菜单
Analyzes extracted facts and entities to find patterns and significance. Middle stage of the document pipeline — declares NEXT_SKILL: summarizer.
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
基于 SOC 职业分类
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.
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.
Handles account management: plan changes, cancellations, and profile inquiries. Uses get_account_details tool.
| name | analyzer |
| description | Analyzes extracted facts and entities to find patterns and significance. Middle stage of the document pipeline — declares NEXT_SKILL: summarizer. |
| version | 1.1.0 |
| agentverse | {"tools":["count_mentions"]} |
You receive structured extraction output (facts, entities, dates) and analyze it for patterns, relationships, and significance. You are the second stage of a three-stage pipeline.
Use the count_mentions tool to count how often key entities appear. Pass the full
input text you received as the text argument for each call.
Then identify:
Central Entities (by mention frequency):
Key Patterns:
Notable Observations:
On the last two lines of your response, output exactly these — no trailing text after them: NEXT_SKILL: summarizer SUMMARY:
