ClawHub

chinese-copywriting-guidelines-full-clawhub

v1.0.0

Apply the complete Chinese Copywriting Guidelines with full upstream content bundled locally. Use when reviewing or rewriting Chinese copy in Markdown, docs,...

⭐ 0· 135·0 current·0 all-time
by@zhonglouxiaonaigao-art
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
Name/description (apply full Chinese copywriting guidelines) matches the bundled files and SKILL.md instructions. The skill only includes text snapshots of the upstream repository and tells the agent to load those local files to apply rules.
ℹ
Instruction Scope
SKILL.md restricts runtime actions to loading the bundled reference files and applying rules, which is appropriate. Note: the included README files contain external links and an <img src> pointing to a CDN; if the agent is allowed to follow or render links/images it could perform network requests. SKILL.md itself does not instruct external fetching, but callers should be aware of this when asking the agent to expand or follow references.
✓
Install Mechanism
No install spec and no code files to execute; nothing will be written or executed during install.
✓
Credentials
No required environment variables, credentials, or config paths are declared or referenced in SKILL.md.
✓
Persistence & Privilege
Skill does not request always:true and uses default invocation behavior. It does not modify other skills or request system-wide settings.
Assessment
This skill is basically a read-only bundle of the Chinese Copywriting Guidelines and instructions for using them — that is coherent and low-risk. Before installing, consider: 1) License mismatch: the SKILL.md/source-info claims the upstream is CC BY-SA 4.0 but bundled LICENSE.txt and package.json indicate WTFPL; verify the actual upstream license if you plan to redistribute or use the rules commercially. 2) The bundled README contains external links and an image URL; if you ask the agent to follow links or render images it may make network requests — avoid that if you want purely local processing. 3) The snapshot includes package.json/Gruntfile as .txt (harmless), but you should still review the bundled text if you care about provenance or contributor attribution. If those items are acceptable, the skill appears coherent with its stated purpose.

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

latestvk971shmr9g5d2dzhdkpfcprc9n834df2

License

MIT-0
Free to use, modify, and redistribute. No attribution required.
Termshttps://spdx.org/licenses/MIT-0.html

Comments