Skill Creator
v1.0.3创建、编辑、改进或审核 OpenClaw AgentSkill。触发场景：用户要求"创建一个 skill"、"写一个技能"、"帮我新建技能"、"改进这个 skill"、"审核 skill"、"整理 skill"、"完善技能说明"。同时用于：skill 目录结构调整、文件迁移（移动到 references/ 或 s...
⭐ 0· 83·0 current·0 all-time
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 claim to help create, edit, and audit skills; packaged files (SKILL.md guide + init/package/validate scripts + references) directly implement that functionality. No unrelated credentials, binaries, or config paths are requested.
Instruction Scope
SKILL.md and the included scripts instruct local operations you would expect from a skill-authoring tool: create directories, write SKILL.md templates, create example resource files, validate frontmatter, and package a skill into a zip (.skill). The instructions reference only local filesystem operations and standard Python execution; they do not direct reading of unrelated system files, network exfiltration, or access to secrets.
Install Mechanism
No install spec or remote downloads. This is an instruction-first skill with small helper scripts included. The scripts are plain Python, use standard libraries (argparse, pathlib, zipfile), and do not fetch remote code.
Credentials
No environment variables, credentials, or config paths are required. The scripts operate on provided filesystem paths. There are no unexpected SECRET/TOKEN/PASSWORD environment variable requests.
Persistence & Privilege
always:false and user-invocable:true (defaults). The skill does create files/directories when run (init, package) but does not modify other skills' configs or request persistent platform privileges.
Assessment
This skill appears coherent and implements a straightforward authoring workflow. Before running: (1) inspect the three included Python scripts yourself — they create files, write templates, validate frontmatter, and create ZIP packages but do not perform network requests; (2) run them in an isolated workspace (not your home or a repo with sensitive files) to avoid accidental file creation or packaging; (3) if you will share packaged .skill files, review frontmatter rules (SKILL.md/quick_validate) to ensure compatibility; and (4) remember the skill runs local commands as written — treat it like any third‑party developer tool and audit code if you have elevated security concerns.Like a lobster shell, security has layers — review code before you run it.
latestvk977z2f0ahzxwzxdggb57zc7qs84awey
License
MIT-0
Free to use, modify, and redistribute. No attribution required.