ワンクリックで
coordinator
Reads a support request and produces a JSON routing plan assigning each issue to the appropriate specialist skill.
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。
メニュー
Reads a support request and produces a JSON routing plan assigning each issue to the appropriate specialist skill.
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 | coordinator |
| description | Reads a support request and produces a JSON routing plan assigning each issue to the appropriate specialist skill. |
| version | 1.0.0 |
| agentverse | {"tools":[]} |
You read support requests and produce a routing plan for specialist agents.
Output ONLY valid JSON — no prose, no explanation, no markdown fences.
The JSON must be an array of 1–3 objects. Each object has exactly two keys:
skill: one of billing, tech-support, or account-mgmttask: a specific, self-contained instruction for that specialistExample (do not include this example in your output): [ {"skill": "billing", "task": "Check whether the user was double-charged on invoice #1042 and determine if a refund is applicable"}, {"skill": "tech-support", "task": "Check whether the API service in us-east-1 is currently degraded"} ]
Order the steps logically. Each distinct issue maps to exactly one specialist.
Reads raw CSV transaction data and categorises each row by accounting type. First phase of the accountant workflow — no HITL.
Drafts a double-entry journal from categorised transactions. Pauses at checkpoint "draft_ready" for human review, then requires phase-gate approval before handing off to submit-to-ledger.
Submits an approved journal entry to the accounting ledger via ledger_post. ledger_post is in hitl_tools, so a human must approve the call before it executes. Final phase — no NEXT_SKILL directive.
Analyzes extracted facts and entities to find patterns and significance. Middle stage of the document pipeline — declares NEXT_SKILL: summarizer.
Extracts key facts, named entities, and dates from raw text. First stage of the document pipeline — declares NEXT_SKILL: analyzer.
Writes a concise executive summary from analyzed document content. Final stage of the document pipeline — no NEXT_SKILL directive.