メニュー
Detects document creation and hands off to n8n for file operations. Trigger when creating prompts, templates, scripts, markdown, JSON, YAML, or when user says save this. Routes to webhook with metadata only - no direct file operations.
Codex または Claude でインストール この Prompt をコピーして Codex、Claude、または他のアシスタントに貼り付けると、Skill ページを確認してインストールできます。
SOC 職業分類に基づく
| name | auto-document-save |
| description | Detects document creation and hands off to n8n for file operations. Trigger when creating prompts, templates, scripts, markdown, JSON, YAML, or when user says save this. Routes to webhook with metadata only - no direct file operations. |
When you detect that saveable content has been created:
Detect Content Type - Analyze the content for type indicators:
midjourney, --ar, --v → type: prompt, category: midjourneycomfyui, workflow, nodes → type: workflow, category: comfyuicharacter, backstory, traits → type: character, category: animationtransaction, VAT, category → type: financial, category: quickbookselevenlabs, voice, SSML → type: prompt, category: elevenlabsGenerate Metadata - Create payload with action, content, and metadata (type, category, suggested_name, tags, project)
Call n8n Webhook - POST to http://localhost:5678/webhook/claude-to-warp
Confirm Briefly - Report what n8n saved
User creates a Midjourney prompt → Detect type=prompt, category=midjourney → POST webhook → "Saved: prompts/midjourney/prompt_name.md"
After completing logical unit of work, commit with context and push. Never leave uncommitted work.
Requires handoff to review platform before deleting, archiving, or consolidating projects and repositories.
Tracks token usage in conversations, warns at 70% capacity, auto-triggers handover at 80% threshold with conversation summary and continuation prompts.
Never expose secrets in output. Use environment variables, reference .env files without reading contents aloud, recommend rotation if exposed.
Every artifact must be filed in correct location with version control. Defines filing structure and naming conventions.
Structured error handling - stop, assess, log, route, then fix or escalate. Prevents compounding problems.