workflow-orchestrator

工作流编排器

一项用于协调多个技能之间工作流的技能：通过评估钩子元数据、记录待处理的后续操作，并且只运行当前宿主运行时中安全且受支持的操作。

此技能的激活时机

在以下情况应使用此技能：

• 某项技能完成其主要工作流
• 达到里程碑（PRD 完成、实现完成等）
• 用户说“完成工作流”或“结束流程”

工作方式

┌─────────────────────────────────────────────────────────────┐
│                    Workflow Orchestration                   │
├─────────────────────────────────────────────────────────────┤
│                                                             │
│  1. Detect Milestone → 2. Read Hooks → 3. Record/Run Safe Follow-ups │
│                                                             │
│  prd-planner complete                                       │
│       ↓                                                     │
│  workflow-orchestrator                                      │
│       ↓                                                     │
│  ┌─────────────────────────────────────┐                   │
│  │ declared self-improving follow-up   │ (record/run)       │
│  │ declared session logging follow-up  │ (record/run)       │
│  └─────────────────────────────────────┘                   │
│                                                             │
└─────────────────────────────────────────────────────────────┘

触发器配置

从 skills/auto-trigger/SKILL.md 读取触发器定义：

hooks:
  after_complete:
    - trigger: self-improving-agent
      mode: background
    - trigger: session-logger
      mode: auto
  on_error:
    - trigger: self-improving-agent
      mode: background

执行模式

模式	行为	使用场景
auto	宿主支持时，运行或记录低风险的后续操作	日志记录、状态更新
background	记录非阻塞的后续操作	反思、分析
ask_first	执行前询问用户	PR、部署、重大更改

里程碑检测

PRD 完成

Detected when:
- docs/{scope}-prd.md exists
- All phases in {scope}-prd-task-plan.md are checked
- Status shows "COMPLETE"

Actions:
1. Record self-improving-agent as a background follow-up
2. Run or record session-logger if the host supports it

实现完成

Detected when:
- All PRD requirements implemented
- Tests pass
- Code committed

Actions:
1. Ask before running code-reviewer
2. Run create-pr only when the user requested submission
3. Run or record session-logger if the host supports it

已应用自我改进

Detected when:
- Candidate validated with auditable evidence
- One named durable owner changed
- Representative behavior rerun
- Candidate recorded as applied

Actions:
1. Ask before running create-pr
2. Run or record session-logger if the host supports it

学习候选项（技能完成）

Detected when:
- A skill completes its workflow and produces reusable evidence
- User provides feedback
- Error or issue encountered

Actions:
1. Record self-improving-agent as a background follow-up
2. Run or record session-logger if the host supports it

The self-improving-agent:
- Captures a candidate only when reusable evidence exists
- Excludes raw transcripts and private tool payloads
- Keeps uncertain findings under observation
- Validates candidates only with explicit, auditable evidence
- Applies validated changes only to a named durable owner with a change reference
- Proves the representative behavior after application

错误处理（on_error）

以下情况会被检测到：

• 命令返回非零退出代码
• 遵循技能指引后测试失败
• 用户报告指引产生了错误结果

操作：

1. 在后台记录 self-improving-agent，以进行自我纠正
2. 运行或记录 session-logger，以捕获错误上下文

技能中的钩子实现

如需声明后续操作元数据，请在任意技能的 SKILL.md 中添加此部分：

## Auto-Trigger (After Completion)

When this skill completes, record or run supported follow-ups:

```yaml
hooks:
  after_complete:
    - trigger: skill-name
      mode: auto|background|ask_first
      context: "relevant context"
  on_error:
    - trigger: self-improving-agent
      mode: background

当前钩子约定

钩子元数据表示声明性的意图，并不证明 CLI 自动化可用。采取行动前，请阅读当前技能的 front matter。缺少钩子意味着未声明后续操作；即使存在钩子，仍须确认宿主支持相关操作，并遵守目标操作的权限边界。

通用学习模式

┌─────────────────────────────────────────────────────────────┐
│                  Skill Completes With Evidence              │
└──────────────┬──────────────────────────────────────────────┘
               │
               ↓
    ┌──────────────────────┐
    │ workflow-orchestrator │
    └──────────┬───────────┘
               │
    ┌──────────┴─────────┐
    ↓                   ↓
self-improving-agent  session-logger
    ↓                   ↓
Capture candidate     Save bounded context
    ↓                   ↓
Validate evidence     Log session
    ↓
Apply to named owner
    ↓
create-pr (only if submission was requested)

## Workflow Examples

### Example 1: PRD Creation Workflow

用户：“为用户身份验证创建一份 PRD” ↓ prd-planner 执行 ↓ 阶段 6 完成：交付 PRD ↓ workflow-orchestrator 检测到里程碑 ↓ ┌─────────────────────────────────┐ │ 后台：self-improving-agent │ → 记录学习提案 │ 自动：session-logger │ → 宿主支持时保存会话 └─────────────────────────────────┘

### Example 2: Full Feature Workflow

用户：“创建一份 PRD 并实现它” ↓ prd-planner → workflow-orchestrator ↓ self-improving-agent（仅捕获候选项） ↓ prd-implementation-precheck ↓ 实现完成 → workflow-orchestrator ↓ code-reviewer → 可选的候选项捕获 ↓ create-pr（仅在收到请求时）→ workflow-orchestrator ↓ session-logger

Each milestone can produce a `self-improving-agent` follow-up, but durable
skill edits still require validation or explicit approval.

## Implementation Steps

### Step 1: Detect Milestone

Check for completion indicators:

```bash
# PRD complete?
grep -q "COMPLETE" docs/{scope}-prd-task-plan.md

# All phases checked?
grep -q "^\- \[x\].*Phase 6" docs/{scope}-prd-task-plan.md

# PRD file exists?
ls docs/{scope}-prd.md

步骤 2：读取触发器配置

# Read hooks from auto-trigger skill
cat skills/auto-trigger/SKILL.md

步骤 3：记录或执行钩子

按顺序处理每个钩子（before_start、after_complete、on_error）：

1. 检查是否满足条件
2. 根据模式和宿主支持情况记录或执行
3. 将上下文传递给触发的技能
4. 根据模式等待或继续

步骤 4：更新状态

记录触发的内容及结果：

## Workflow Execution

- [x] self-improving-agent (background) - Started
- [x] session-logger (auto) - Session saved
- [ ] create-pr (ask_first) - Pending user approval

配置了自动触发器的技能

技能	触发时机
prd-planner	self-improving-agent、session-logger
self-improving-agent	不自动创建 PR；已应用的更改可以声明日志记录后续操作
prd-implementation-precheck	self-improving-agent、session-logger
code-reviewer	self-improving-agent、session-logger
create-pr	session-logger
refactoring-specialist	self-improving-agent、session-logger
debugger	self-improving-agent、session-logger

为现有技能添加后续操作元数据

如需为现有技能添加后续操作元数据，请在其 SKILL.md 末尾添加：

---

## Auto-Trigger

When this skill completes, record or run supported follow-ups:

```yaml
hooks:
  after_complete:
    - trigger: session-logger
      mode: auto
      context: "Save session context"

For more complex triggers, specify mode and context:

```markdown
## Auto-Trigger

When this skill completes:

```yaml
hooks:
  after_complete:
    - trigger: next-skill
      mode: background
      context: "Description"
    - trigger: session-logger
      mode: auto
      context: "Save session"
    - trigger: create-pr
      mode: ask_first
      context: "Create PR if files modified"
  on_error:
    - trigger: self-improving-agent
      mode: background

## Best Practices

1. **Log only when supported and appropriate** - Session logging is a bounded optional follow-up
2. **Ask before major actions** - PRs, deployments, destructive changes
3. **Background for analysis** - Reflection, evaluation, optimization
4. **Auto for status** - Logging, status updates, bookmarks
5. **Don't create loops** - Ensure chains terminate