No red flags found in any of the 11 categories — no credential harvesting, no data exfiltration, no curl-pipe-shell installer. Scanned against the SlowMist agent-security taxonomy, refreshed every 8 hours. Full audit →
by SNL-UCSB · Claude Skill · ★ 160
Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h
🔒 Is paper-writing-skill safe to install? View the security audit →
paper-writing-skill PhD students know what they found. Turning that into a paper that gets accepted is where they stall. The problem isn't writing ability — it's operational friction. Structuring sections, maintaining cross-section coherence, compressing to page limits, matching voice conventions, synthesizing figures, responding to reviewers: students spend weeks on scaffolding that an experienced advisor could sketch in an afternoon. This skill offloads that scaffolding to the machine. It encodes 14 editorial principles, section-specific rhetorical move sequences, a five-stage writing pipeline, and a figure synthesis workflow for architectural and conceptual diagrams. All were extracted from forensic analysis of 6 papers, 8 submissions, 7,600+ Overleaf edits, 100+ tex file versions, and 5 peer review processes. These are the patterns that empirically distinguished accepted papers from rejected ones in the same research group. The student retains the hard parts: deciding what the paper claims, whether the evidence supports it, and how to position the work. The machine handles drafting mechanics, structural compliance, figure generation, and revision logistics.
| Stars | 160 |
| Forks | 8 |
| Language | Shell |
| Category | Claude Skill |
| License | MIT |
| Quality Score | 70.9071358929744/100 |
| Open Issues | 2 |
| Last Updated | 2026-07-31 |
| Created | 2026-03-25 |
| Platforms | claude-code, cli |
| Est. Tokens | ~18k |
Looking for a paper-writing-skill alternative? If you're comparing paper-writing-skill with other claude skill tools, these 6 projects are the closest alternatives on Agent Skills Hub — ranked by topic overlap, star count, and community traction.
面向中文用户的学术论文与科研 Agent Skill 每日排行榜 · 自动搜索、过滤并排名 GitHub 上的 Claude Code / Codex / OpenCode 科研 Skill 仓库
An AI workflow skill pack for research, competitions, and innovation projects.
PhD Research Skills for Claude Code: paper reproduction, experiment design, paper review, result comparison an
🎓 AI 科研论文写作助手 - 30 个 Prompt 模板覆盖论文写作全流程。支持中英文翻译、润色、文献综述、投稿回复、基金申请等。
Research automation skills for Claude Code. Idea to submittable paper in one session.
Agent Skill that transforms AI assistants into expert economics paper writers. Synthesizes 50+ guides by Cochr
Explore other popular claude skill tools:
paper-writing-skill is A Claude Code skill that encodes battle-tested editorial principles, section-specific rhetorical moves, and a structured writing pipeline for research papers. Brainstorm → Draft 0 → Evaluate → Write →. It is categorized as a Claude Skill with 160 GitHub stars.
paper-writing-skill is primarily written in Shell. It covers topics such as academic-writing, claude-code, paper-writing.
You can find installation instructions and usage details in the paper-writing-skill GitHub repository at github.com/SNL-UCSB/paper-writing-skill. The project has 160 stars and 8 forks, indicating an active community.
paper-writing-skill is released under the MIT license, making it free to use and modify according to the license terms.
The top alternatives to paper-writing-skill on Agent Skills Hub include awesome-academic-research-skills, Light-skills, phd-skills. Each offers a different approach to the same problem space — compare them side-by-side by stars, quality score, and community activity.
Grades come from a rule-based scan built on the SlowMist agent-security taxonomy, covering 11 red-flag categories including credential harvesting, data exfiltration, and curl | sh installers. It is a first-layer scan, not a manual audit — we say so rather than overstate it.
The scale of the problem is documented independently: Liu et al. (2026), in a study of 31,132 agent skills, report that 26.1% contain security vulnerabilities. Our own full-catalog census is published as a citable open dataset.
Sources & who's responsible: