ClawHub

Language Coach

v2.0.3

Multi-language writing coach for grammar, word choice, collocations, and idiom errors. Supports English, Chinese, Spanish, French, and Japanese. Activated vi...

⭐ 0· 80·1 current·1 all-time
byKaigeGao@kaigegao1110
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 match the provided command files and SKILL.md. All declared pages and command templates are language-correction focused; nothing requests unrelated access (cloud creds, system files, etc.).
✓
Instruction Scope
Runtime instructions restrict behavior to reviewing the user-provided text and returning a single brief correction + one-sentence explanation. The skill does not instruct the agent to read other files, environment variables, or to transmit data to external endpoints.
✓
Install Mechanism
No platform install spec is provided (instruction-only). README offers manual GitHub clone or zip download, which is standard and uses a well-known host (github.com). Nothing downloads from obscure URLs or writes code during automated install.
✓
Credentials
The skill declares no required environment variables, credentials, or config paths. The requested scope (none) is appropriate for a text-correction skill.
✓
Persistence & Privilege
always is false and user-invocable is true (default). The skill does not request elevated system presence or modify other skills. Autonomous invocation remains possible (platform default) but is not flagged by the skill itself.
Assessment
This skill is instruction-only and internally consistent with its stated purpose. A few practical things to consider before installing: (1) The SKILL.md asserts user text "never stored or transmitted externally" — that is a developer claim, not a platform enforcement guarantee; if you have strong privacy needs, review the repository locally before installing or avoid sending highly sensitive text. (2) The README shows manual install via GitHub (standard); if you install via an automated tool, inspect what the installer does. (3) Because the skill can be invoked autonomously by agents (platform default), be mindful that it will see any text you prefix with the activation commands. Overall this appears coherent and proportionate for a writing-coach skill.

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

latestvk977fjcwrrzhfrtxx0nfn10eh983sn3b

License

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

Comments