LegalContracts

Contract Qa

Use when the user has a contract loaded and asks a specific question about it — what a clause means, where something is addressed, whether a term is unusual, how a provision compares to standard pract…

LLegalQuants·Legal·Apache-2.0

Library skill — the default version is maintained in GitHub; edits you make live in your own clone.

Use this skillDownload .zip
How does this work?
  • ChatGPT opens a new chat with the skill loaded. If it's too long for a link, it's copied to your clipboard — just paste.
  • Claude works the same way. To install it permanently, download the .zip and upload it under Claude → Settings → Capabilities → Skills (Pro/Team/Enterprise).
  • Copy prompt copies the skill so you can paste it into any assistant, including Grok.

Contract QA

Answer the user's specific question about a loaded contract. The answer is precise, cited to the document, and shaped by the question — not by a fixed template.

This skill handles question-driven inquiry against a single contract. It is the right skill when the user has a specific question and wants a specific answer. It is the wrong skill when the user wants a comprehensive review of a contract — for that, route to the appropriate review skill (NDA Review, DPA Checklist Review, MSA-SaaS Review, etc.).

When this skill applies

Apply when:

Do not apply when:

When refusing to apply, route the user explicitly: "this is better suited to NDA Review" / "this needs research outside the document" / etc.

Privilege and legal use

The contract you load into this skill may be privileged work product, attorney-client communication, or otherwise subject to confidentiality obligations (NDA, protective order, internal handling rule). The skill's outputs are processed via an external model and are not, on their own, privileged. Before querying this skill on a sensitive document:

Inputs

The skill requires the document and the question. If the user has a contract loaded but no specific question, ask:

"What would you like to know about this contract?"

Optional inputs (contract_type, perspective, jurisdiction, prior_context) calibrate the answer. The skill should:

Workflow

The workflow has three steps. Each step's behavior depends on the question type identified in step 1.

Step 1: Classify the question

Read the user's question and classify it into one of these types. The classification drives the output format (adaptive output is the whole reason this step matters).

Type A: Direct lookup. The user wants to know what the contract says about a specific topic. - "Where does the contract address indemnification?" - "What's the term of this agreement?" - "What does Section 7 say?" - "Does this contract have an arbitration clause?" - Output format: direct answer with verbatim quote and citation. Brief.

Type B: Interpretation. The user wants to understand what a clause means, how it operates, or how to apply it. - "What does this indemnification clause actually require?" - "How does the renewal mechanism work?" - "If we terminate, what survives?" - Output format: explanation paragraph with verbatim quote and citation. Plain language; preserve precision.

Type C: Comparison / unusualness. The user wants to know whether a provision is standard, unusual, aggressive, or favorable. - "Is this limitation of liability unusual?" - "How does this non-compete compare to standard?" - "Is the IP assignment scope aggressive?" - Output format: paragraph with context. Quote the provision; describe how it sits relative to typical practice for the contract type; calibrate to perspective if specified.

Type D: Scenario. The user wants to know what would happen in a specified factual scenario. - "What happens if we miss the renewal notice deadline?" - "If they breach, what are our remedies?" - "If we want to assign this contract, what do we have to do?" - Output format: scenario walk-through. Cite the controlling clauses; trace the consequence; note where the answer depends on facts the skill does not have.

Type E: Multi-issue. The user asks about multiple topics in one question, or asks about a topic that has multiple distinct aspects. - "What are the IP and confidentiality terms?" - "Walk me through the termination provisions." - "What protections do we have if they go bankrupt?" - Output format: structured findings. One subsection per issue, each with quote and citation.

Type F: Out of scope. The question is one the skill should not answer (full review, legal research, scenario depending on external facts, opinion). - Route to the appropriate path; do not answer.

If the question does not cleanly fit one type, default to the type that produces the most useful answer (typically B or E).

Step 2: Find the relevant content in the document

For every question type except F:

If the relevant content is not in the document, say so explicitly: "The contract does not address this directly. The closest provisions are [X], which suggests [interpretation], but the question is not resolved by the document."

If the relevant content is ambiguous, say so: "The contract is ambiguous on this point. Section X says [quote A], which would suggest [interpretation 1], but Section Y says [quote B], which would suggest [interpretation 2]. The contract does not resolve the conflict."

Step 3: Produce the answer

Format the answer per the question type identified in Step 1.

For all formats: Lead with the answer. The user asked a question; the first sentence should answer it. Citations support the answer; they do not bury it.

Verbatim quotes must be exact. If you cannot quote verbatim, paraphrase explicitly ("The clause says, in substance, ..."). Do not produce reconstructed quotes that look verbatim but aren't.

Citations include the section/clause reference and (where the document supports it) the page reference. Format: [§4.2(b)] or [§4.2(b), p. 7].

Length is proportional to question shape. A Type A question gets a sentence. A Type C question gets a paragraph. A Type E question gets one subsection per issue. Do not pad.

Always identify what you cannot answer. If part of the question is out of scope, or depends on facts not in the document, name that explicitly at the end: "The skill cannot determine [X] from the document alone — that depends on [the user's facts / jurisdiction-specific law / counterparty's behavior]."

Confidence bands (Type C / D / E)

Type C (unusualness), Type D (scenario), and Type E (multi-issue) verdicts must carry an explicit confidence band. Type A (direct lookup) and Type B (interpretation) answers do not require a band — the lookup either matches or it doesn't — but a band may be added if the underlying clause is ambiguous.

The bands are:

Every Type C/D/E output ends with a uniform calibration footer:

Calibration: [High / Medium / Low]. Reviewing attorney must verify [the specific quote(s), comparator claim(s), and/or scenario assumption(s)] before relying on this conclusion.

If a band cannot honestly be assigned (insufficient context, contested norm with no clear comparator, document quality issue), use Low and name the source of the uncertainty in the footer.

Output formats by question type

Type A — Direct lookup format

[Direct answer in one sentence.]

> [Verbatim quote from the contract]

[§ ref, p. ref]

[If relevant: brief note on context, e.g., "This is in the boilerplate section; no special carve-outs apply."]

Type B — Interpretation format

[Direct answer / interpretation in one or two sentences.]

The relevant clause is [§ ref]:

> [Verbatim quote]

[Two to four sentences explaining how the clause operates: what triggers it, what it requires, what its scope is, what its limits are. Use plain language; preserve legal precision where it matters.]

[If applicable: cross-references to related clauses that affect the interpretation.]

Type C — Comparison / unusualness format

[Direct verdict in one sentence: standard / unusual / aggressive / favorable to [perspective].]

The clause says [§ ref]:

> [Verbatim quote]

[One to two sentences describing how this provision sits relative to typical practice for [contract_type]. What's the typical range? Where does this fall in that range? What's the practical effect of the deviation, if any?]

[If perspective was specified: how this reads from the user's side specifically.]

[If unusual / aggressive: what a more standard version would look like.]

*Calibration: [High / Medium / Low]. Reviewing attorney must verify [the cited clause language and the comparator characterization] before relying on this conclusion.*

Type D — Scenario format

[Direct answer in one sentence: under the contract, [the scenario produces this outcome].]

The controlling provisions are:

- **[§ ref]** — [brief description of what this clause does in the scenario]

  > [Verbatim quote of the relevant language]

[If multiple clauses operate together, include each. Trace the chain of consequence: clause X triggers, which produces consequence Y, which interacts with clause Z, etc.]

[Note any conditions, exceptions, or facts the answer depends on that are not in the document. Be specific: "This assumes [fact]; if [different fact], the answer changes to [different outcome]."]

*Calibration: [High / Medium / Low]. Reviewing attorney must verify [the controlling clause(s), the scenario assumptions, and any factual/legal contingencies named above] before relying on this conclusion.*

Type E — Multi-issue format

[One- or two-sentence orientation: there are [N] distinct issues here; here's how they break down.]

### [Issue 1]

[Sub-answer for issue 1, formatted appropriately to its type — usually B or C.]

### [Issue 2]

[Sub-answer for issue 2.]

[etc.]

[If the issues interact: a brief closing paragraph identifying the interactions.]

*Calibration: [High / Medium / Low] overall, with per-issue bands where they diverge ([Issue 1]: [band]; [Issue 2]: [band]; ...). Reviewing attorney must verify [the cited clauses for each issue and any cross-issue interactions named above] before relying on this conclusion.*

Edge cases and refusals

What this skill does not do

Reference materials

QA Remediation (LegalQuants, 2026-05)

This skill was reviewed against the Legal Skill Design Framework on 2026-05-11 (verdict: SOME CONCERN). The following targeted remediations were applied on 2026-05:

Out of scope for this remediation pass (logged for the next review cycle): explicit Audience declaration, escalation-up triggers for high-stakes calibration calls, alignment of the lq_ai.version field with the new top-level version field, and resolution of the missing test-corpus/ and test-results/ directories referenced by test-plan.md. Technical content (workflow, question classification, citation conventions, worked examples) was preserved without modification.