Editorial Review
v0.1.0Comprehensive editorial review for Chinese content before publication. Use when the user asks to 'review my article', 'proofread this', 'check for errors', '...
⭐ 0· 109·0 current·0 all-time
MIT-0
Download zip
LicenseMIT-0 · Free to use, modify, and redistribute. No attribution required.
Security Scan
OpenClaw
Benign
high confidencePurpose & Capability
Name/description (Chinese editorial review) match what the skill asks for: no extra credentials or unrelated binaries are required. The skill.json declares network and filesystem access, which are reasonable for fact‑checking (network) and producing/saving review reports (filesystem).
Instruction Scope
SKILL.md describes a bounded 8-layer review pipeline that operates on user-provided Chinese text and the bundled reference docs. Instructions do not direct the agent to read unrelated system files, environment variables, or exfiltrate data to unknown endpoints; network use is described only for source verification.
Install Mechanism
Instruction-only skill with no install spec and no code files; nothing will be written to disk by an installer. This is the lowest-risk install model and matches the skill type.
Credentials
No environment variables, credentials, or config paths are requested. The declared capabilities (network, filesystem read/write) are proportional to fact-checking and generating reports; no extraneous secrets are required.
Persistence & Privilege
always is false; the skill does not request forced inclusion or system-wide configuration changes. Autonomous invocation is allowed by default (platform normal), and the skill does not claim to modify other skills or system settings.
Assessment
This skill appears coherent for pre-publication Chinese editorial and compliance reviews. Before installing, consider: (1) granting network access lets the agent fetch and verify sources externally — if you disallow network, fact-checking will be limited; (2) filesystem write permission lets it save structured reports — revoke if you don't want files written; (3) the political/compliance layer flags sensitive terminology and recommends human review for high-stakes content, so treat its political/legal suggestions as advisory and get a qualified human sign-off for regulated or high-risk publications; (4) the skill is labeled experimental — review a few outputs carefully to ensure its suggestions match your editorial standards.Like a lobster shell, security has layers — review code before you run it.
latestvk97a2szhrep62ask9rny441fmh839mcs
License
MIT-0
Free to use, modify, and redistribute. No attribution required.