Refine academic writing for computer science research papers targeting top-tier venues (NeurIPS, ICLR, ICML, AAAI, IJCAI, ACL, EMNLP, NAACL, CVPR, WWW, KDD, SIGIR, CIKM, and similar). Use this skill whenever a user asks to improve, polish, refine, edit, or proofread academic or research writing — including paper drafts, abstracts, introductions, related work sections, methodology descriptions, experiment write-ups, or conclusion sections. Also trigger when users paste LaTeX content and ask for w
Security Analysis
high confidenceThe skill is an instruction-only academic-writing editor whose requested resources and runtime instructions align with its stated purpose and do not request extra system or credential access.
The name and description (refining academic CS writing) match the contents of SKILL.md and the included reference guides. No binaries, env vars, or external services are required, which is appropriate for a prose-refinement skill.
SKILL.md gives concrete, bounded editing instructions (section-specific advice, sentence-level edits, LaTeX-preservation rules). It does not instruct the agent to read unrelated files, exfiltrate data, call external endpoints, or access system credentials.
There is no install spec and no code files — the skill is instruction-only. This is the lowest-risk install profile and proportionate to the described functionality.
The skill declares no required environment variables, credentials, or config paths. That matches its purpose (text refinement) and there are no hidden env accesses in the provided instructions or reference files.
always is false and the skill does not request persistent/system-wide privileges or modifications. It does not ask to modify other skills' configs or system settings.
Guidance
This skill appears internally consistent and low-risk: it only contains editing instructions and reference guides and requests no credentials or installs. Before using, consider data-sensitivity: do not paste unpublished confidential data, private datasets, or secrets into the editor unless you trust the platform's data-retention and privacy policies. If you will share LaTeX source that includes \\input, external graphics, or custom compile commands, be aware those could reference local files (the skill itself won't execute them, but sharing full sources can expose paths or private content).
Latest Release
v1.0.0
- Initial release of "academic-writing-refiner" skill for polishing computer science research papers targeting top-tier venues. - Refines abstracts, introductions, related work, methodology, experiments, conclusions, and supports both section and full-paper editing. - Handles LaTeX content with careful preservation of formatting, citations, and mathematical environments. - Applies section-specific conventions and systematic sentence-level improvements for clarity, precision, and conciseness. - Provides clear output: refined text, marginal change notes, and flags unfixable issues.
Popular Skills
Published by @Zihan-Zhu on ClawHub
