Operations workflow
Document intake: classify, extract and verify
Labels each pasted document (contract, invoice, RFP, resume, report), extracts its fields, checks each value against a verbatim quote and flags risks. Exports JSON or CSV after you approve.
Running it here
Every step runs here with Claude when you're signed in, and in your own agent.
- TriggerManual startPaste {{documents}} (4,000 characters max), separated by lines containing only ---. Optional: extra {{fields}}, {{priorities}} for the risk review, {{output_format}} (JSON or CSV).→ manual
- PromptList and label the documentsSplit {{documents}} on lines containing only ---. Per part: doc number, type (contract, invoice, RFP, resume, research report, other), confidence (high, medium, low), evidence, title or first line, word count, and whether it looks cut off. Table, then a last line: 'Batch: single type <type>' or 'Batch: mixed'.
- RouterPick the extraction schemaFrom {{inventory}}: one shared type uses its route (resumes and research reports: 'Report or resume'); mixed types or any 'other' use 'Mixed batch'.
- ContractFrom each document in {{documents}}: parties (legal names, roles), effective date, term, renewal (automatic?, notice), termination (cause, convenience, notice), fees and payment terms, price-change rights, liability cap and exclusions, indemnities (who covers whom), governing law and venue, confidentiality term, IP ownership, assignment and change of control, exclusivity or non-compete, unusual clauses. Plus: {{fields}} Table doc | field | value | quote with the shortest verbatim quote per value; missing = 'not found', no quote. Don't infer or compute.
- InvoiceFrom each document in {{documents}}: vendor name, address, tax ID, invoice number and date, due date, payment terms, PO, bill-to, currency, line items (description, quantity, unit price, amount), subtotal, tax (rate, amount), total, payment details. Plus: {{fields}} Table doc | field | value | quote with the shortest verbatim quote per value; missing = 'not found', no quote. Don't infer or convert currencies. Add two 'derived' rows per invoice with the math: line items vs subtotal, subtotal plus tax vs total, each 'matches' or the difference.
- RFPFrom each document in {{documents}}: issuer, title and reference, submission deadline (date, time, time zone), question deadline, submission method and format, page limits, each 'must' or 'shall' requirement as a numbered row, desirable requirements, criteria with weights, budget, contract length, eligibility, required documents, contact. Plus: {{fields}} Table doc | field | value | quote with the shortest verbatim quote per value; missing = 'not found', no quote. Don't infer.
- Report or resumeFrom each document in {{documents}}. Resume: name, location, contact, roles (company, title, dates), skills, education, certifications, gaps over 6 months (marked 'derived'). Research report: title, authors, organization, date, question, method, sample size and population, findings with numbers, stated limitations, funding or conflicts. Plus: {{fields}} Table doc | field | value | quote with the shortest verbatim quote per value; missing = 'not found', no quote. Infer nothing except 'derived' rows.
- Mixed batchExtract from {{documents}} by each type in {{inventory}}. Contract: parties, dates, term, renewal and notice, termination, fees, liability cap, indemnities, governing law, unusual clauses. Invoice: vendor, tax ID, number, dates, PO, currency, line items, subtotal, tax, total, payment details, plus 'derived' math checks (line items vs subtotal; subtotal plus tax vs total). RFP: issuer, deadlines with time zone, submission method, mandatory requirements, weighted criteria, budget. Resume: name, roles with dates, skills, education. Report: title, authors, date, method, sample size, findings, limitations. Other: title, parties, dates, amounts, obligations. Plus: {{fields}} Table doc | type | field | value | quote with the shortest verbatim quote per value; missing = 'not found', no quote. Infer nothing except 'derived' rows.
- PromptVerify every field against the sourceRe-read {{documents}} and mark every row of {{extraction}}: - verified: the quote is in that document (ignoring spacing) and supports the value - corrected: the quote is real but misread; give the fix - not found: no quote, or it isn't there; clear the value Derived rows pass only if the math is shown on verified values. Add rows for fields wrongly marked 'not found'. Return the table with type and status columns, then counts per status.
- PromptPlain-English summary and red flagsFor each document in {{verified}}, write an actionable plain-English summary under 100 words, then red flags (high, medium, low) citing field and quote. Use only verified or corrected values. Check at least: contracts: auto-renewal with notice over 60 days, uncapped or one-sided liability or indemnity, unilateral price changes, one-sided termination, assignment without consent. Invoices: totals that don't add up, missing PO or tax ID, repeated numbers, the due date (state it so the reviewer can check it hasn't passed), payment details that differ between one vendor's invoices or a request to pay a new account (a fraud sign: confirm by phone on a number you already have). RFPs: deadline up front, pass/fail requirements, unweighted scoring. Reports: small samples, missing method. Resumes: unexplained gaps. Weigh the user's priorities (may be blank): {{priorities}} Say when a check fails for a 'not found' field. End with: 'This is a reading aid, not legal or accounting advice.'
- PromptFormat the exportTurn {{verified}} into {{output_format}} (JSON if blank). JSON: an array of {doc, type, field, value, quote, status}, value null when not found. CSV: header doc,type,field,value,quote,status; values double-quoted, inner quotes doubled; one row per line item (line_item_1, line_item_2…). Return only the data.
- ApprovalSpot-check and approveSpot-check 3+ values against the originals, starting with corrected rows and high flags; note fixes in the approval note. Approve to export; reject to stop.→ chat
- OutputSave the extractionReturn {{export}} and {{summary}}.→ file
Good for
Ops, finance and legal teams pulling fields out of contracts, invoices or resumes and checking each value.
Last reviewed
Install as a skill
The whole workflow as one SKILL.md. Install it in Claude Code, Codex or Copilot and ask your agent to run “Document intake: classify, extract and verify”.
Get the document-intake-extract-verify skillWhat each step does
1. Manual start (Trigger)
Paste {{documents}} (4,000 characters max), separated by lines containing only ---. Optional: extra {{fields}}, {{priorities}} for the risk review, {{output_format}} (JSON or CSV).
2. List and label the documents (Prompt)
Split {{documents}} on lines containing only ---. Per part: doc number, type (contract, invoice, RFP, resume, research report, other), confidence (high, medium, low), evidence, title or first line, word count, and whether it looks cut off. Table, then a last line: 'Batch: single type <type>' or 'Batch: mixed'.
3. Pick the extraction schema (Router)
From {{inventory}}: one shared type uses its route (resumes and research reports: 'Report or resume'); mixed types or any 'other' use 'Mixed batch'.
- Contract: From each document in {{documents}}: parties (legal names, roles), effective date, term, renewal (automatic?, notice), termination (cause, convenience, notice), fees and payment terms, price-change rights, liability cap and exclusions, indemnities (who covers whom), governing law and venue, confidentiality term, IP ownership, assignment and change of control, exclusivity or non-compete, unusual clauses. Plus: {{fields}} Table doc | field | value | quote with the shortest verbatim quote per value; missing = 'not found', no quote. Don't infer or compute.
- Invoice: From each document in {{documents}}: vendor name, address, tax ID, invoice number and date, due date, payment terms, PO, bill-to, currency, line items (description, quantity, unit price, amount), subtotal, tax (rate, amount), total, payment details. Plus: {{fields}} Table doc | field | value | quote with the shortest verbatim quote per value; missing = 'not found', no quote. Don't infer or convert currencies. Add two 'derived' rows per invoice with the math: line items vs subtotal, subtotal plus tax vs total, each 'matches' or the difference.
- RFP: From each document in {{documents}}: issuer, title and reference, submission deadline (date, time, time zone), question deadline, submission method and format, page limits, each 'must' or 'shall' requirement as a numbered row, desirable requirements, criteria with weights, budget, contract length, eligibility, required documents, contact. Plus: {{fields}} Table doc | field | value | quote with the shortest verbatim quote per value; missing = 'not found', no quote. Don't infer.
- Report or resume: From each document in {{documents}}. Resume: name, location, contact, roles (company, title, dates), skills, education, certifications, gaps over 6 months (marked 'derived'). Research report: title, authors, organization, date, question, method, sample size and population, findings with numbers, stated limitations, funding or conflicts. Plus: {{fields}} Table doc | field | value | quote with the shortest verbatim quote per value; missing = 'not found', no quote. Infer nothing except 'derived' rows.
- Mixed batch: Extract from {{documents}} by each type in {{inventory}}. Contract: parties, dates, term, renewal and notice, termination, fees, liability cap, indemnities, governing law, unusual clauses. Invoice: vendor, tax ID, number, dates, PO, currency, line items, subtotal, tax, total, payment details, plus 'derived' math checks (line items vs subtotal; subtotal plus tax vs total). RFP: issuer, deadlines with time zone, submission method, mandatory requirements, weighted criteria, budget. Resume: name, roles with dates, skills, education. Report: title, authors, date, method, sample size, findings, limitations. Other: title, parties, dates, amounts, obligations. Plus: {{fields}} Table doc | type | field | value | quote with the shortest verbatim quote per value; missing = 'not found', no quote. Infer nothing except 'derived' rows.
4. Verify every field against the source (Prompt)
Re-read {{documents}} and mark every row of {{extraction}}: - verified: the quote is in that document (ignoring spacing) and supports the value - corrected: the quote is real but misread; give the fix - not found: no quote, or it isn't there; clear the value Derived rows pass only if the math is shown on verified values. Add rows for fields wrongly marked 'not found'. Return the table with type and status columns, then counts per status.
5. Plain-English summary and red flags (Prompt)
For each document in {{verified}}, write an actionable plain-English summary under 100 words, then red flags (high, medium, low) citing field and quote. Use only verified or corrected values. Check at least: contracts: auto-renewal with notice over 60 days, uncapped or one-sided liability or indemnity, unilateral price changes, one-sided termination, assignment without consent. Invoices: totals that don't add up, missing PO or tax ID, repeated numbers, the due date (state it so the reviewer can check it hasn't passed), payment details that differ between one vendor's invoices or a request to pay a new account (a fraud sign: confirm by phone on a number you already have). RFPs: deadline up front, pass/fail requirements, unweighted scoring. Reports: small samples, missing method. Resumes: unexplained gaps. Weigh the user's priorities (may be blank): {{priorities}} Say when a check fails for a 'not found' field. End with: 'This is a reading aid, not legal or accounting advice.'
6. Format the export (Prompt)
Turn {{verified}} into {{output_format}} (JSON if blank). JSON: an array of {doc, type, field, value, quote, status}, value null when not found. CSV: header doc,type,field,value,quote,status; values double-quoted, inner quotes doubled; one row per line item (line_item_1, line_item_2…). Return only the data.
7. Spot-check and approve (Approval)
Spot-check 3+ values against the originals, starting with corrected rows and high flags; note fixes in the approval note. Approve to export; reject to stop.
8. Save the extraction (Output)
Return {{export}} and {{summary}}.
Use it in your own agent
Paste into ChatGPT, Claude or Gemini. Parallel steps run one after another, and approvals become “wait for my OK”.
You're going to run a multi-step workflow: Document intake: classify, extract and verify.
Inputs:
- documents: Paste the document text (4,000 characters max per run; for long contracts paste the clauses you care about). Separate documents with a line containing only ---
- fields: cost center, project code
- priorities: We're the buyer. Flag auto-renewals, any liability cap under 12 months of fees, and invoices without a PO.
- output_format: JSON
Work through these steps in order. Label each step's output with its number. Where a step says to wait for my OK, stop and wait.
1. **List and label the documents** — Split Paste the document text (4,000 characters max per run; for long contracts paste the clauses you care about). Separate documents with a line containing only --- on lines containing only ---. Per part: doc number, type (contract, invoice, RFP, resume, research report, other), confidence (high, medium, low), evidence, title or first line, word count, and whether it looks cut off. Table, then a last line: 'Batch: single type <type>' or 'Batch: mixed'. Save the result as `inventory`.
2. **Pick the extraction schema** — From {{inventory}}: one shared type uses its route (resumes and research reports: 'Report or resume'); mixed types or any 'other' use 'Mixed batch'. Pick one route: Save the result as `extraction`.
- **Contract**: From each document in Paste the document text (4,000 characters max per run; for long contracts paste the clauses you care about). Separate documents with a line containing only ---: parties (legal names, roles), effective date, term, renewal (automatic?, notice), termination (cause, convenience, notice), fees and payment terms, price-change rights, liability cap and exclusions, indemnities (who covers whom), governing law and venue, confidentiality term, IP ownership, assignment and change of control, exclusivity or non-compete, unusual clauses. Plus: cost center, project code
Table doc | field | value | quote with the shortest verbatim quote per value; missing = 'not found', no quote. Don't infer or compute.
- **Invoice**: From each document in Paste the document text (4,000 characters max per run; for long contracts paste the clauses you care about). Separate documents with a line containing only ---: vendor name, address, tax ID, invoice number and date, due date, payment terms, PO, bill-to, currency, line items (description, quantity, unit price, amount), subtotal, tax (rate, amount), total, payment details. Plus: cost center, project code
Table doc | field | value | quote with the shortest verbatim quote per value; missing = 'not found', no quote. Don't infer or convert currencies. Add two 'derived' rows per invoice with the math: line items vs subtotal, subtotal plus tax vs total, each 'matches' or the difference.
- **RFP**: From each document in Paste the document text (4,000 characters max per run; for long contracts paste the clauses you care about). Separate documents with a line containing only ---: issuer, title and reference, submission deadline (date, time, time zone), question deadline, submission method and format, page limits, each 'must' or 'shall' requirement as a numbered row, desirable requirements, criteria with weights, budget, contract length, eligibility, required documents, contact. Plus: cost center, project code
Table doc | field | value | quote with the shortest verbatim quote per value; missing = 'not found', no quote. Don't infer.
- **Report or resume**: From each document in Paste the document text (4,000 characters max per run; for long contracts paste the clauses you care about). Separate documents with a line containing only ---. Resume: name, location, contact, roles (company, title, dates), skills, education, certifications, gaps over 6 months (marked 'derived'). Research report: title, authors, organization, date, question, method, sample size and population, findings with numbers, stated limitations, funding or conflicts. Plus: cost center, project code
Table doc | field | value | quote with the shortest verbatim quote per value; missing = 'not found', no quote. Infer nothing except 'derived' rows.
- **Mixed batch**: Extract from Paste the document text (4,000 characters max per run; for long contracts paste the clauses you care about). Separate documents with a line containing only --- by each type in {{inventory}}. Contract: parties, dates, term, renewal and notice, termination, fees, liability cap, indemnities, governing law, unusual clauses. Invoice: vendor, tax ID, number, dates, PO, currency, line items, subtotal, tax, total, payment details, plus 'derived' math checks (line items vs subtotal; subtotal plus tax vs total). RFP: issuer, deadlines with time zone, submission method, mandatory requirements, weighted criteria, budget. Resume: name, roles with dates, skills, education. Report: title, authors, date, method, sample size, findings, limitations. Other: title, parties, dates, amounts, obligations. Plus: cost center, project code
Table doc | type | field | value | quote with the shortest verbatim quote per value; missing = 'not found', no quote. Infer nothing except 'derived' rows.
3. **Verify every field against the source** — Re-read Paste the document text (4,000 characters max per run; for long contracts paste the clauses you care about). Separate documents with a line containing only --- and mark every row of {{extraction}}:
- verified: the quote is in that document (ignoring spacing) and supports the value
- corrected: the quote is real but misread; give the fix
- not found: no quote, or it isn't there; clear the value
Derived rows pass only if the math is shown on verified values. Add rows for fields wrongly marked 'not found'. Return the table with type and status columns, then counts per status. Save the result as `verified`.
4. **Plain-English summary and red flags** — For each document in {{verified}}, write an actionable plain-English summary under 100 words, then red flags (high, medium, low) citing field and quote. Use only verified or corrected values.
Check at least: contracts: auto-renewal with notice over 60 days, uncapped or one-sided liability or indemnity, unilateral price changes, one-sided termination, assignment without consent. Invoices: totals that don't add up, missing PO or tax ID, repeated numbers, the due date (state it so the reviewer can check it hasn't passed), payment details that differ between one vendor's invoices or a request to pay a new account (a fraud sign: confirm by phone on a number you already have). RFPs: deadline up front, pass/fail requirements, unweighted scoring. Reports: small samples, missing method. Resumes: unexplained gaps.
Weigh the user's priorities (may be blank): We're the buyer. Flag auto-renewals, any liability cap under 12 months of fees, and invoices without a PO.
Say when a check fails for a 'not found' field. End with: 'This is a reading aid, not legal or accounting advice.' Save the result as `summary`.
5. **Format the export** — Turn {{verified}} into JSON (JSON if blank). JSON: an array of {doc, type, field, value, quote, status}, value null when not found. CSV: header doc,type,field,value,quote,status; values double-quoted, inner quotes doubled; one row per line item (line_item_1, line_item_2…). Return only the data. Save the result as `export`.
6. **Spot-check and approve** — Show me the result and wait for my OK before the next step: Spot-check 3+ values against the originals, starting with corrected rows and high flags; note fixes in the approval note. Approve to export; reject to stop.
7. **Save the extraction** — Finish: Return {{export}} and {{summary}}.Want different steps? Open it in the workflow builder.