通用去 AI 化写作 Skill,兼容任意 Agent Skills 协议的 Agent(通过 Skills CLI 支持 77+),并提供 Claude Code、Codex、Grok Build、Antigravity 的原生插件。修复虚构写作的叙事架构,按场景匹配专业文体规则。基于 StoryScope(arXiv:2604.03136)。De-AI writing skill for any Agent Skills-compatible agent (77+ via the Skills CLI), with native plugins for Claude Code, Codex, Grok Build, and Antigravity. Narrative-architecture repair for fiction, venue-matched rules for professional prose. Based on StoryScope (arXiv:2604.03136).
趋势榜
实时增长榜 · 周综述每周日由 spark 生成
按日期回看
2026-08-29 新收录仓库 33 个
ChatGPT 负责思考,Codex 负责执行。保留 Codex harness 的同时,让 ChatGPT 担任规划大脑。ChatGPT thinks. Codex works. Use ChatGPT as the planning brain while keeping the Codex harness.
ACRYL - Agent Context Relay Yielding Lifecycles。一个持久化工作空间,一份规范上下文,兼容任意 coding agent。ACRYL - Agent Context Relay Yielding Lifecycles. One persistent workspace, one canonical context, any coding agent.
GLM-5.3 Flash EXL3,针对 2x DGX Sparks。GLM-5.3 Flash EXL3 for 2x DGX Sparks
面向 Claude Code 与 Codex 的 MCP server。一次 tool call 即可替代约 42 分钟的 agent 探索。MCP server for Claude Code and Codex. One tool call replaces ~42 minutes of agent exploration
受 Premiere 启发、面向 MiniMax H3 Ref2VA 的 PySide6 导演工作室,集成 AI 分镜规划、语义媒体增强、时间线 prompt 调和,以及通过 ComfyUI 实现的镜头感知长视频渲染。Premiere-inspired PySide6 director studio for MiniMax H3 Ref2VA with AI shot planning, semantic media enrichment, timeline prompt reconciliation and shot-aware long-video rendering through ComfyUI.
由 CyberLeek 泄露的 GTA 6 Alpha 构建版本,包含可玩完整构建、Vice City 地图、玩法、过场动画与资产。启动器仅 100 MB,安装过程中下载完整 106 GB 构建。GTA 6 Alpha build leaked by CyberLeek. Full playable build with Vice City map, gameplay, cutscenes, and assets. Launcher is 100 MB — downloads the full 106 GB build during installation.
基于 UltraStarFox 代码库构建的原生 60 FPS PC 源码移植版本。A native 60 FPS PC source port built from the UltraStarFox codebase.
开源元搜索引擎后端、MCP server 与面向 LLM agent 的 AI 搜索 API。基于 Python FastAPI 的搜索网关,通过 SerpBase 与 Serper 集成 Google 搜索,支持多引擎搜索聚合、结构化 JSON 输出、provider 回退与去重,并提供 SearXNG 替代架构以适配 agent 工作流。Open-source metasearch backend, MCP server, and AI search API for LLM agents. Python FastAPI search gateway with Google search via SerpBase and Serper, multi-engine search aggregation, structured JSON output, provider fallback, deduplication, and SearXNG alternative architecture for agent workflows.
AI浏览器 MCP Server — Windows 本地浏览器自动化 MCP 服务端 · 265 tools · Cursor/Claude Code/Claude Desktop/Trae 原生 stdio 直连 · Web Scraping · JS 逆向 · CDP 断点 · 指纹反检测 · 网络拦截 · 填表 RPA · FBrowser CEF 内核 · MIT 开源
Writing Support Desk(WSD)—— 温莎大学 | 学术写作、引用规范(APA、MLA、IEEE、Chicago)与学术诚信资源Writing Support Desk (WSD) – University of Windsor | Academic writing, citation standards (APA, MLA, IEEE, Chicago), and academic integrity resources
符合 NASA、ESA、CSA 规范的 FAIR 开放科学、开源软件与可复现研究。代码许可:EUPL 1.2。数据/文档许可:CC BY-SA 4.0。通过 Zenodo/OSF 分配 DOI。研究者:Louis-Philippe Audette | psivi.comFAIR open science, open-source software, and reproducible research aligned with NASA, ESA, and CSA. Code: EUPL 1.2. Data/Docs: CC BY-SA 4.0. DOIs via Zenodo/OSF. Researcher: Louis-Philippe Audette | psivi.com
面向 Claude Code 的对抗式学术写作审阅工具包 — 包含 30+ 审计 Skill(LaTeX、文献、可读性、模拟同行评审)以及一个机械检查器的 MCP server。Adversarial academic-writing review toolkit for Claude Code — 30+ audit skills (LaTeX, bibliography, readability, simulated peer review) plus an MCP server of mechanical checkers.
面向 DeepSeek Harness 的本地文献综述、PDF 标注、证据综合与研究笔记工作台。A local literature review, PDF annotation, evidence synthesis, and research notes workbench for DeepSeek Harness.
Agentic 流水线,检索 arXiv、Semantic Scholar 与 Hugging Face Papers,基于每篇论文自身的"局限性与未来工作"章节产出未来工作思路报告,并对缺少该章节的论文给出明确标注的推断分级。通过 Ollama 完全本地运行。Agentic pipeline that searches arXiv, Semantic Scholar, and Hugging Face Papers, then produces a report with future work ideas grounded in each paper's own Limitations and Future Work sections, plus a clearly labeled inferred tier for papers without one. Runs fully locally through Ollama.
由 LLM 编排的自主 EDA 与数据预处理框架 — 自动生成面向特定数据集的研究问题,编写并自我修正分析代码,自动选择可视化。基于 Claude/GPT 构建。LLM-orchestrated framework for autonomous EDA and data pre-processing — generates dataset-specific research questions, writes and self-corrects analysis code, and auto-selects visualizations. Built with Claude/GPT.
Jupyter notebook 示例Example Jupyter notebook
通过 GNOME Shell 扩展为桌面添加细腻的纸张质感纹理叠加层,缓解用眼疲劳,方便阅读与编码。Reduce eye strain with a GNOME Shell extension that adds a subtle paper-like texture overlay to your desktop for easier reading and coding
面向研究论文的可编辑科学图表的创建、评审与精炼。Create, critique, and refine editable scientific diagrams for research papers.
面向初学者的研究项目,通过统计分析与线性回归探究学习习惯与学业表现之间的关系。A beginner research project investigating the relationship between study habits and academic performance using statistical analysis and linear regression.
Statistika Berbasis Data — Bahasa Indonesia (id-ID) 工作版,基于 OpenIntro Statistics 派生,包含 LaTeX 源文件、PDF 阅读器、模块化后端与 QA。Statistika Berbasis Data — edisi kerja Bahasa Indonesia (id-ID), diturunkan dari OpenIntro Statistics, dengan sumber LaTeX, pembaca PDF, backend modular, dan QA.
在 Overleaf 中直接启用 AI 驱动的引用检索与论文审阅,提升写作与引用效率。Enable AI-driven citation search and paper review directly within Overleaf to improve referencing and writing efficiency.
关于延长 5 天方案对比标准 3 天方案 artemether-lumefantrine 治疗非复杂型 Plasmodium falciparum 疟疾的 systematic review 与 meta-analysis 的可复现工作流、数据、分析与补充材料。Reproducible workflow, data, analyses, and supplementary materials for a systematic review and meta-analysis of extended 5-day versus standard 3-day artemether-lumefantrine for uncomplicated Plasmodium falciparum malaria.
SLU GS-VMAS 研究生院与 MedBioInfo 的合作项目,2026 年版。Collaboration between SLU's GS-VMAS Graduate School and MedBioInfo, 2026 rendition
2026-08-29 增长榜定格 当日周增 Top 20
| 名次 | 名称 | 方向 | 周增 | Stars |
|---|---|---|---|---|
| 1 — | odysseus-dev/odysseus | Agent 智能体 | +152,621 | 84,138 |
| 2 — | anywhere-labs/deepseek-harness-desktop | 评测基准 | +8,281 | 13,495 |
| 3 — | stablyai/orca | Agent 智能体 | +5,299 | 47,228 |
| 4 — | s1dashu/ip-as-logo-skill | Agent 智能体 | +4,646 | 3,727 |
| 5 — | MiniMax-AI/MiniMax-H3 | LLM 基础设施 | +4,445 | 4,611 |
| 6 — | diegosouzapw/OmniRoute | Agent 智能体 | +4,343 | 53,672 |
| 7 — | holaboss-ai/holaOS | Agent 智能体 | +3,798 | 9,436 |
| 8 — | safishamsi/graphify | 数据与向量库 | +3,752 | 76,856 |
| 9 — | NousResearch/hermes-agent | Agent 智能体 | +3,386 | 230,735 |
| 10 — | zhu1090093659/dsh-web-ui | 评测基准 | +3,318 | 4,541 |
| 11 — | firecrawl/firecrawl | RAG 检索增强 | +2,975 | 165,271 |
| 12 — | firecrawl/anydoc | 工程化 | +2,870 | 13,720 |
| 13 — | koala73/worldmonitor | Agent 智能体 | +2,239 | 82,478 |
| 14 — | bojieli/ai-agent-book | Agent 智能体 | +2,191 | 42,597 |
| 15 — | hoainho/img2threejs | 多模态 | +2,051 | 4,176 |
| 16 — | DietrichGebert/ponytail | Agent 智能体 | +1,869 | 100,293 |
| 17 — | HKUDS/DeepTutor | Agent 智能体 | +1,820 | 35,926 |
| 18 — | anthropics/skills | Agent 智能体 | +1,722 | 167,649 |
| 19 — | infiniflow/ragflow | RAG 检索增强 | +1,661 | 88,637 |
| 20 — | addyosmani/agent-skills | Agent 智能体 | +1,631 | 85,866 |