openspec-apply-change
Manages the execution of implementation tasks within an OpenSpec workflow.
Install
mkdir -p .claude/skills/openspec-apply-change && curl -L -o skill.zip "https://agentskills.codes/api/skills/download/1677" && unzip -o skill.zip -d .claude/skills/openspec-apply-change && rm skill.zipInstalls to .claude/skills/openspec-apply-change
Activation
This is the description your AI agent reads to decide when to run this skill — the better it matches your request, the more reliably it fires.
实现 OpenSpec 变更中的任务。当用户想要开始实现、继续实现或处理任务时使用。Key capabilities
- →Select an OpenSpec change for implementation
- →Check the status of a selected change to understand its schema
- →Obtain application instructions for a change
- →Read context files relevant to the change's schema
- →Display current progress of tasks within a change
- →Implement tasks by making code changes and marking them complete
How it works
The skill guides the user through implementing an OpenSpec change by selecting a change, checking its status, retrieving instructions, reading context files, and iteratively implementing tasks.
Inputs & outputs
When to use openspec-apply-change
- →Implementing tasks in a spec-driven workflow
- →Tracking progress on an active OpenSpec change
- →Managing implementation state for design tasks
About this skill
实现 OpenSpec 变更中的任务。
输入:可选指定变更名称。如果省略,检查是否可以从对话上下文中推断。如果模糊或不明确,你必须提示获取可用变更。
步骤
-
选择变更
如果提供了名称,使用它。否则:
- 如果用户提到了某个变更,从对话上下文中推断
- 如果只存在一个活动变更,自动选择
- 如果不明确,运行
openspec list --json获取可用变更,并使用 AskUserQuestion tool 让用户选择
始终宣布:“正在使用变更:<name>”以及如何覆盖(例如,
/opsx:apply <other>)。 -
检查状态以了解 Schema
openspec-cn status --change "<name>" --json解析 JSON 以了解:
schemaName:正在使用的工作流(例如:"spec-driven")- 哪个产出物包含任务(对于 spec-driven 通常是 "tasks",检查其他产出物的状态)
-
获取应用指令
openspec-cn instructions apply --change "<name>" --json这返回:
- 上下文文件路径(因 Schema 而异 - 可能是 proposal/specs/design/tasks 或 spec/tests/implementation/docs)
- 进度(总计,完成,剩余)
- 带有状态的任务列表
- 基于当前状态的动态指令
处理状态:
- 如果
state: "blocked"(缺少产出物):显示消息,建议使用 openspec-continue-change - 如果
state: "all_done":祝贺,建议归档 - 否则:继续实现
-
阅读上下文文件
阅读 apply instructions 输出中
contextFiles列出的文件。 文件取决于正在使用的 Schema:- spec-driven: proposal, specs, design, tasks
- 其他模式:遵循 CLI 输出中的 contextFiles
-
显示当前进度
显示:
- 正在使用的 Schema
- 进度:"N/M 任务已完成"
- 剩余任务概览
- 来自 CLI 的动态指令
-
实现任务(循环直到完成或受阻)
对于每个待处理任务:
- 显示正在处理哪个任务
- 进行所需的代码更改
- 保持更改最小化且专注
- 在任务文件中标记任务完成:
- [ ]→- [x] - 继续下一个任务
暂停如果:
- 任务不清楚 → 询问澄清
- 实现揭示了设计问题 → 建议更新产出物
- 遇到错误或阻碍 → 报告并等待指导
- 用户中断
-
完成或暂停时,显示状态
显示:
- 本次会话完成的任务
- 总体进度:"N/M 任务已完成"
- 如果全部完成:建议归档
- 如果暂停:解释原因并等待指导
实现期间的输出
## 正在实现:<change-name> (schema: <schema-name>)
正在处理任务 3/7:<task description>
[...正在进行实现...]
✓ 任务完成
正在处理任务 4/7:<task description>
[...正在进行实现...]
✓ 任务完成
完成时的输出
## 实现完成
**变更:** <change-name>
**Schema:** <schema-name>
**进度:** 7/7 任务已完成 ✓
### 本次会话已完成
- [x] 任务 1
- [x] 任务 2
...
所有任务已完成!准备归档此变更。
暂停时的输出(遇到问题)
## 实现暂停
**变更:** <change-name>
**Schema:** <schema-name>
**进度:** 4/7 任务已完成
### 遇到的问题
<问题描述>
**选项:**
1. <选项 1>
2. <选项 2>
3. 其他方法
您想怎么做?
护栏
- 继续执行任务直到完成或受阻
- 开始前始终阅读上下文文件(来自 apply instructions 输出)
- 如果任务模棱两可,暂停并在实现前询问
- 如果实现揭示了问题,暂停并建议更新产出物
- 保持代码更改最小化并限定在每个任务范围内
- 完成每个任务后立即更新任务复选框
- 遇到错误、阻碍或不清楚的需求时暂停 - 不要猜测
- 使用 CLI 输出中的 contextFiles,不要假设特定的文件名
流畅的工作流集成
此技能支持“变更上的操作”模型:
- 可以随时调用:在所有产出物完成之前(如果存在任务),部分实现之后,与其他操作交错
- 允许产出物更新:如果实现揭示了设计问题,建议更新产出物 - 不是阶段锁定的,流畅地工作
When not to use it
- →When the user does not want to start, continue, or process a task
Prerequisites
Limitations
- →The skill pauses if tasks are unclear, implementation reveals design issues, errors are encountered, or the user interrupts.
- →The skill does not guess if requirements are unclear.
How it compares
This skill provides a structured, step-by-step workflow for OpenSpec change implementation, contrasting with a manual approach that lacks guided task processing and status tracking.
Compared to similar skills
openspec-apply-change side by side with the closest alternatives in the catalog.
| Skill | Installs | Updated | Safety | Difficulty |
|---|---|---|---|---|
| openspec-apply-change (this skill) | 6 | 6mo | Review | Intermediate |
| command-development | 16 | 8mo | Review | Intermediate |
| skill-forge | 11 | 9mo | Review | Intermediate |
| codex-skill | 12 | 5mo | Review | Advanced |
Try saying
Example prompts that trigger this skill in your AI assistant.
More by studyzy
View all by studyzy →You might also like
command-development
anthropics
This skill should be used when the user asks to "create a slash command", "add a command", "write a custom command", "define command arguments", "use command frontmatter", "organize commands", "create command with file references", "interactive command", "use AskUserQuestion in command", or needs guidance on slash command structure, YAML frontmatter fields, dynamic arguments, bash execution in commands, user interaction patterns, or command development best practices for Claude Code.
skill-forge
WilliamSaysX
Automated skill creation workshop with intelligent source detection, smart path management, and end-to-end workflow automation. This skill should be used when users want to create a new skill or convert external resources (GitHub repositories, online documentation, or local directories) into a skill. Automatically fetches, organizes, and packages skills with proactive cleanup management.
codex-skill
feiskyer
Use when user asks to leverage codex, gpt-5, or gpt-5.1 to implement something (usually implement a plan or feature designed by Claude). Provides non-interactive automation mode for hands-off task execution without approval prompts.
agent-factory
alirezarezvani
Claude Code agent generation system that creates custom agents and sub-agents with enhanced YAML frontmatter, tool access patterns, and MCP integration support following proven production patterns
subagent-driven-development
davila7
Use when executing implementation plans with independent tasks in the current session
peekaboo
openclaw
Capture and automate macOS UI with the Peekaboo CLI.