1. Load

   ~/.claude/plugins/config/claude-for-legal/corporate-legal/CLAUDE.md

   → diligence structure, thresholds, house format.
2. Confirm: what documents, what columns, where does the output go.
3. Build the typed schema. Write

   .review-schema.yaml

   . Confirm with the user.
4. Sample run (3–5 docs). Adjust schema. Confirm.
5. Fan out — one sub-agent per document, parallel. Each cell: value + state + verbatim quote + location.
6. Normalization pass. Flag outliers and inconsistencies.
7. Output:

   .xlsx

   or Google Sheets (ask which), plus

   .csv

   +

   _sources.csv

   + markdown always. Work-product header.
8. Summary: verification workload (counts of not_present / unclear / needs_review per column), flagged columns, where the files are, reminder that every cell is a lead not a finding.

/corporate-legal:tabular-review
/corporate-legal:tabular-review --schema .review-schema.yaml --docs ./vdr/02-Contracts/
/corporate-legal:tabular-review --template ma-diligence

--schema <path>

--template <name>

references/

ma-diligence

--docs <path>

--output <xlsx|gsheets|csv>

--sample <n>

• ~/.claude/plugins/config/claude-for-legal/corporate-legal/CLAUDE.md

  → diligence structure, materiality thresholds, house format preferences

• ~/.claude/plugins/config/claude-for-legal/corporate-legal/deals/[code]/deal-context.md

  if working a specific deal
• An existing schema file if the user has one (

  .review-schema.yaml

  )

1. Documents. Where are they? VDR MCP (Box, Datasite, iManage), local folder, Google Drive folder, or a list of files. How many? If >200, warn that this will take a while and offer to start with a materiality-filtered subset.
2. Schema. What columns? Two paths:
   • User picks a template from

     references/

     (M&A diligence standard is the default)
   • User describes columns in natural language and you structure them into the typed schema
3. Output. Excel (

   .xlsx

   ) or Google Sheets — ask which the team works in. CSV and markdown always written as fallbacks. Output goes to the deal folder, Drive, or wherever the user says.

• Columns where most answers are

  unclear

  — the prompt is ambiguous, rewrite it

• classify

  columns where answers don't fit the options — add options or change to

  free

• verbatim

  columns returning paraphrases — reinforce that it must be character-for-character

1. Reads the entire document (not a RAG chunk — the whole thing).
2. For each column, finds the relevant provision.
3. Returns a structured row: for each column,

   {value, state, quote, location}

   .

   • value

     is the typed answer (or null if

     state

     is not

     answered

     )

   • state

     is

     answered | not_present | unclear | needs_review

   • quote

     is the verbatim supporting text (exact, no paraphrase, no ellipsis inside a sentence — if you cut, cut at sentence boundaries and mark it)

   • location

     is where the quote lives (section number, heading, page — whatever the document gives you)

state: answered

• The

  quote

  MUST be a character-for-character copy of contiguous text from the source document, retrievable at the

  location

  the sub-agent cites. Do NOT compose a quote from a section heading plus standard boilerplate you expect to be there. Do NOT paraphrase and call it verbatim. Do NOT reconstruct a quote from memory of how such clauses "usually" read. Do NOT fill gaps in the source with ellipsis-stitching across non-contiguous text.
• The

  location

  must be specific enough for the normalization pass to re-open the document and re-read the same span — a section number, heading, or page reference the reviewer can navigate to.
• If the sub-agent cannot locate and copy the exact text (source truncated, OCR garbage, provision implied but not written, section heading visible but body not loaded), the cell state is

  needs_review

  , the

  value

  is null, and

  notes

  MUST contain

  quote_unavailable: <reason>

  . It is NEVER acceptable to set

  state: answered

  with a composed or reconstructed quote.
• The same rule applies to

  verbatim

  -typed columns AND to the companion source quotes attached to

  classify

  /

  date

  /

  duration

  /

  currency

  /

  number

  /

  free

  cells. The supporting quote carries the same verbatim obligation as the cell value.

location

quote

needs_review

quote_mismatch

classify

• Check that every

  answered

  value is in the options list. Outliers get re-classified or bumped to

  needs_review

  .
• Check for clusters: if 180 documents say

  consent_required

  and 20 say

  consent_not_unreasonably_withheld

  , that's probably real. If 195 say

  consent_required

  and 5 say

  freely_assignable

  , look at the 5 — they're either genuinely different or misclassified.

date

duration

currency

• Check format consistency. Normalize.
• Flag implausible values (a 99-year term, a $1 cap) as

  needs_review

  .

verbatim

• Spot-check by re-opening the source document at the cited

  location

  for a random sample (at least 3–5 rows per column, or 10% of rows, whichever is larger) and comparing the stored

  quote

  character-for-character against the source.
• If any quote is composed, paraphrased, reconstructed, or cannot be located at the cited span: downgrade that cell to

  needs_review

  with

  quote_mismatch

  in notes, and flag the whole column — expand the spot-check to the rest of the column rather than assuming the other rows are clean. One fabricated quote is enough to justify widening the check.
• A cell with

  state: answered

  and a mismatched quote is a higher-severity failure than an

  unclear

  or

  needs_review

  cell — it misrepresents the evidence trail. Downgrade aggressively.

| Document | Counterparty | Effective Date | Change of Control | Assignment | ⚠️ Flags |
|---|---|---|---|---|---|
| Vendor MSA — Acme | Acme Corp | 2023-04-01 | consent_required | consent_required | — |
| Supply Agmt — Beta | Beta LLC | 2021-11-15 | ⚠️ unclear | silent | CoC ambiguous §14.2 |

.csv

_sources.csv

.xlsx

references/excel-output.md

references/gsheets-output.md

openpyxl

• Each data column is paired with a hidden source column containing the quote and location. Cell comments (Excel) or notes (Sheets) on the visible column surface the quote on hover.
• Color code by state: white = answered, yellow = unclear or needs_review, gray = not_present.
• A

  Verified

  column per data column, blank by default. The reviewer marks it. This is the verify/flag pattern that makes the table auditable — the deal team can see at a glance what a human has actually checked.
• A

  _schema

  sheet with the column definitions, so the file is self-documenting.

## Outputs

This review is derived from source documents that may be privileged, confidential, or both. It inherits the sources' privilege and confidentiality status — distribution beyond the privilege circle can waive privilege. Store with the matter's privileged files and make distribution decisions deliberately.

• Document count, column count, rows completed
• Count of

  not_present

  ,

  unclear

  ,

  needs_review

  per column — this is the verification workload
• Any columns where the normalization pass flagged >10% of rows
• Where the output files are
• A reminder: every cell is a lead, not a finding. Verification required before this informs a rep, a schedule, or a memo.

• It does not replace reading the documents. It tells you where to look.
• It does not produce confidence scores. A 0.73 is not information. The

  unclear

  /

  needs_review

  states and the verbatim quotes are the confidence signal — if the quote doesn't support the value, flag it.
• It does not silently skip documents. Every document the user pointed at gets a row. A document that couldn't be read gets a row of

  needs_review

  with a note.
• It does not pretend a paraphrase is a quote. The evidence trail is the whole point.

• diligence-issue-extraction

  finds issues; this extracts data points. If an extraction reveals an issue (a MAC clause that references a specific earnings target, a poison pill), note it and suggest running diligence-issue-extraction on that document.

• material-contract-schedule

  builds one specific table (the disclosure schedule). It can consume this skill's output directly — the schedule is a filtered, reformatted view of a tabular review.

• ai-tool-handoff

  hands bulk review to Luminance/Kira when the corpus is too large or the team prefers a dedicated platform. This skill is the in-house option for anything it can handle — run it first, hand off the residue.