参谋官审核
v1.0.0专业内容参谋官，严格审核稿件错别字、流畅度、逻辑性、完整性及需求符合度，输出合格与否及具体问题。
⭐ 0· 71·0 current·0 all-time
byLaton@xiaozha87
MIT-0
Download zip
LicenseMIT-0 · Free to use, modify, and redistribute. No attribution required.
Security Scan
OpenClaw
Benign
high confidencePurpose & Capability
Name, description, and SKILL.md all describe a content quality reviewer (spelling, fluency, logic, completeness, requirement fit). The skill requests no binaries, env vars, or configs that would be unrelated to that purpose.
Instruction Scope
SKILL.md directs the agent to evaluate the previous draft along specific dimensions and to output a concise pass/fail result with issues if not passing. It does not instruct reading system files, environment variables, or sending data to external endpoints. The reference to '上一步生成的稿件' (the prior-generated draft) is expected for this use.
Install Mechanism
No install spec or code files — instruction-only. Nothing will be downloaded or written to disk by an installer.
Credentials
The skill declares no required environment variables, credentials, or config paths; there are no disproportionate credential requests.
Persistence & Privilege
The skill does not request always-on presence and uses platform defaults for invocation. It does not modify other skills or request elevated/system privileges.
Assessment
This skill is instruction-only and appears internally consistent with its stated purpose: it reviews a provided draft and returns a concise pass/fail plus issues. Before installing, consider: (1) the skill will evaluate whatever text you feed it — avoid sending sensitive or private information to be reviewed; (2) review results are produced by the agent/model and should be spot-checked for correctness; and (3) test with non-sensitive examples to confirm the output format and behavior meet your needs.Like a lobster shell, security has layers — review code before you run it.
latestvk975ekafee6tqpf2gq8qf3kpes83p4r3
License
MIT-0
Free to use, modify, and redistribute. No attribution required.