OpenClaw Skills Creator
v1.0.0Create, edit, improve, or audit AgentSkills. Use when creating a new skill from scratch or when asked to improve, review, audit, tidy up, or clean up an exis...
⭐ 0· 81·0 current·0 all-time
bySuper 9°@super9du·duplicate of @super9du/openclaw-skills-creator (1.0.0)·canonical: @super9du/wolf-skill-creator
MIT-0
Download zip
LicenseMIT-0 · Free to use, modify, and redistribute. No attribution required.
Security Scan
Capability signals
These labels describe what authority the skill may exercise. They are separate from suspicious or malicious moderation verdicts.
OpenClaw
Benign
high confidencePurpose & Capability
Name/description match the included files: SKILL.md is a skill-authoring guide and the repository includes init, package, and validate scripts plus tests. The requested resources (none) and file contents are proportional to a 'skills creator' utility.
Instruction Scope
SKILL.md stays on-topic (how to author skills, when to include scripts/references/assets). It explicitly notes scripts may be executed; the bundled scripts are typical (create templates, validate frontmatter, package into a zip). That means running the skill could involve executing bundled code — review scripts before running them in your environment.
Install Mechanism
No install spec or external downloads are present. This is an instruction-and-scripts bundle only, so nothing is fetched from untrusted URLs or installed automatically.
Credentials
The skill declares no required environment variables or credentials. The code references only local filesystem operations and standard Python modules; PyYAML is optional and only used if present.
Persistence & Privilege
The skill does not request always:true and uses default autonomous-invocation behavior (normal). It does not attempt to modify other skills or system-wide configurations in the provided code.
Assessment
This package appears coherent for the stated purpose: templates, a validator, a packager, and tests for creating AgentSkills. Before running any scripts, review them locally — they create directories and write files (init_skill) and will read/write filesystem paths when packaging/validating. Packaging includes explicit protections (skips symlinks, checks files stay within the skill root). There are no external downloads, no required secrets, and no odd environment variables. Recommended steps before use: (1) inspect scripts for any network calls or subprocess.exec usage you don't expect, (2) run tests in an isolated/sandbox environment, and (3) if you will execute init_skill or package_skill on directories with sensitive data, ensure the target path is correct to avoid accidental inclusion.Like a lobster shell, security has layers — review code before you run it.
creatorvk976hthfycjdyv7rbttgk3wryx84k5k8latestvk976hthfycjdyv7rbttgk3wryx84k5k8openclawvk976hthfycjdyv7rbttgk3wryx84k5k8skillvk976hthfycjdyv7rbttgk3wryx84k5k8
License
MIT-0
Free to use, modify, and redistribute. No attribution required.