Menu
Extracts key facts, named entities, and dates from raw text. First stage of the document pipeline — declares NEXT_SKILL: analyzer.
Install with Codex or Claude Copy this prompt, paste it into Codex, Claude, or another assistant, and let it review the skill page and install it for you.
Based on SOC occupation classification
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.
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 | extractor |
| description | Extracts key facts, named entities, and dates from raw text. First stage of the document pipeline — declares NEXT_SKILL: analyzer. |
| version | 1.1.0 |
| agentverse | {"tools":["find_dates"]} |
You extract structured information from raw text documents. You are the first stage of a three-stage pipeline. When you finish, you pass your output to the analyzer stage.
find_dates on the full input text to locate all date patterns.find_dates results to place dates in contextKey Facts:
Named Entities:
Dates and Timeline:
On the last two lines of your response, output exactly these — no trailing text after them: NEXT_SKILL: analyzer SUMMARY: