Validate Cross References

legal.cross_reference_validate

ProductionBounded custom (Class B)Deterministicstrictfastv1.0.0

No network

Overview

You send anchors and references you already extracted. We resolve each targetLabel with EXACT or NORMALIZED matching, including Roman-to-decimal folding, and report missing, duplicate and type-mismatched targets. We do not parse a document. A successful call costs 1 execution credit.

Cross-reference checking is label matching once extraction is done; parsing the deed would be a different skill.

Reliability

CROSS_REF_LIMIT_EXCEEDED — trigger: more than 10000 anchors or references; retryable: no; next: split the set.

Context footprint

Labels only; no document bytes. A successful call costs 1 execution credit.

When to use it

When anchors and references are already extracted and you need missing or ambiguous targets.

When the labels still live only in document prose or you need a semantic reading of a clause.

Scope

Note

Resolves caller-extracted reference labels against a supplied anchor list.

Non-goals

Does not parse DOCX or PDF prose
Does not renumber clauses
Does not judge whether a reference is semantically correct

Properties

IdempotentRetry safeStreaming supportedFile input supportedRequires external service

Capabilities

validation

Cost & billing

Flat rate per invocation

MetercallsBillable onsuccessCost per call1 credit

File handling

Accepts file_refProduces file_refMax input2 MB

How we handle your data

Sensitive input, safe output

What this means

This skill may receive sensitive content, but it does not target sensitive data and returns only a structured non-sensitive result.

Squillify guarantees

Runs inside Squillify
This skill runs inside Squillify.
Payloads are not sent to an external service by this skill.
Squillify does not permanently store submitted payloads.
Telemetry records metadata only, not submitted content.
Submitted payloads are not used for training.
Submitted payloads are not reviewed by humans.
This skill does not target sensitive data.
The response does not contain submitted content.

Your responsibility

Squillify does not determine whether submitted content is sensitive. Your application is responsible for deciding what data it is allowed to submit. Your application is responsible for securing the response.

Read the Microskill Data Handling Policy

Input schema

Field	Type	Required	Description
anchors	array	No	Extracted anchors with id and label, 0 through 10001 entries; runtime accepts at most 10000. Omit it for none.
references	array	No	Extracted references with sourceId and targetLabel, 0 through 10001 entries; runtime accepts at most 10000. Omit it for none.
matching	string	No	EXACT or NORMALIZED; omit it for EXACT.

Output schema

Field	Type	Required	Description
valid	boolean	Yes	True when no ERROR diagnostic was produced.
matching	string	Yes	Matching mode that was applied.
resolved	array	Yes	Per-reference resolution rows in request order, 0 through 10000 entries.
diagnostics	array	Yes	Deterministically ordered diagnostics, 0 through 500 entries, each with code, severity, message and path; empty when nothing was flagged.
assumptions	array	Yes	Caller-visible mechanical assumptions for this answer, such as default weekend days or a grammar version, never a legal conclusion.
limitations	string	Yes	Fixed notice that only supplied parameters are applied and that validity, compliance and enforceability are not determined.

API contract

POST /v1/execute

curl

curl -sS -X POST "$BASE/v1/execute" -H "Authorization: Bearer $KEY" -H 'Content-Type: application/json' -d '{"skillKey":"legal.cross_reference_validate","input":{"anchors":[{"id":"sch-a","label":"Schedule A"}],"references":[{"sourceId":"sch-a","targetLabel":"Schedule A"}]}}'

Integrations

TypeScript SDK

import { Squillify } from "@squillify/sdk";

const sq = new Squillify({ apiKey: process.env.SQUILLIFY_API_KEY });

const { output } = await sq.execute("legal.cross_reference_validate", {"anchors":[{"type":"SECTION","id":"s-5","label":"Section 5"},{"type":"SCHEDULE","id":"sch-a","label":"Schedule A"}],"references":[{"sourceId":"s-5","targetLabel":"Schedule A","type":"SCHEDULE"}]});

Errors

Code	HTTP	Retryable	Description
VALIDATION_ERROR	400	No	The request payload failed schema validation.
UNAUTHORIZED	401	No	Missing or invalid API key.
SKILL_NOT_ACCESSIBLE	403	No	The API key is not granted access to this skill.
SKILL_NOT_AVAILABLE_FOR_PLAN	403	No	This skill is not included in your current plan.
PLAN_ELIGIBILITY_UNAVAILABLE	503	Yes	Plan eligibility could not be decided. Retry after backoff.
SKILL_NOT_FOUND	404	No	The requested skill or version does not exist.
TENANT_RATE_LIMITED	429	Yes	Request rate limit exceeded. Retry after backoff.
QUOTA_EXCEEDED	429	Yes	Plan quota exhausted. Retryable once the quota period resets.
EXECUTION_TIMEOUT	504	Yes	Execution exceeded the allowed time budget.
CROSS_REF_LIMIT_EXCEEDED	429	No	A size, quota, rate, or time limit was exceeded.

Other limits

Limit	Value
Recommended inline bytes	32 KiB

Limitations

Does not parse DOCX or PDF prose
Does not renumber clauses
Does not judge whether a reference is semantically correct
Extracting references from a document
Editing hyperlinks

How to call

POST /v1/execute (requires authentication)

Request bodyjson

{
  "skillKey": "legal.cross_reference_validate",
  "input": {
    "anchors": [
      {
        "type": "SECTION",
        "id": "s-5",
        "label": "Section 5"
      },
      {
        "type": "SCHEDULE",
        "id": "sch-a",
        "label": "Schedule A"
      }
    ],
    "references": [
      {
        "sourceId": "s-5",
        "targetLabel": "Schedule A",
        "type": "SCHEDULE"
      }
    ]
  }
}

Examples

Section 5 points at Schedule A by exact label

Inputjson

{
  "anchors": [
    {
      "type": "SECTION",
      "id": "s-5",
      "label": "Section 5"
    },
    {
      "type": "SCHEDULE",
      "id": "sch-a",
      "label": "Schedule A"
    }
  ],
  "references": [
    {
      "sourceId": "s-5",
      "targetLabel": "Schedule A",
      "type": "SCHEDULE"
    }
  ]
}

Expected outputjson

{
  "resolved": [
    {
      "sourceId": "s-5",
      "targetLabel": "Schedule A",
      "status": "RESOLVED",
      "targetId": "sch-a"
    }
  ],
  "valid": true,
  "matching": "EXACT",
  "assumptions": [
    "Anchors and references are caller-extracted; no document prose is parsed.",
    "NORMALIZED matching folds Unicode, case, dashes and Roman numerals; it does not judge semantic identity."
  ],
  "limitations": "Calculations use only the parameters supplied in this call. No implicit legal rule is applied, and the answer does not determine validity, compliance or enforceability.",
  "diagnostics": []
}

Tip

The schedule label matches one anchor, so status is RESOLVED.

Article IV matches Article 4 after Roman folding