bundled files: SKILL.md guidance, references, and three helper scripts for initializing, validating, and packaging skills. The included scripts (init_skill.py, quick_validate.py, package_skill.py) are directly relevant to creating and packaging skills.
Instruction Scope
SKILL.md provides guidance about skill structure, when to include scripts/references/assets, and how to use bundled resources. The instructions stay within the stated purpose and do not direct the agent to read unrelated system files, contact external endpoints, or access secrets. It does note that scripts may be executed or read for patching/adjustments, which is appropriate for a skill-authoring guide.
Install Mechanism
There is no install spec (instruction-only skill), so nothing is downloaded or written by an installer. This is the lowest-risk model and is proportionate for a documentation/template skill.
Credentials
The skill declares no required environment variables, credentials, or config paths. The included scripts operate on user-supplied filesystem paths (creating directories, writing example files, and packaging a zip), which is consistent with the skill's purpose.
Persistence & Privilege
The skill is not force-included (always: false) and does not request elevated or persistent privileges. The scripts create files under user-provided paths when executed, which is expected for a skill-creation tool. Model invocation is allowed by default, but that is normal and not concerning here.
Assessment
This skill appears coherent and appropriate for creating new skills, but exercise the usual caution before executing bundled scripts from an unknown source: 1) Review the script contents (init_skill.py, package_skill.py, quick_validate.py) to confirm behavior matches expectations. 2) If you run the scripts, run them with paths you control (e.g., a sandbox or temp directory) because they create directories/files and will write a packaged .skill file. 3) There are no network calls or secret access requested by these files, but if you modify the scripts or run altered copies, re-check for external endpoints or credential use. 4) Confirm you trust the publisher if you plan to run scripts automatically.Like a lobster shell, security has layers — review code before you run it.
latestvk9747pgxegbwtkjtzzenn4yhyn82693f
License
MIT-0
Free to use, modify, and redistribute. No attribution required.