按模型自适应地缩放系统提示指引:一个 oh-my-pi 插件,按模型系列、版本与层级追加经过能力调优的指令块。Scales system-prompt guidance to the model reading it: an oh-my-pi plugin that appends a capability-tuned directive block chosen by model family, version, and tier.
仓库/Skill 库
850 个 · 工具
运行在你 PC 上的开源 AI 内容工厂——自动发现主题、调研、撰写、多模型 QA 审核并发布。基于 Ollama 本地优先,$0 API 成本。The open-source AI content factory that runs on your PC — discovers topics, researches, writes, reviews with multi-model QA, and publishes. Local-first via Ollama, $0 API costs.
本地优先、可审计的技术文档与源代码知识编译器。Local-first, auditable knowledge compiler for technical docs and source code
Claude Code 插件,用于科学论文写作、来源可追溯的审稿与去 AI 化润色。在统一类型化标准下汇聚 8 项 skill + 24 个工具:不可豁免的完整性阻断项、零目标 L0 词库、分级告警以及显式测量状态,避免缺失校准被误读为通过。针对 ApJ/MNRAS/PRD/JCAP 级期刊稿件进行了语料校准。Claude Code plugin for scientific paper writing, source-traced review, and de-AI rewriting. 8 skills + 24 tools under one typed standard: non-waivable integrity blockers, zero-target L0 lexicon, ranked advisories, and explicit measurement states so missing calibration never reads as clean. Corpus-calibrated for ApJ/MNRAS/PRD/JCAP-class manuscripts.
基于大语言模型的智能研发效能助手。深度解析需求文档,精准识别逻辑漏洞;多维度生成测试用例,提升用例设计效率;构建可复用的测试知识库,将个人经验转化为团队资产。赋能 QA ,实现质量保障智能化。
基于 Tectonic 的超快离线 La/TeX 编译 API,部署于 Hugging Face SpacesA blazingly fast API for compiling La/TeX offline with Tectonic, hosted on Hugging Face Spaces.
Preprint Bot —— 学术论文推荐系统。Preprint Bot - Academic Paper Recommendation System
Claude Code 扩展、hooks 和插件的实时索引,每 15 分钟从 GitHub 刷新一次。Live index of Claude Code extensions, hooks, and plugins — refreshed every 15 minutes from GitHub
基于 Keystone 构建的开发者友好型书籍发布模板,为精简变体——项目体积小,使用公共 Docker 镜像。Developer-friendly book publishing template built on Keystone. Slim variant — minimal project footprint, uses a public Docker image
🔍 使用 DeepSearch 自动化数字足迹分析,借助高级 Google 搜索操作符高效收集多平台洞察。🔍 Automate digital footprint analysis with DeepSearch, using advanced Google search operators to gather insights from multiple platforms efficiently.
🔬 用 Science Flake 探索数据科学工作流——一个强大工具,可轻松管理和分享可复现的研究环境。🔬 Explore data science workflows with Science Flake, a powerful tool for managing and sharing reproducible research environments effortlessly.
基于 DNS、证书透明日志与未认证身份发现的公开元数据域情报。本地 Python CLI、版本化 JSON 与 stdio MCP server,无需凭证或主动扫描。Public-metadata domain intelligence from DNS, certificate transparency, and unauthenticated identity discovery. Local Python CLI, versioned JSON, and stdio MCP server. No credentials or active scanning.
Local-first、确定性的验证层,用于 AI 声明、记忆写入和风险操作。Local-first, deterministic verification layer for AI claims, memory writes, and risky actions.
并行运行 Claude Code、Codex 与 Gemini,并支持彼此交接任务。面向 AI CLI 的便携 Windows 终端。Run Claude Code, Codex and Gemini side by side — and let them hand work to each other. Portable Windows terminal for AI CLIs.
基于 Rust 的 SIP 与 RTP 抓包、分析与安全工具,单二进制,仅依赖 libpcap。SIP & RTP capture, analysis, and security tool. One binary, one dependency (libpcap), built in Rust.
遵循中文学术写作规范的学术 humanizer。Fork 自 AIScientists-Dev/academic-humanizer。Academic humanizer with Chinese academic writing rules. Fork of AIScientists-Dev/academic-humanizer.
Comic Sol —— 以本地优先的 AI 漫画生产,作为 Codex Skill、Python CLI 和 MCP 服务器。Comic Sol - local-first AI comic production as a Codex Skill, Python CLI, and MCP server.
DSH 完整移植版 DietrichGebert/ponytail — 懒惰 senior 模式,6 个中文 Skill,无空 tool
基于 Zotero 的文献综述助手,支持基于原文的 PDF 抽取、声明验证、内容综合及 Semantic Scholar 检索Zotero-based literature review assistant for grounded PDF extraction, claim verification, synthesis, and Semantic Scholar search.
利用 LLM 提示词、证据链接笔记、Excel 跟踪与跨论文综合,从 PDF 自动生成博士文献综述Automate PhD literature reviews from PDFs with LLM prompts, evidence-linked notes, Excel tracking, and cross-paper synthesis.
自托管语义代码搜索。将代码仓库和知识源索引至本地向量数据库,然后通过 CLI 或任何 MCP 兼容 Agent 进行自然语言搜索。Self-hosted semantic code search. Index repos and knowledge sources into a local vector DB, then search by natural language from CLI or any MCP-compatible agent.
自动化并规模化 "LLMs as a participant",将 LLM 作为研究参与者Automates and scales "LLMs as a participant."
原生 LaTeX 的修订追踪,面向人类与 AI 辅助审阅。LaTeX-native track changes for human and AI-assisted review
为你的 AI 编程助手打造的持久记忆。它会记住你告诉它的内容,并在恰当时机把对应的笔记交还。本地机器全量运行。A memory for your AI coding assistant. It keeps what you tell it and hands the right note back at the moment it matters. Runs entirely on your own machine.
MendCode:可定制的 CLI,面向 agent、团队、记忆、评审与 TUI。MendCode: Customizable CLI for agents, teams, memory, reviews, and TUI.
面向多 Agent 工作流的 MCP 协调原语。LLM 无关、CLI 无关、可自托管。TypeScript + SQLite。MCP coordination primitive for multi-agent workflows. LLM-agnostic, CLI-agnostic, self-hostable. TypeScript + SQLite.
🛠️ 使用 Sherlock AI Plugin 将研究论文转化为可执行代码,是你高效进行文献综述与实现工作的必备工具。🛠️ Transform research papers into executable code with Sherlock AI Plugin, your essential tool for efficient literature review and implementation.
A field-adaptive academic writing Skill for Chinese and English research papers. | 面向中英文学术论文的领域自适应写作 Skill。
用于生成基于 Transformer 的 LLM 完整注意力头热力图的一组脚本。A set of scripts to generate full attention-head heatmaps for transformer-based LLMs
对 CPI(消费者价格指数)与工资差距趋势的统计分析,涵盖数据探索、可视化及基于 R 的计量经济学方法。包含对既有研究的回顾以及可复现的扩展分析工作流。Statistical analysis of CPI (Consumer Price Index) and wage disparity trends, combining data exploration, visualization, and R-based econometric methods. Includes a review of prior research and a reproducible workflow for extending the analysis.
可复现研究代码:检验足球预测优势是否依赖于博彩公司去水方法。Reproducible research code testing whether football forecasting edges depend on bookmaker de-margining methods.
本地 LaTeX 项目与 Overleaf 之间可靠的双向同步。Reliable bidirectional synchronization between local LaTeX projects and Overleaf
让研究资源更易于查找、复用与共享,记录可复现研究的资产。(镜像)Making research resources easy to find, reuse, and share, documenting assets for reproducible research. (Mirror)