AgentSkillsCN

skill-orchestrator

根据任务语言和状态,将命令路由到合适的工作流。在执行 /task、/research、/plan、/implement 命令时调用。

SKILL.md
--- frontmatter
name: skill-orchestrator
description: Route commands to appropriate workflows based on task language and status. Invoke when executing /task, /research, /plan, /implement commands.
allowed-tools: Read, Glob, Grep, Task
context: fork

Orchestrator Skill

Central routing intelligence for the task management system.

Trigger Conditions

This skill activates when:

  • A slash command needs language-based routing
  • Task context needs to be gathered before delegation
  • Multi-step workflows require coordination

Core Responsibilities

1. Task Lookup

Given a task number, retrieve full context:

code
1. Read .claude/specs/state.json
2. Find task by project_number
3. Extract: language, status, project_name, description, priority
4. Read TODO.md for additional context if needed

2. Language-Based Routing

Route to appropriate skill based on task language:

LanguageResearch SkillImplementation Skill
pythonskill-python-researchskill-theory-implementation
generalskill-researcherskill-implementer
metaskill-researcherskill-implementer
markdownskill-researcherskill-implementer

3. Status Validation

Before routing, validate task status allows the operation:

OperationAllowed Statuses
researchnot_started, planned, partial, blocked
plannot_started, researched, partial
implementplanned, implementing, partial, researched
reviseplanned, implementing, partial, blocked

4. Context Preparation

Prepare context package for delegated skill:

json
{
  "task_number": 259,
  "task_name": "task_slug",
  "language": "python",
  "status": "planned",
  "description": "Full task description",
  "artifacts": {
    "research": ["path/to/research.md"],
    "plan": "path/to/plan.md"
  },
  "focus_prompt": "Optional user-provided focus"
}

Execution Flow

code
1. Receive command context (task number, operation type)
2. Lookup task in state.json
3. Validate status for operation
4. Determine target skill by language
5. Prepare context package
6. Invoke target skill via Task tool
7. Receive and validate result
8. Return result to caller

ModelChecker-Specific Routing

Python Tasks

  • Research: skill-python-research

    • Z3 API exploration
    • Codebase pattern discovery
    • Theory implementation patterns
  • Implementation: skill-theory-implementation

    • TDD workflow enforcement
    • pytest integration
    • Theory component creation

General Tasks

  • Research: skill-researcher

    • Web search
    • Documentation exploration
  • Implementation: skill-implementer

    • Direct code changes
    • Non-theory modifications

Return Format

json
{
  "status": "completed|partial|failed",
  "routed_to": "skill-name",
  "task_number": 259,
  "result": {
    "artifacts": [],
    "summary": "..."
  }
}

Error Handling

  • Task not found: Return clear error with suggestions
  • Invalid status: Return error with current status and allowed operations
  • Skill invocation failure: Return partial result with error details