面向 AI 代理时代的软件意图开放标准。
speckit 开源项目推荐(105 个)
speckit 话题在 GitHub 上没有填写简介,这里按 Star 数汇总最相关的热门仓库。
热门项目 前 20
按 Star 数排序展示前 20 个 · GitHub 共 105 个仓库用于简化规范驱动开发的 CLI
Vision/Mission https://ambient-code.ai : Virtual team management and collaboration platform. User guides: https://ambient-code.github.io/platform/
A Claude Code Skill that manages GitHub SpecKit updates.
Spec-kit中文支持,包含所有原版功能,新增fixbug模板。
Orchestrate a full feature lifecycle with human-in-the-loop gates across all SpecKit phases
A comprehensive, evidence-based comparison of state-of-art techniques, methodologies, and frameworks for structured AI-assisted software development
Repository-native persistent memory hub for Spec Kit, powered by an SQLite caching optimizer & native Model Context Protocol (MCP) server.
A Spec Kit extension that enables modular composition of project constitutions
Набор скиллов для AI-агентов, который делает работу с ними удобнее, проще и эффективнее
Agent-agnostic GitHub SpecKit extension that grounds spec, plan & task generation in Figma design context - REST + optional MCP, with single/mono/multi-repo support.
Constitution: Spec‑Driven Development for WordPress Projects
Win32/DirectX C++ Matrix-rain screensaver + desktop app with configurable density/colors/glow
Turn GitHub Copilot into a coordinated engineering team — specification-driven development lifecycle with quality gates, persistent memory, and human-in-the-loop governance
Spec‑driven GTM execution for AI/LLM SaaS. Systematic sales, marketing, and go‑to‑market workflows with AI agents. Built on Spec‑Kit
A thorough alternative to /speckit-clarify for identifying and resolving ambiguities in feature specifications.
Governed handoff and evidence verification for AI coding agents.
🎼 Spec-Driven Orchestra: SDD is the framework that conducts five skills it calls (Karpathy 4 Principles, grill-me, Verification Design, Handoff, Harness), backed by enforcement gates. Universal — new, legacy, or production. Built for Claude Code.
A Spec Kit extension that collects performance metrics, execution times, and human-time-saved estimates seamlessly in the background
Harness engineering for AI coding agents. Guides steer the agent before it acts, sensors catch what it got wrong after: a project constitution and concern catalogs, 12 read-only review agents, a 12-gate commit chain, and loop closure that blocks commits lacking closure evidence.
关于这个话题
- 清单取自 GitHub 话题页并按 Star 数排序,每次展示前 20 个项目;原始页面见 https://github.com/topics/speckit。
- 该话题在 GitHub 上共有 105 个仓库, 本站收录的是其中最热门的 20 个,不是全量列表。
- Star / Fork 每日自动刷新一次,实时数据以 GitHub 为准。
- 当前 20 个项目累计 785 Star,覆盖 7 种主要语言,数据更新于 2026-11-08。
- 中文介绍来自 GitHub 官方话题说明(github/explore)的机器翻译,可点「查看原文」对照;译文缺失时会先展示原文。