#workflow

Project memory system for AI coding assistants (Claude Code, Cursor, Codex): session logs, project wiki, rules, TODOs, and handoff.

Skillscript — a small declarative language for authoring agent workflows. Runtime, compiler, and CLI.

🔨Reusable personal Agent Skills and practice-backed Q&A for AI Agent engineering, runtime reliability, multi-agent systems, evaluation, and AI-native frontend.

Visualize Claude Code dynamic workflows from your terminal — a fan-out→barrier→reduce DAG, a gantt timeline, live concurrency, and a self-contained interactive HTML report. Zero runtime deps.

Open-source AI research workspace built with Electron and FastAPI, featuring provider-neutral agent workflows for DeepSeek, GLM, and other OpenAI-compatible models.

Workflow-first, AI-ready iOS architecture with typed effects, manifests, SwiftUI/UIKit examples, and agent-safe code generation.

本地多运行时 Agent 工作台：围绕材料研究、生成可编辑报告、独立复核、追溯证据，并从人工反馈持续学习。

Dispatch is a board for Obsidian that gives a small agent-native team a working process: skills that run through the wiki and the team chat, and a chip on every card that sends an agent at the work.

A thin, structured workflow for shipping features with Claude Code. Not a full-blown framework like GSD or bmad-method. Just a wrapper around Claude Code's own built-in commands (/batch, /goal, /model, /security-review) that adds structure, quality gates, and optional GitHub issue tracking so nothing falls through the cracks.

🗼 An orchestrator skill for Claude Code: describe a task in plain language — Manara picks the stage, routes to the right skills, keeps guards blocking, and resumes across context clears.

Recoverable engineering workflows for coding agents: issue claims, mission lists, validation, and delivery across eight runtimes and GitHub, GitLab, and Gitea. Pairs with Kaola Project Runner for cross-runtime collaboration.

三个实战验证的Claude Code Skill：会话交接、CLAUDE.md 生成、事前否决审计

Host-neutral durable DAG workflows for Agents: CLI-native access, fixed MCP gateway, on-demand Skills, triggers, replay, and visual Canvas.

Claude Code plugin marketplace: opinionated workflows for code (dev-workflow — Rails & Python, TDD + pre-commit gate) and non-code (craft-workflow — design, content, research).

Cursor Agent workflow template with role definitions, TDD/SMART/MVP rules, Symphony-ready SOPs, and Git/PR handoff standards.

本地自架的視覺化 workflow 自動化平台，用白話跟 AI 建立、修改、修復流程 (local-first AI workflow automation, powered by loop engineering not model intelligence)

GENESIS - a project operating system for Claude Code: prep protocol, per-project registries, and seven enforced gates

Environment-adaptive orchestration skill for AI agents.

Workflow harness for Pi coding agent

Agent-safe action and workflow runner for TypeScript backends.

🚀 Master Claude Code Skills 2026: AI-Powered PR Reviews & Security Audits

Your Ultimate Claude Skills Library & Hub 2026 – Integrate & Organize AI Workflows

A Hermes Agent skill for turning painful fixes into replayable benchmarked workflows

A community-driven collection of reusable AI Agent workflow loops. 大家以前分享 Prompt，这里分享 Agent 怎么循环干活。

AI Travel Planner Agent built with Dify, LLM and RAG for executable travel planning

Vocational education AI agent | Dify workflow + RAG for printing industry training.

Agent-first 百度网盘影视资源搜索、转存与安全整理工作流

面向专业内容制作的多 Agent 协作框架：超强 Planner 主 Agent 规划 + 长内容一致性骨架，网文·漫画·漫剧·音乐

Personal open-source collection of Claude Code plugins & skills — starting with dev-flow, a resumable multi-phase / multi-PR engineering flow.

AI-powered executive customer briefing workflow built in n8n using Tavily and OpenAI.

AI-powered document processing workflow using Microsoft 365, SharePoint, Power Automate, Azure OpenAI and Microsoft Teams.

Portable, auditable, coverage-honest dev lifecycle plugin — spec→plan→build→review→test→merge with reviewer/QA handoff docs. Runs on Claude Code & Cursor.

Planner-led local agent workflow workbench with structured handoffs and hidden runtime graph.

Small, configurable workflow checks at coding-agent lifecycle events. Local-first, zero runtime dependencies, no network requests, silent until checks are explicitly enabled.

A suite of Claude Code skills that keep a project's record, roadmap, docs and tooling honest — a secretary to coding, not the coder.

以规范文档驱动的 AI 开发工作流 Skill 集：决策由人确认，事实由 AI 查证，从项目规划到功能落地全程可追溯

The Universal Full-Stack AI Developer & Autonomous Agentic Workflow Framework. Features 2-stage gated onboarding (/project), UI/UX design intelligence, fluid spring animations, 24 technical SEO skills, and OWASP defensive security for Antigravity, Claude Code & Cursor.

Barid (بريد): a prompt relay board for people who run several AI agent sessions. Order, dependencies, shared resources, file conflicts, handoff between agents, browser panel. Agent skill, zero-dependency Python.

An AI powered enquiry automation for Sapoholic Labs built with n8n, OpenAI, Google Forms, Google Sheets, Gmail and Telegram.

Rust-first AiPlus CLI for project-local AI-agent workflow kits