仓库/Skill 库

基于确定性状态机的无头 Agent 编排器——处理 bead 队列，分派至任意 LLM CLI，覆盖所有结果分支。Rust 实现。Headless agent orchestrator with deterministic state machine — processes a bead queue, dispatches to any LLM CLI, handles every outcome. Rust.

紧凑型 Codex skill，涵盖比例化编码、测试、ML 验证与学术写作。A compact Codex skill for proportional coding, testing, ML validation, and academic writing.

用于创建你自己的文献综述引擎的模板。A template to create your own literature survey engine

持久化的多 agent 工作流编排——DAG 任务、git worktree、merge gate，兼具桌面端 + CLI + Slack。Persisted multi-agent workflow orchestration — DAG tasks, git worktrees, merge gates, desktop + CLI + Slack

🦙 使用 Ollama CLI 配置 GitHub Actions。🦙 Set up GitHub Actions with Ollama CLI.

面向 AI 编码工具的桌面端聚焦型 Provider 管理器与路由器A focused desktop provider manager and router for AI coding tools.

面向 Claude Code 的零幻觉参考验证——实时 CrossRef/S2/PubMed 校验、摘要逐字溯源、撤稿检查。Zero-hallucination reference verification for Claude Code — live CrossRef/S2/PubMed verification, verbatim abstract traceability, retraction check

在一个终端驾驶舱内跨所有仓库调度 Claude Code 会话集群——分派任务、观察交付、对阻塞项即时响应。Terminal cockpit for running a fleet of Claude Code sessions across all your repos — dispatch work, watch what ships, and act on what's blocked, from one screen.

每日 LLM 价值排行榜——基于智能、速度、价格对比 300+ 模型。OpenRouter + Artificial Analysis。大模型性价比排行榜Daily LLM value rankings - compare 300+ models by intelligence, speed and price. OpenRouter + Artificial Analysis. 大模型性价比排行榜

Memory OS CLI 和 npm 包Memory OS CLI and npm package

原生终端的 LifeOS，可选本地 Web UI，支持任务、笔记、习惯、日程、时间记录、关系与人机协作。Terminal-native LifeOS with an optional local Web UI for tasks, notes, habits, schedules, timelogs, relationships, and human-agent collaboration.

面向 systematic review 和 evidence synthesis 的 AI 驱动全文筛选与数据提取。AI-Driven Full-Text Screening and Data Extraction for Systematic Reviews and Evidence Synthesis

清理、去重并丰富用于系统综述的 RIS 文献格式文件。Clean, deduplicate, and enrich RIS bibliographic files for systematic reviews.

为 MCP agent 提供 policy-as-code：在工具调用执行前拒绝高风险操作，以可验证证据证明实际运行内容，并在内核层面强制出站控制（eBPF/LSM，Linux）。确定性、离线优先、声明有界。Policy-as-code for MCP agents: deny risky tool calls before they run, prove what ran with verifiable evidence, and enforce egress in the kernel (eBPF/LSM, Linux). Deterministic, offline-first, bounded claims.

在 macOS 后台稳定运行 Codex 和 Claude Code — 提供原生 dashboard、持久化 tmux session、本地 checkpoint、恢复、通知和合盖运行支持。Run Codex and Claude Code reliably in the background on macOS—with a native dashboard, persistent tmux sessions, local checkpoints, recovery, notifications, and closed-lid support.

实验性的本地优先 memory CLI，面向 MCP agent：只读访问 Gmail、日历、iMessage 与文件 → 输出带引用的本地上下文。Experimental local-first memory CLI for MCP agents: read-only Gmail, calendars, iMessage, and files → cited local context

Numbat Systematic Review ManagerNumbat Systematic Review Manager

Claude Code Skill：为经济学与人口学研究者推荐学术期刊。Claude Code Skill: academic journal recommendation for Economics & Demography researchers

科学文档的确定性 linterDeterministic linter for scientific docs

Claude Code 与 Codex 的质量门控式自主任务闭环（规划、执行、评审、打分、迭代）。Quality-gated autonomous mission completion loop for Claude Code and Codex (plan, execute, review, score, iterate).

Remyx AI 的 CLI：安装 Outrider，管理研究兴趣，浏览论文推荐。CLI for Remyx AI: install Outrider, manage research interests, browse paper recommendations

💻 在 macOS 上借助 Metal GPU 实现 Qwen3 Transformer 模型，获得加速且高效的性能，并支持关键架构特性💻 Implement Qwen3 transformer model on macOS using Metal GPU for accelerated, efficient performance with support for key architecture features.

🧪 Cypress AI 命令，通过 LLM（大语言模型）生成 E2E 测试🧪 Cypress AI command that generates E2E tests with LLM (Large Language Model).

📄 自动从 PDF 中提取 BibTeX 条目，无需手动输入或调用外部 API 即可生成完整参考文献列表。📄 Extract BibTeX entries from PDFs automatically, generating a complete bibliography without manual input or reliance on external APIs.

面向 LLM Agent 的本地优先上下文引擎——在检索路径上无需 LLM 调用即可检索、权衡并压缩代码库到上下文窗口。采用 SQLite 知识存储，支持 CLI + HTTP + MCP，提供 know/miss Agent 契约。Local-first context engine for LLM agents — retrieves, weighs, and compresses your codebase into the context window with no LLM call on the retrieval path. SQLite knowledge store; CLI + HTTP + MCP; know/miss agent contract.

论文 PDF 知识提取与学术写作 — Claude Code PluginPaper PDF Knowledge Extraction and Academic Writing – Claude Code Plugin

自动跟踪、下载并分析 HuggingFace 上的 AI 论文，轻松掌握前沿研究 🐙📄Automate the tracking, downloading, and analysis of AI papers from HuggingFace. Stay updated with cutting-edge research effortlessly! 🐙📄

DebugBundle 产品源码与运行时代码。DebugBundle product source and runtime code.

Codex 的主题画廊、预览器、构建器与社区。The theme gallery, previewer, builder, and community for Codex.

面向中小企业的 AI 运营层。将 Telegram、WhatsApp、Slack、Discord、GitLab、cron、webhook 以及 mesh 任务路由到基于 Claude、OpenAI 或任意 LLM 的 AI agent。非技术运营者使用 Web 向导，工程师使用 CLI。支持自托管。AI operations layer for small & medium businesses. Route Telegram, WhatsApp, Slack, Discord, GitLab, crons, webhooks, and mesh tasks to AI agents on Claude, OpenAI, or any LLM. Web wizard for non-technical operators, CLI for engineers. Self-hosted.

系统性文献综述辅助工具，可基于预定义标注体系对一组论文进行标注。A tool that helps in Systematic Literature Review for annotating a set of papers based on a defined annotation schema

自动检查 BibTeX .bib 文件的样式规范性（借助 CTAN 的 bibcop）Automated checking of BibTeX .bib files for style correctness (with the help of bibcop from CTAN)

Jaz 的完整 agent 技术栈。包含插件、Skills、MCP 工具和 CLI，支持 Claude Code、Cowork、Codex、Copilot、Cursor 等。Complete agent stack for Jaz. Plugins, Skills, MCP tools, and CLI for Claude Code, Cowork, Codex, Copilot, Cursor, and more.

自维护的 API 集成——监控代码所调用的第三方 API，在出现故障、漂移或浪费资金时自动提交经 CI 验证的 pull request。Self-maintaining API integrations — watches the third-party APIs your code calls and opens CI-verified pull requests when one breaks, drifts, or wastes money.

Claude Code 学术研究防幻觉插件。严格 FSM + 10 源 PDF 级联 + 首页防同名歧义 + 19 条不变量 + 每条引用审计。与 Vault 解耦（Obsidian/扁平目录/Zotero）。MIT 许可。Anti-hallucination plugin for academic research in Claude Code. Strict FSM + 10-source PDF cascade + page 1 anti-homonymy + 19 invariants + per-citation audit. Vault-agnostic (Obsidian/flat/Zotero). MIT.

为 AI 编码 Agent 提供调用图上下文——展示调用者、测试与 blast radius，让 Agent 安全地变更代码。CLI 与 MCP。MIT 许可。Call-graph context for AI coding agents — surfaces callers, tests, and blast radius so agents make changes safely. CLI and MCP. MIT.