Cell 风格写作
v0.1.0Personal Chinese writing-style skill for Cell 细胞 style articles, rewrites, style enhancement, and style review. Use when Codex needs to write, rewrite, enhan...
⭐ 0· 26·0 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, and included assets (templates, style guides, checklists, personal-variables) all match a writing-style skill. Nothing in the manifest requests unrelated credentials, binaries, or config paths.
Instruction Scope
Runtime instructions are limited to reading the skill's local assets (brief template, style guides, checklists) and applying style rules. The references include a 'personal-variables' sheet with specific identity/project examples; while the SKILL.md explicitly forbids fabricating personal history, the presence of these identity examples means the agent could be prompted to write as a specific persona if the user allows it. Users should check or edit personal-variables.md if they do not want those identity claims used or exposed, and avoid submitting sensitive private content to the skill.
Install Mechanism
No install spec and no code files — instruction-only. Nothing is downloaded or written to disk by an installer.
Credentials
The skill requires no environment variables, credentials, or external endpoints. Requested data and assets are all local to the skill bundle.
Persistence & Privilege
always:false and standard model invocation settings. The skill is user-invocable and may be invoked autonomously by an agent (platform default), but it does not request permanent presence or elevated privileges.
Assessment
This skill appears coherent and low-risk: it's instruction-only, asks for no credentials, and only uses its included templates and guides. Before installing or using it: (1) review assets/personal-variables.md and edit or remove any persona or project claims you don't want the agent to assert; (2) avoid submitting sensitive or verifiable private data as source material (the skill encourages adding lived details but also warns against fabrication); (3) test the skill on non-sensitive drafts first to ensure outputs meet your expectations; (4) remember the skill can be invoked autonomously by agents per platform defaults—disable or restrict autonomous use in your agent settings if you do not want that behavior.Like a lobster shell, security has layers — review code before you run it.
latestvk972p9yex7fazmv4yapps62ken84ddgz
License
MIT-0
Free to use, modify, and redistribute. No attribution required.