Openspec Agent Sdd

Use when an autonomous coding agent (no human in the loop) needs to drive OpenSpec spec-driven development end-to-end — bootstrap, propose, implement, and archive a change without slash commands or interactive prompts. Triggers on "用 openspec 自主开发", "agent-own spec-driven dev", "openspec 无人值守 / 非交互", "spec-driven 自动跑一遍", "openspec init/propose/apply/archive 全自动", "drive OpenSpec from an agent". Captures the verified non-interactive CLI loop, the status/instructions state machine, the substitutions for OpenSpec's built-in "ask the user" stops, and validation-driven self-correction.

7 starsAI, LLMs & Agents

Install

skills CLI (Claude Code, Cursor, Codex and more)

npx skills add trotsky1997/openspec-agent-sdd --skill openspec-agent-sdd

Manual install

git clone --depth 1 https://github.com/trotsky1997/openspec-agent-sdd.git /tmp/openspec-agent-sdd
mkdir -p ~/.claude/skills
cp -r /tmp/openspec-agent-sdd/. ~/.claude/skills/openspec-agent-sdd

Personal skills live in ~/.claude/skills. Use .claude/skills in a project folder to share a skill with your team.

From the SKILL.md

# OpenSpec Agent-Own Spec-Driven Development

Drive [OpenSpec](https://github.com/Fission-AI/OpenSpec) (`@fission-ai/openspec`) from an autonomous agent, with **no human in the loop and no slash commands**. OpenSpec's `/opsx:*` slash commands are not features for humans — they are procedural scripts written *for an agent* (they live in `.claude/commands/opsx/*.md` and `.claude/skills/openspec-*/SKILL.md` after init). An agent can skip them and call the underlying CLI directly, because the CLI is `--json`-first: **its first consumer is an agent, not a person.**

This skill is the distilled, hands-on-verified loop (tested against openspec 1.3.1, Node 22). Everything below was confirmed by actually running it, not just reading docs.

## Mental model: the CLI is a state machine

- `openspec status --change <name> --json` is the **state machine**: it returns each artifact's `status` (`ready` / `blocked` / `done`), its `missingDeps`, and `applyRequires` (the artifacts that must be `done` before implementation).
- `openspec instructions <artifact|apply> --change <name> --json` is the **per-step instruction source**: it tells you what to read (`dependencies` / `contextFiles`), what to write (`template`, `instruction`), and where (`resolvedOutputPath` / `outputPath`).
- `openspec validate --strict` is the **self-correction oracle**: errors are precise and machine-actionable (e.g. `ADDED "X" must include at least one scenario`), so the agent fixes and retries instead of stopping.

Read the full skill on GitHub

Details

Skill name: openspec-agent-sdd
Repository: trotsky1997/openspec-agent-sdd
License: MIT
Repo updated: 6 June 2026

FAQ

What does the Openspec Agent Sdd skill do?

How do I install the Openspec Agent Sdd skill?

skills CLI (Claude Code, Cursor, Codex and more): npx skills add trotsky1997/openspec-agent-sdd --skill openspec-agent-sdd. Skills go in ~/.claude/skills (personal) or .claude/skills (project), and Claude loads them automatically when a task matches the description.

Is Openspec Agent Sdd popular?

It lives in trotsky1997/openspec-agent-sdd, which has 7 GitHub stars and 0 forks.

Related skills

Pelago

Mikebouskila/pelago

Make an AI coding Wrapped from local Claude Code and Codex history. Turns every project into a pixel-art island and adds a story-style recap, a coding archetype such as "The Midnight Harbormaster", relics, shareable cards and a short video reel, all in one offline HTML page. Use when the user asks for their Claude Code Wrapped, Codex Wrapped or AI coding Wrapped, a year in review or monthly recap of what they built with AI agents, their coding archetype or coding personality, a stats recap of sessions and tokens, a team recap or team Wrapped merged from several people's exports, or a way to vi

AI, LLMs & Agents

Mggu

transicle/MGGU-LLM-NoCode-Prompt

Cut off AI code generation entirely, instead explain the how and why.

AI, LLMs & Agents

Prompt Engineering Expert

S3LabsAI/prompt-engineering-expert

Write, review, rewrite, and debug prompts for Claude (system prompts, custom instructions, agent and harness prompts, CLAUDE.md files, one-off task prompts), tuned to the model that will run them. Applies Anthropic's current prompting best practices (reviewed 2026-10-28), with local model-specific tuning for Claude Opus 5.5 and Claude Fable 5.1 / Mythos 5.1, per-model notes and docs lookups for Sonnet 5.5, Sonnet 5, Haiku 5.5, Opus 5, Opus 4.8, and Fable 5, and general guidance for every other model. Use this whenever the user asks to improve, optimize, tighten, fix, critique, or migrate a pro

AI, LLMs & Agents

Kandong

jeszhou/kandong-skill

看懂 AI 的长回答：把一大段文字做成先看全局、再点开细节的 HTML 页面。用于：用户说「看不懂」「太长了」「出 HTML」；你刚写完一段很长的回答（超过约 800 字，或有 3 个以上读者不熟的概念）；用户要把看懂页面存进知识库时。

AI, LLMs & Agents

Reelwright

janieehe/reelwright

面向旅拍店、妆造店、民宿，以及独立摄影师、独立妆造师等本地生活内容生产者，系统产出可直接开拍的短视频内容。覆盖拆解爆款、商家档案、客群画像、账号定位、内容矩阵、选题清单、脚本、分镜表、拍摄方案九个方向，每个方向都能单独用、也能串成一条从对标到开拍的线，台词/旁白去 AI 味、逐字可念。当创作者或自媒体人想拍短视频、起号、规划账号或选题、写脚本或改稿、拆分镜、排拍摄方案，或拆解对标视频/评论区、把爆款拍法换成自己的店（换皮）时使用。

AI, LLMs & Agents

Imclaw

OpenMOSS/imclaw-skill

IMClaw 跨网通信能力 — 让 AI Agent 具备实时聊天能力。用于：(1) Agent 需要与其他 Agent 实时通信，(2) 管理群聊，(3) 订阅和接收群聊消息，(4) 构建聊天机器人或协作 Agent。触发词：imclaw、跨网通信、agent 聊天、群聊、实时消息、龙虾。

AI, LLMs & Agents

Browse the most popular Claude skills, all ai, llms & agents skills, or write your own with the skills generator.