forztf avatar

Openspec Implementation Cn

This is a Chinese language skill for systematically implementing approved OpenSpec proposals through a test-driven, task-by-task workflow. It's designed for when you've already got a spec proposal ready and need to execute it methodically. The approach is strict about sequence: read the full proposal, load tasks into TodoWrite for progress tracking, execute each task individually with immediate testing, and only mark complete after verification passes. It explicitly warns against skipping tasks or batching work without testing. The workflow handles common scenarios like database migrations before API code, blocked tasks, and breaking changes with versioning. If you're the type who shortcuts testing until the end, this will slow you down on purpose, which is probably the point.

skills.sh installs
384
GitHub stars
10
last updated
Aug 21, 2026

Install

$ npx -y skills add forztf/open-skilled-sdd --skill openspec-implementation-cn --agent claude-code

Installs into .claude/skills of the current project.

Files

规范实施

以任务为单位,循序执行并进行充分测试与验证,系统性地实现已批准的规范提案。

快速开始

实施遵循每个任务的 读 → 执行 → 测试 → 验证 循环:

  1. 阅读完整提案与任务清单
  2. 按顺序逐个执行任务
  3. 为每个完成的任务进行测试
  4. 仅在验证通过后标记完成

关键规则:使用 TodoWrite 跟踪进度。切勿跳过任务或将未完成工作标记为完成。

工作流

复制此清单并跟踪进度:

开发进度:
- [ ] 第 1 步:加载并理解提案
- [ ] 第 2 步:设置 TodoWrite 任务跟踪
- [ ] 第 3 步:按序执行任务
- [ ] 第 4 步:为每个任务进行测试与验证
- [ ] 第 5 步:更新常驻规范(如果适用)
- [ ] 第 6 步:标记提案为实施完成

第 1 步:加载并理解提案

开始之前,读取全部上下文:

# 读取提案
cat spec/changes/{change-id}/proposal.md

# 读取所有任务
cat spec/changes/{change-id}/tasks.json

# 读取规范差异以理解需求
find spec/changes/{change-id}/specs -name "*.md" -exec cat {} \;

理解:

  • 变更的动因(来自 proposal.md)
  • 预期结果是什么
  • 哪些规范将被影响
  • 验收标准(来自场景)

第 2 步:设置 TodoWrite 进行任务跟踪

在开始工作之前,将 tasks.json 中的task和step加载到 TodoWrite:

**模式**:
读取 tasks.json → 提取task和step列表 → 创建 TodoWrite 条目

Sponsors

Details

Repository
github.com/forztf/open-skilled-sdd
First seen
Jun 3, 2026

More from forztf/open-skilled-sdd

All 16

Recommended

1juliusbrussee avatarcavemanjuliusbrussee/cavemanUltra-compressed communication mode. Cuts output tokens 65% (measured) by speaking like caveman while keeping full technical accuracy. Supports intensity levels618.3Kskills.sh installs
2mattpocock avatargrill-memattpocock/skillsA relentless interview to sharpen a plan or design.1.5Mskills.sh installs
3shadcn avatarimproveshadcn/improveSurvey any codebase as a senior advisor and produce prioritized, self-contained implementation plans for OTHER models/agents to execute. Strictly read-only on s40Kskills.sh installs
4obra avatarsystematic-debuggingobra/superpowersUse when encountering any bug, test failure, or unexpected behavior, before proposing fixes326.7Kskills.sh installs
5forrestchang avatarkarpathy-guidelinesforrestchang/andrej-karpathy-skillsBehavioral guidelines to reduce common LLM coding mistakes through explicit assumptions, simplicity, and verifiable success criteria.17.9Kskills.sh installs
6vercel-labs avatarfind-skillsvercel-labs/skillsHelps users discover and install agent skills when they ask questions like "how do I do X", "find a skill for X", "is there a skill that can...", or express int4.3Mskills.sh installs