Idea-to-store harness for Flutter/Flame games

88 installable open-source Agent Skills for research, social intelligence, marketing, and business workflows—compatible with Codex, Claude Code, Cursor, Gemini CLI, and DeepSeek Harness.

Prompt as Code | GPT-Image2 工业级提示词引擎与模板库，530+ 个案例逆向工程，20+ 套工业级模板，并提炼出Skills，持续更新中

管线管理内核（pipeline-kernel）：单向任务链的任务板/台账/注册表/巡检/播种/打包/自愈。v0.9.0：rc.8 削薄工程（依赖对齐 rc.8、DshAgentRuntime 窄收口、webServer inject、domain/changed 统一失效、契约测试、CI 全量门禁；业务语义与入口冻结）。

TongFlow — Multimodal GenAI Studio

SRE thinking applied to Claude Code, based on Boris Cherny's Q&A. It enforces a strict 4-stage pipeline with gates between each step. You literally cannot skip verification. You cannot ship without approval.

Text-first browser & background macOS control for DeepSeek Harness (DSH): target the right process and window without taking the user's pointer. 为 DSH 提供文本优先的电脑控制：后台操作 Chromium 与 macOS，不抢前台、不移动鼠标。

为 DeepSeek Harness 提供电脑控制插件：新鲜 Accessibility 观测、过期状态拒绝、作用域权限与安全输入（目前支持macos）｜Accessibility-first macOS Computer Use bundle for DSH with fresh observations, stale-state rejection, scoped permissions, and safe input.

DSH（DeepSeek Harness）插件：把 ego-lite 浏览器（给 AI Agent 用的 Chromium）接入 HARNESS——13 个结构化 ego_* 工具（文本语义快照、语义定位点击、表单填充、截图、CDP 控制、任务空间隔离），内置 ego 运行时，Linux + Chrome 开箱即用，无需克隆官方仓库或手动构建。

Multi-agent mathematical problem-solving & verification frameworks for DeepSeek Harness — TWO agent presets in one install: vibe-math-v1 (classic pipeline: brainstorm → solver iteration → multi-verifier debate → Verified) and vibe-math-v2 (new probability

One macOS app for Claude Code, Codex, and every agent runtime you use — scheduled runs, global hotkey launcher, per-run git worktrees, one review board.

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.

The framework that powers your Agentic Company

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.

Runtime guardrails for Claude Code. Auto-approve what's safe, gate what's risky, block what's dangerous. Dual enforcement, full audit trail. MIT.

The batteries-included, No-Code FinOps automation platform, with the AI you trust.

ERPAVal — autonomous software development. Six-phase Explore/Research/Plan/Act/Validate/Compound workflow with classifier-driven routing and a compounding lessons store.

DeepSeek Harness 插件:数学建模论文自动化流水线 v2(8 步骤 × 19 迭代 × N 轮:图表视觉自检与修复、评审问题修复闭环、跨步骤缺陷台账与向上修复、论文兜底定稿、质疑驱动、断点续跑、进度面板)

Open-source alternative to Claude Cowork — a local-first AI agent desktop app · multi-model · self-evolving skills · privacy-first · multi-Harness roadmap · DeepSeek Harness integration in progress

AI-native task management for Claude Code. Track tasks in MASTER_PLAN.md — pick, save, ship.

Sync your local skills across 41+ AI coding agents with a single command.

Lightweight agent orchestration dev tool that lives in your repo

One command to cut token usage by up to 50%+

One capabilities.yaml wires skills, tools, rules, sub-agents, MCP servers, and plugins into Cursor, Claude Code, Codex, Windsurf, GitHub Copilot, and 30+ other AI coding agents