LLMGraphDAGジョブのライフサイクルと registry 観察パターン

Community

Fix DAG result retrieval with onComplete

Authortransreal
Version1.0.0
Installs0

System Documentation

What problem does it solve?

This Skill prevents confusion when LLMGraphDAG jobs disappear from the registry after successful completion, and when external observation of $iLLMGraphDAGJobs fails due to context resolution differences.

Core Features & Use Cases

  • Registry lifecycle awareness: Explains that fully successful DAG jobs are intentionally removed from $iLLMGraphDAGJobs, so LLMGraphDAGStatus may return Missing["JobNotFound", jobId].
  • Correct result capture pattern: Shows how to reliably extract node results via the onComplete callback and store them in external variables.
  • Safe registry observation: Describes why directly referencing ClaudeCode`$iLLMGraphDAGJobs externally can resolve to a different symbol, and provides the correct approach—observing from inside the node handler where context matches.
  • Targeted debugging checklist: Provides a verification list to avoid false diagnoses when testing DAG behavior.

Quick Start

Ask Claude Code to run an LLMGraphDAGCreate test that saves the final node result inside the job's onComplete callback rather than relying on LLMGraphDAGStatus after completion.

Dependency Matrix

Required Modules

None required

Components

Standard package

💻 Claude Code Installation

Recommended: Let Claude install automatically. Simply copy and paste the text below to Claude Code.

Please help me install this Skill:
Name: LLMGraphDAGジョブのライフサイクルと registry 観察パターン
Download link: https://github.com/transreal/claudecode/archive/main.zip#llmgraphdag-registry

Please download this .zip file, extract it, and install it in the .claude/skills/ directory.
View Source Repository

Agent Skills Search Helper

Install a tiny helper to your Agent, search and equip skill from 471,000+ vetted skills library on demand.