菜单
Use OpenSpec for specification-driven development. Apply when planning features, implementing changes, or managing project deliverables.
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
基于 SOC 职业分类
| name | openspec-workflow |
| description | Use OpenSpec for specification-driven development. Apply when planning features, implementing changes, or managing project deliverables. |
OpenSpec ensures AI agents build what was planned, not what they invented.
project/
└── openspec/
├── specs/ # Source of truth (what IS built)
├── changes/ # Proposals & WIP (what SHOULD change)
├── ideas/ # Quick-capture for later
└── project.md # Project conventions
Create a change proposal before implementing anything significant.
openspec/changes/add-feature-x/
├── proposal.md # What and why
├── tasks.md # Numbered implementation steps
├── design.md # Technical approach
└── specs/ # Delta specs (what will change)
Work through tasks.md sequentially. Keep specs in sync with code.
When complete: openspec archive <change-id>
Specs merge to source of truth. Change moves to archive.
# List all changes
openspec list
# Show specific change details
openspec show <change-id>
# Validate a change
openspec validate <change-id> --strict
# Archive completed change
openspec archive <change-id> --yes
# List specs
openspec spec list --long
proposal.md format:
# Feature Name
## Summary
One paragraph: what this change does.
## Motivation
Why we need this. What problem it solves.
## Scope
- What's included
- What's explicitly NOT included
## Dependencies
- Other changes this depends on
- External requirements
tasks.md format:
# Implementation Tasks
## Phase 1: Foundation
- [ ] Task 1.1: Description
- [ ] Task 1.2: Description
## Phase 2: Core Implementation
- [ ] Task 2.1: Description
...
openspec validate --strict must passYES - Use OpenSpec for:
NO - Skip OpenSpec for:
OpenSpec tracks WHAT gets built. megg tracks WHY decisions were made.
Use both:
Before marking a change complete:
openspec validate --strict passesRead Claude Code documentation to learn about features, capabilities, hooks, skills, MCP, subagents, and how to use Claude Code effectively.
Close a dev-cycle session, capture learnings, and optionally commit. Use when development work is complete and ready to wrap up.
Fully autonomous development mode. Spec in, production-ready software out. Claude makes decisions, uses agents, commits locally. Only stops for hard blockers.
Run QA checks on current work. Tests, linting, type checking, build verification. Use during or after development to catch issues early.
Release candidate preparation. Final checks before merge - QA, security, review, changelog. The last gate before shipping.
Security audit with Sentinel. Checks for vulnerabilities, secrets, dependencies, and security best practices. Use before shipping or when working on auth/crypto/sensitive areas.