auto-trigger

Compare original and translation side by side

🇺🇸

Original

English

🇨🇳

Translation

Chinese

Auto-Trigger Hooks

自动触发钩子

This skill defines automatic trigger relationships between skills. When a skill completes its workflow, it should automatically trigger the next skill in the chain.

该技能定义了技能之间的自动触发关联。当一个技能完成其工作流后，应自动触发链中的下一个技能。

Hook Definitions

钩子定义

PRD Creation Chain

PRD 创建链

yaml

prd_complete:
  triggers:
    - skill: self-improving-agent
      mode: background
      condition: PRD file exists and is complete
    - skill: session-logger
      mode: auto
      context: "PRD created for {feature_name}"

prd_implemented:
  triggers:
    - skill: session-logger
      mode: auto
      context: "Implemented PRD: {feature_name}"

yaml

prd_complete:
  triggers:
    - skill: self-improving-agent
      mode: background
      condition: PRD file exists and is complete
    - skill: session-logger
      mode: auto
      context: "PRD created for {feature_name}"

prd_implemented:
  triggers:
    - skill: session-logger
      mode: auto
      context: "Implemented PRD: {feature_name}"

Implementation Chain

实现链

yaml

implementation_complete:
  triggers:
    - skill: code-reviewer
      mode: ask_first
      message: "Implementation complete. Run code review?"
    - skill: create-pr
      mode: auto
      condition: changes_staged

yaml

implementation_complete:
  triggers:
    - skill: code-reviewer
      mode: ask_first
      message: "Implementation complete. Run code review?"
    - skill: create-pr
      mode: auto
      condition: changes_staged

Session Management

会话管理

yaml

session_start:
  auto_triggers:
    - skill: session-logger
      action: create_session_file

session_end:
  auto_triggers:
    - skill: session-logger
      action: update_session_file

yaml

session_start:
  auto_triggers:
    - skill: session-logger
      action: create_session_file

session_end:
  auto_triggers:
    - skill: session-logger
      action: update_session_file

Hook Format in Skills

技能中的钩子格式

To add auto-trigger capability to a skill, add to its front matter:

yaml

---
name: my-skill
description: Skill description
allowed-tools: Read, Write, Edit
hooks:
  before_start:
    - trigger: session-logger
      mode: auto
      context: "Start {skill_name}"
  after_complete:
    - trigger: self-improving-agent
      mode: background
    - trigger: session-logger
      mode: auto
  on_error:
    - trigger: self-improving-agent
      mode: background
---

要为技能添加自动触发功能，需在其前置元数据中添加以下内容：

yaml

---
name: my-skill
description: Skill description
allowed-tools: Read, Write, Edit
hooks:
  before_start:
    - trigger: session-logger
      mode: auto
      context: "Start {skill_name}"
  after_complete:
    - trigger: self-improving-agent
      mode: background
    - trigger: session-logger
      mode: auto
  on_error:
    - trigger: self-improving-agent
      mode: background
---

Implementation Guide

实现指南

When a skill completes its workflow:

Check
hooks
in its own front matter (

before_start

after_complete

on_error

on_progress

)

For each hook:
- If
```
mode: auto
```
  , trigger immediately
- If
```
mode: background
```
  , trigger without waiting
- If
```
mode: ask_first
```
  , ask user before triggering
- If
```
condition:
```
  exists, check it first
Pass context to the triggered skill

当技能完成其工作流时：

检查自身前置元数据中的
hooks
（

before_start

、

after_complete

、

on_error

、

on_progress

）

针对每个钩子：
- 若
```
mode: auto
```
  ，立即触发
- 若
```
mode: background
```
  ，无需等待直接触发
- 若
```
mode: ask_first
```
  ，触发前询问用户
- 若存在
```
condition:
```
  ，先检查条件是否满足
传递上下文给被触发的技能

Example Integration

集成示例

prd-planner should add:

prd-planner 应添加：

yaml

---
name: prd-planner
description: Creates PRDs using persistent file-based planning...
allowed-tools: Read, Write, Edit, Bash, Grep, Glob, AskUserQuestion, WebSearch
hooks:
  after_complete:
    - trigger: self-improving-agent
      mode: background
      context: "PRD created at {prd_file}"
    - trigger: session-logger
      mode: auto
      context: "PRD creation complete"
---

yaml

---
name: prd-planner
description: Creates PRDs using persistent file-based planning...
allowed-tools: Read, Write, Edit, Bash, Grep, Glob, AskUserQuestion, WebSearch
hooks:
  after_complete:
    - trigger: self-improving-agent
      mode: background
      context: "PRD created at {prd_file}"
    - trigger: session-logger
      mode: auto
      context: "PRD creation complete"
---

self-improving-agent already has:

self-improving-agent 已包含：

yaml

---
name: self-improving-agent
description: Universal self-improvement that learns from all skill experiences...
allowed-tools: Read, Write,Edit, Bash, Grep, Glob, WebSearch
hooks:
  after_complete:
    - trigger: create-pr
      mode: ask_first
      condition: skills_modified
    - trigger: session-logger
      mode: auto
      context: "Self-improvement cycle complete"
  on_error:
    - trigger: self-improving-agent
      mode: background
---

yaml

---
name: self-improving-agent
description: Universal self-improvement that learns from all skill experiences...
allowed-tools: Read, Write,Edit, Bash, Grep, Glob, WebSearch
hooks:
  after_complete:
    - trigger: create-pr
      mode: ask_first
      condition: skills_modified
    - trigger: session-logger
      mode: auto
      context: "Self-improvement cycle complete"
  on_error:
    - trigger: self-improving-agent
      mode: background
---

create-pr should add:

create-pr 应添加：

yaml

---
name: create-pr
description: Creates pull requests with bilingual documentation updates...
allowed-tools: Read, Write, Edit, Bash, Grep, AskUserQuestion
hooks:
  after_complete:
    - trigger: session-logger
      mode: auto
      context: "PR created: {pr_title}"
---

yaml

---
name: create-pr
description: Creates pull requests with bilingual documentation updates...
allowed-tools: Read, Write, Edit, Bash, Grep, AskUserQuestion
hooks:
  after_complete:
    - trigger: session-logger
      mode: auto
      context: "PR created: {pr_title}"
---

Chain Visualization

链可视化

┌──────────────┐
│ prd-planner  │
└──────┬───────┘
       │ after_complete
       ├──→ self-improving-agent (background)
       │         └──→ create-pr (ask_first)
       │                  └──→ session-logger (auto)
       └──→ session-logger (auto)

┌──────────────┐
│ prd-planner  │
└──────┬───────┘
       │ after_complete
       ├──→ self-improving-agent (background)
       │         └──→ create-pr (ask_first)
       │                  └──→ session-logger (auto)
       └──→ session-logger (auto)

Error Correction Chain

错误修正链

yaml

on_error:
  triggers:
    - skill: self-improving-agent
      mode: background
      context: "Error occurred in {skill_name}"
    - skill: session-logger
      mode: auto
      context: "Error captured for {skill_name}"

yaml

on_error:
  triggers:
    - skill: self-improving-agent
      mode: background
      context: "Error occurred in {skill_name}"
    - skill: session-logger
      mode: auto
      context: "Error captured for {skill_name}"

Important Rules

重要规则

Don't create infinite loops - Ensure chains terminate
Ask before major actions - Use
```
mode: ask_first
```
for PRs, deployments
Background tasks - Use
```
mode: background
```
for non-blocking tasks
Pass context - Always include relevant context to triggered skills

请勿创建无限循环——确保触发链能够终止
重大操作前询问用户——对PR创建、部署等操作使用
```
mode: ask_first
```
后台任务——对非阻塞任务使用
```
mode: background
```
传递上下文——始终向被触发的技能传递相关上下文信息