Skip to main content

Squillify development is paused indefinitely. Read why, and discover what this experiment achieved. Read the story

MicroSkills Reference

Compare Dependencies

code.compare_dependencies

ProductionBounded custom (Class B)Deterministicverifiablefastv1.0.0
No network

Overview

When you have two manifest snapshots — for example before and after a PR — we extract dependencies from each side and report added, removed, changed, upgraded, downgraded, and scope-changed entries. Upgrade/downgrade direction is reliable for SemVer-style versions; other schemes fall back to lexical comparison. We do not install packages, run builds, or resolve ranges against a registry — do not use this for vulnerability scanning or authoritative resolution.

Raw manifest diffs are noisy. We turn them into a structured dependency drift report you can gate on in review.

Reliability

Deterministic once dependencies are extracted; stable ordering. Upgrade and downgrade direction is authoritative for SemVer versions; otherwise lexical. Invalid side shapes throw validation errors — fix the input before retrying.

Context footprint

Returns a summary object plus a sorted changes array and warnings. A successful call costs 1 execution credit.

When to use it

When you already extracted or can supply both manifest snapshots and need a drift summary.

For vulnerability scanning, builds, or registry resolution.

Scope

Note
Compares two dependency manifests and classifies drift between them.

Non-goals

  • Does not install packages
  • Does not query vulnerability databases
  • Does not run builds
  • Does not resolve version ranges against a registry
  • Upgrade/downgrade on non-SemVer versions is best-effort lexical

Properties

IdempotentRetry safeStreaming supportedFile input supportedRequires external service

Capabilities

analysisparsing

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

FieldTypeRequiredDescription
leftobjectYesClosed dependency-manifest snapshot with 0 through 200 filename-and-content file objects.
rightobjectYesClosed dependency-manifest snapshot with 0 through 200 filename-and-content file objects.
ecosystemHintstringNoInert ecosystem hint; omit it because filenames select parsers.
includeDevDependenciesbooleanNoWhether development scopes are included; omit it for true.
versionComparestringNoVersion-direction policy; omit it for semver.

Output schema

FieldTypeRequiredDescription
summaryobjectYesClosed counts containing added, removed, changed, upgraded, and downgraded properties.
changesarrayYesFrom 0 through 100,000 changed dependencies in stable order.
warningsarrayYesFrom 0 through 400 parsing warnings, at most one per supplied file.

API contract

POST /v1/execute
curl
curl -sS -X POST "$BASE/v1/execute" -H "Authorization: Bearer $KEY" -H 'Content-Type: application/json' -d '{"skillKey":"code.compare_dependencies","input":{"left":{"files":[{"filename":"package.json","content":"{}"}]},"right":{"files":[]}}}'
Integrations
TypeScript SDK
import { Squillify } from "@squillify/sdk";

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

const { output } = await sq.execute("code.compare_dependencies", {"left":{"files":[{"filename":"package.json","content":"{\"dependencies\":{\"react\":\"18.2.0\"}}"}]},"right":{"files":[{"filename":"package.json","content":"{\"dependencies\":{\"react\":\"18.3.1\"}}"}]}});

Errors

CodeHTTPRetryableDescription
VALIDATION_ERROR400NoThe request payload failed schema validation.
UNAUTHORIZED401NoMissing or invalid API key.
SKILL_NOT_ACCESSIBLE403NoThe API key is not granted access to this skill.
SKILL_NOT_AVAILABLE_FOR_PLAN403NoThis skill is not included in your current plan.
PLAN_ELIGIBILITY_UNAVAILABLE503YesPlan eligibility could not be decided. Retry after backoff.
SKILL_NOT_FOUND404NoThe requested skill or version does not exist.
TENANT_RATE_LIMITED429YesRequest rate limit exceeded. Retry after backoff.
QUOTA_EXCEEDED429YesPlan quota exhausted. Retryable once the quota period resets.
EXECUTION_TIMEOUT504YesExecution exceeded the allowed time budget.

Other limits

LimitValue
Recommended inline bytes32 KiB

Limitations

  • Does not install packages
  • Does not query vulnerability databases
  • Does not run builds
  • Does not resolve version ranges against a registry
  • Upgrade/downgrade on non-SemVer versions is best-effort lexical
  • Vulnerability scanning
  • Registry-backed transitive resolution

How to call

POST /v1/execute (requires authentication)

Request bodyjson
{
  "skillKey": "code.compare_dependencies",
  "input": {
    "left": {
      "files": [
        {
          "filename": "package.json",
          "content": "{\"dependencies\":{\"react\":\"18.2.0\"}}"
        }
      ]
    },
    "right": {
      "files": [
        {
          "filename": "package.json",
          "content": "{\"dependencies\":{\"react\":\"18.3.1\"}}"
        }
      ]
    }
  }
}

Examples

Patch-level npm upgrade on one dependency

Inputjson
{
  "left": {
    "files": [
      {
        "filename": "package.json",
        "content": "{\"dependencies\":{\"react\":\"18.2.0\"}}"
      }
    ]
  },
  "right": {
    "files": [
      {
        "filename": "package.json",
        "content": "{\"dependencies\":{\"react\":\"18.3.1\"}}"
      }
    ]
  }
}
Expected outputjson
{
  "warnings": [],
  "summary": {
    "upgraded": 1,
    "downgraded": 0,
    "added": 0,
    "changed": 1,
    "removed": 0
  },
  "changes": [
    {
      "manager": "npm",
      "changeType": "changed",
      "rightVersion": "18.3.1",
      "name": "react",
      "versionDirection": "upgraded",
      "leftVersion": "18.2.0"
    }
  ]
}

Identical manifests produce an empty diff

Inputjson
{
  "left": {
    "files": [
      {
        "filename": "package.json",
        "content": "{\"dependencies\":{\"lodash\":\"4.17.21\"}}"
      }
    ]
  },
  "right": {
    "files": [
      {
        "filename": "package.json",
        "content": "{\"dependencies\":{\"lodash\":\"4.17.21\"}}"
      }
    ]
  }
}
Expected outputjson
{
  "changes": [],
  "summary": {
    "upgraded": 0,
    "downgraded": 0,
    "added": 0,
    "changed": 0,
    "removed": 0
  },
  "warnings": []
}
  • Review dependency changes in a pull request
  • Audit drift between two release manifests
  • Summarize lockfile or package.json differences

Avoid for

  • Vulnerability scanning
  • Registry-backed transitive resolution

Composable with

Safety & privacy

  • Runs without calling any external service.
  • Your payloads are never stored permanently.
  • Telemetry captures metadata only — never your payload contents.
  • We never train models on your payloads.
  • No human reviews your payloads.

Tags

codedependenciesanalysis