— · MIT
AI agent 通用任务治理框架:对齐目标与事实,规划和调度能力,守住授权与风险边界,治理任务执行到真实验收与交付。Governance framework for evidence-driven planning, orchestration, and verified delivery.
— · Apache-2.0
One portable memory layer for every AI agent: local-first, Markdown-native, user-owned, and self-evolving across apps, tools, and workflows.
— · Apache-2.0
Self-evolving memory OS for LLM & AI Agents: ultra-persistent memory, hybrid-retrieval, and cross-task skill reuse, with 35.24% token savings and DeepSeek Harness support.
v5.4.2 · MIT
HEDGEHOG codes Cleaner, Faster and with Fewer Tokens. Hedgehog's AI-driven development builds a task dependency graph from your spec-driven, BMAD-METHOD plan, so Claude Code, Cursor & Gemini CLI stay locked to it. A CLI-enforced state machine for agentic coding. Now builds DeepSeek DSH Plugins. DeepSeek Harness、DSH 插件、AI 编程、BMAD 方法
— · MIT
A persistent, unified memory layer for all your AI agents (e.g. Claude Code, Codex, DSH), backed by Markdown and Milvus.
v3.1.0 · MIT
Reverse engineer anything with agents, from app behavior down to native binaries.
v3.1.9 · no license
一个自主的高级智能伙伴,不仅分析问题,更持续工作直到完成实现和验证。
— · MIT
为纯文本模型"看图“设计更好的视觉工具箱和技能,支持多图理解,图片问答,前端UI还原、GUI 自动化等,并可选无缝接入多个主流agent,直接识别粘贴图片| A vision toolkit and skill designed for text-only llms — image Q&A, long-screenshot OCR, frontend UI restoration, and GUI automation, with optional seamless integration for Codex, Claude Code, Pi, Oh My Pi, and OpenCode
v0.1.0 · MIT
Open-source macOS record-and-replay workflow recorder for computer use agents. Captures mouse, keyboard, and UI events as structured traces so agents can learn, replay, and automate real desktop tasks.
— · MIT
Precision PPT design skill for OpenCode/Claude Code/Codex, with 40,000+ styles, pixel-perfect build-mode control, and AI image generation
— · Apache-2.0
The fastest way to put Volcengine Ark in your terminal and your AI agent — go from prompt to generated media, multimodal answer, or deployed endpoint in a single command, no API glue code.
— · Apache-2.0
Open-source infrastructure that turns scattered SKILL.md files into curated, retrieval-ready agent-skill corpora—with retrieval and evaluation tooling included.
— · MIT
Скилл для ИИ-агентов: находит и убирает следы машинной генерации из русского текста. 38 паттернов, 39 regex-маркеров с реестром доказательств, слепые парные прогоны, файловый слой снятия C2PA/EXIF/XMP. Пакет на PyPI и онлайн-демо | Russian AI-writing humanizer skill, PyPI: humanizer-ru, live demo
— · BSD-3-Clause
帮 DSH 搜索、安装并验证插件的 Skill|A DSH skill that finds, installs, and verifies GitHub plugins
— · no license
last30days-cn 是一个 AI Agent 技能(Skill),能够自动搜索中国互联网 8 大主流平台最近 30 天的内容,综合分析后生成有据可查的研究报告。
— · no license
No description yet.
— · MIT
Codex Switch 是一个 macOS 工具,一键配置 Codex 的自定义 API,同时保留官方 OpenAI 登录。保存后 Codex 的模型选择器里只会出现你选的那个 provider 的模型。也支持 Claude Code 的官方 / 自定义 API 切换。Codex Switch is a lightweight helper for configuring multiple coding-agent API routes. For Codex, it keeps Official OpenAI and a custom API provider configured in parallel, registers the custom model in Codex's mod
— · no license
✨ All your agents and workspaces in one place, on every device you own. Track tasks on a board, accessible from desktop, mobile, browser, or API. Self-hosted.
— · Apache-2.0
Resource-aware multi-agent orchestration for Codex and DeepSeek Harness (All in Flash DSH plugin)
— · MIT
把法律画出来 · Make the Law Visible —— 给法律人的诉讼可视化工具集:把凌乱的诉讼图重画成能进材料的图,或直接读案件材料画准一张时间轴。Claude Skill / DeepSeek Harness 通用。
— · MIT
Know if your agent skill actually works. A lightweight evaluation harness that tracks a success rate across Claude Code, Codex, Pi, and Hermes.
— · no license
幻银量化A股阿法狗AlphaHYQi,100%由ai自主驱动的实盘交易机器。接入自产龙虾iClaw,手机端一句话控制四大模型同时干活。获取方法:前往https://hyqibot.com/card-shop.html 购服务卡即可获得软件,详情README.md。 A股Ai炒股大赛历史排行(模拟基金):https://hyqibot.github.io/A-share-Ai/reports/report.html A股Ai炒股大赛历史排行(全市场):https://hyqibot.github.io/A-share-Ai/reportsall/report.html 实时播报:https://hyqibot.github.io/A-share-Ai
— · MIT
Portable Agent Skill for repository-native Spec programming, informed by public DeepSeek Harness engineering patterns.
— · no license
DeepSeek V4 × J-Space capability realization report — benchmark evidence that J-Space reduces capability-realization loss on DeepSeek V4.