ClawHub

AI 写作诊断

v0.1.0

AI-writing fingerprint diagnosis for Chinese text. Use when Codex needs to inspect a draft for overly smooth, formulaic, generic, or authorless writing patte...

⭐ 0· 17·0 current·0 all-time
by@cellinlab
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 (AI-writing diagnosis for Chinese text) aligns with the SKILL.md, pattern catalog, rewrite guidance, and report template. There are no unrelated required binaries, environment variables, or config paths.
✓
Instruction Scope
Runtime instructions are limited to reading the user-provided text, quoting suspicious passages, classifying patterns using the included references, and suggesting fixes. The skill does not instruct reading system files, environment variables, or transmitting data to external endpoints. It references handing work off to `$celf-style-writer`, which is a logical workflow note, not an unexplained credential or external URL.
✓
Install Mechanism
No install spec and no code files are present; this is instruction-only, so nothing is written to disk or downloaded at install time.
✓
Credentials
The skill declares no required environment variables, credentials, or config paths. The instructions do not reference any secrets or external service keys.
✓
Persistence & Privilege
always is false and model invocation is allowed (platform default). There is no request for permanent system presence or modification of other skills' configs.
Assessment
This is a low-risk, instruction-only skill that analyzes user-provided Chinese text and uses only its bundled reference files. Before using it, consider: (1) privacy — any text you submit will be read by the agent (avoid feeding secrets or sensitive personal data); (2) autonomous invocation — the agent may call the skill when relevant, so ensure you are comfortable with automatic analysis of drafts; and (3) handoff behavior — the SKILL.md mentions `$celf-style-writer` as a possible downstream step; check whether that other skill exists and what privileges it has if you plan to use the rewrite handoff. Otherwise, the skill's requests and instructions are proportionate to its stated purpose.

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

latestvk97es7hf596xjq05vww8y50kq984jwgd

License

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

Comments