OpenClaw Skill Creator

v1.0.0

Crea skills para OpenClaw con el formato correcto. YAML frontmatter, _meta.json, estructura de archivos. Publicar en ClawHub es opcional.

1· 73·0 current·0 all-time
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 (OpenClaw skill creator) match the instructions and required files (_meta.json and SKILL.md). The requested actions (create files in the local workspace, validate YAML/JSON, optionally publish via the ClawHub CLI) are coherent with the stated purpose.
Instruction Scope
Instructions tell the agent to write skill files under /mnt/data/openclaw/workspace/.openclaw/workspace/skills/... and to restart the OpenClaw gateway. Writing to the user's workspace and restarting the gateway are reasonable for this skill but require user consent and appropriate filesystem/daemon permissions. Publishing steps invoke 'npx clawhub' which will fetch code at runtime if executed by the user (this is optional and outside the skill itself).
Install Mechanism
No install spec and no bundled code are present (instruction-only). There are no download URLs or archive extraction. Note: the SKILL.md demonstrates using 'npx clawhub' for publishing, which will download an npm package at publish time — that is an expected, optional external action and not part of the skill's installation.
Credentials
The skill declares no required environment variables, no credentials, and no config paths. The publishing workflow asks the user to authenticate via 'npx clawhub login' and GitHub — that is optional and appropriate for publishing, not required for skill creation.
Persistence & Privilege
The skill is not always-on and does not request elevated or permanent platform privileges. Model invocation is allowed (platform default) but the skill itself contains only instructions and no autonomous installers or persistent agents.
Assessment
This skill is an instruction/template helper and looks safe to use, but review these points before proceeding: (1) Confirm you want the agent to write files under /mnt/data/... and that the path matches your environment — the skill will create files in your workspace. (2) Restarting the OpenClaw gateway may require permissions or affect running agents; perform that step only if you control the instance. (3) Publishing is optional and uses 'npx clawhub' which will download code at publish time and requires GitHub login — do not publish if you don't want to authenticate or expose the package to an external registry. (4) Inspect generated SKILL.md and _meta.json contents before publishing to ensure no sensitive data was accidentally included.

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

latestvk977ry8mf1yjfjxzj7fctyc8g9841sm2localvk977ry8mf1yjfjxzj7fctyc8g9841sm2openclawvk977ry8mf1yjfjxzj7fctyc8g9841sm2skill-creatorvk977ry8mf1yjfjxzj7fctyc8g9841sm2templatevk977ry8mf1yjfjxzj7fctyc8g9841sm2

License

MIT-0
Free to use, modify, and redistribute. No attribution required.

Comments