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 tsingyuai · AI Tool · ★ 2.2k
Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h
🔒 Is scientify safe to install? View the security audit →
Scientify 端到端自主演进的 AI 科研系统 Scientify.tech · English 端到端自主研究：持续演进，产出 SOTA 级成果 给 Scientify 一个研究目标，它会自主完成文献调研、假设生成、代码实现、审查和实验验证，并根据结果持续修正研究方向。 Scientify 通过多智能体迭代推进研究。编排器保留研究假设和已有积累，调度独立智能体完成实现、审查和实验。每轮实验的结果都会沉淀为下一轮的经验，让研究沿着更有效的路径持续推进。 案例 1：自主发现 KV2 算法，达到领域领先性能 研究目标：针对长上下文大语言模型推理，设计一种同时降低首 token 时延和单请求通信量的策略。 Scientify 自主完成文献调研、假设生成、代码实现与消融实验，提出 KV2 算法。相较于现有研究，KV2 的首 token 时延第 95 百分位（TTFT p95）和单请求通信量（bytes/request）均有降低，性能达到 SOTA 水平。 Scientify 自主产出的学术论文，呈现 KV2 的设计思路与实验结果 KV2 与现有方法的性能对比 案例 2：揭示黑洞状态演变的三个边界，建立可预测的理论框架 Scientify 独立完成理论推导、数值分析和论文撰写，产出 Equilibrium Gibbs Bifurcations of Bardeen-AdS Black Holes at Fixed Pressure。 理论发现：在论文采用的 Bardeen-AdS 黑洞热力学定义下，Scientify 将已有研究中的复杂自由能曲线归纳为具有三个明确边界的演变序列：随着黑洞中心平滑区域扩大，曲线从燕尾形经过 8 字形、c 形，最终变为单分支。关键发现是，第一次曲线变形后，大小黑洞仍可稳定共存。三个形态边界都服从同一压力缩放关系，最终单分支边界还具有精确解析解。 数据依据：Scientify 比较三个压力下的温度与自由能计算数据，通过曲线转折点和交点追踪三次形态变化。将压力与中心尺度按同一方式组合后，各压力下的三个边界分别归并为三个固定数值，揭示出跨压力的共同结构。它进一步从方程中推导出这一关系，并用热容检查稳定性、用自由能比较大小黑洞，验证了曲线变形后仍存在稳定共存。 理论意义：它把此前描述曲线形状的结果推进为可计算转变位置
| Stars | 2,245 |
| Forks | 190 |
| Language | TypeScript |
| Category | AI Tool |
| Quality Score | 44.4949691740194/100 |
| Open Issues | 6 |
| Last Updated | 2026-09-08 |
| Created | 2026-02-04 |
| Platforms | node |
| Est. Tokens | ~14k |
These tools work well together with scientify for enhanced workflows:
Looking for a scientify alternative? If you're comparing scientify with other ai tool tools, these 6 projects are the closest alternatives on Agent Skills Hub — ranked by topic overlap, star count, and community traction.
Examples of my Claude Code infrastructure with skill auto-activation, hooks, and agents
This tool has been deprecated. Use Agentic Document Extraction instead.
Visual Skills Pack for Obsidian: generate Canvas, Excalidraw, and Mermaid diagrams from text with Claude Code
All powerful skills of ClaudeKit.cc!
A tool uses Windows Filtering Platform (WFP) to block Endpoint Detection and Response (EDR) agents from report
A java agent to generate method mappings to use with the linux `perf` tool
Explore other popular ai tool tools:
scientify is Automatic and end-to-end scientific research workflow. Produces state-of-the-art level research results.. It is categorized as a AI Tool with 2.2k GitHub stars.
scientify is primarily written in TypeScript.
You can find installation instructions and usage details in the scientify GitHub repository at github.com/tsingyuai/scientify. The project has 2.2k stars and 190 forks, indicating an active community.
The top alternatives to scientify on Agent Skills Hub include claude-code-infrastructure-showcase, vision-agent, axton-obsidian-visual-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: