Academic Paper Assistant

v1.0.0

专业的学术论文写作助手。当用户要求撰写、修改、润色学术论文,或需要论文结构规划、参考文献整理、学术用语规范化、查重检测等支持时使用。触发短语包括:"写论文"、"润色论文"、"修改论文"、"论文结构"、"参考文献格式"、"学术用语"、"论文查重"等。

0· 80·0 current·0 all-time
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 (academic writing, editing, citation formatting, guidance on plagiarism) matches the SKILL.md content and the included reference docs. The included helper scripts are packaging/validation utilities and are reasonable for a skill repository; nothing in the manifest requests unrelated cloud credentials, binaries, or configuration paths.
Instruction Scope
SKILL.md confines runtime behavior to analyzing and transforming user-provided text (structure suggestions, wording, citation formatting, guidance on check/duplication). It does not instruct the agent to read system files, access external endpoints, or gather unrelated system context. Note: performing its functionality requires the user to provide manuscript text, which may be sensitive.
Install Mechanism
There is no install spec (instruction-only runtime). The two Python scripts in scripts/ are benign utilities (packaging and frontmatter/metadata validation) and do not perform network I/O or hidden downloads. No archive downloads or third-party installs are requested.
Credentials
The skill declares no required environment variables, credentials, or config paths. There are no requests for unrelated secrets or elevated access that would be disproportionate for an academic writing assistant.
Persistence & Privilege
always is false and the skill is user-invocable; disable-model-invocation is false (normal). The skill does not request permanent presence or system-wide configuration changes.
Assessment
This skill appears coherent and safe in terms of requested access, but be cautious about the content you share: do not paste unpublished confidential data, personally identifiable information, or proprietary datasets unless you are comfortable sharing them. The skill's '查重' / duplicate-detection is guidance only (not an official plagiarism report) — for formal checks use a dedicated institutional plagiarism service. The included Python scripts are local utilities; you don't need to run them to use the skill, and you should only execute code from sources you trust. If you need higher assurance, request the publisher/owner or more provenance (homepage or repository) before installing.

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

latestvk978t2nkxf9aezbvp9b40tq3rd83jvw5

License

MIT-0
Free to use, modify, and redistribute. No attribution required.

Comments