Skip to main content

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

MicroSkills Reference

Agent Execution Trace Validator

agent.execution_trace_validate

ProductionBounded custom (Class B)Deterministicstrictmoderatev1.0.0
No network

Overview

You send 1 to 10,000 events with id, optional parentId, type, ISO-8601 timestamp, optional correlationId and status STARTED, RUNNING, SUCCEEDED, FAILED or CANCELLED. clockSkewMs 0-60,000 (default 0) tolerates child-before-parent skew. We report roots, depth, duration and diagnostics for cycles, missing parents, duplicate ids, timestamp inversions, terminal-before-start and depth over 256. We do not retrieve distributed traces or diagnose latency.

A cyclic or orphaned trace is not a replayable audit record.

Reliability

Deterministic graph and time checks; timestamps are parsed, never taken from a clock. TRACE_INVALID — trigger: a malformed timestamp or empty events; retryable: no; next: send ISO-8601 instants. TRACE_LIMIT_EXCEEDED — trigger: more than 10,000 events; retryable: no; next: window the trace.

Context footprint

Counts and diagnostics only. A successful call costs 2 execution credits.

When to use it

When a captured agent trace must be a forest with legal times and statuses.

When you need to fetch traces, score latency, or apply full OpenTelemetry semantics.

Scope

Note
Validates parent, time and status invariants in a bounded agent execution trace.

Non-goals

  • Does not retrieve distributed traces
  • Does not diagnose latency
  • Does not validate full OpenTelemetry semantics

Properties

IdempotentRetry safeStreaming supportedFile input supportedRequires external service

Capabilities

analysisvalidation

Cost & billing

Flat rate per invocation

MetercallsBillable onsuccessCost per call2 credits

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
eventsarrayYesBounded array of 1 through 10001 events; runtime accepts at most 10000.
clockSkewMsintegerNoChild-before-parent allowance in milliseconds. Omit it for 0.

Output schema

FieldTypeRequiredDescription
validbooleanYesTrue when no ERROR diagnostic was raised.
eventCountintegerYesHow many events were judged.
rootCountintegerYesHow many events had no parentId.
maxDepthintegerYesLongest parent chain from a root.
durationMsintegerYesMilliseconds from earliest to latest timestamp.
clockSkewMsintegerYesApplied skew allowance.
diagnosticsarrayYesNormalized findings as a bounded array of 0 through 500 closed {code, severity, message, path, source, details} objects.

API contract

POST /v1/execute
curl
curl -sS -X POST "$BASE/v1/execute" -H "Authorization: Bearer $KEY" -H 'Content-Type: application/json' -d '{"skillKey":"agent.execution_trace_validate","input":{"events":[{"id":"a","type":"task","timestamp":"2026-08-27T00:00:00Z","status":"STARTED"}]}}'
Integrations
TypeScript SDK
import { Squillify } from "@squillify/sdk";

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

const { output } = await sq.execute("agent.execution_trace_validate", {"events":[{"status":"STARTED","timestamp":"2026-08-27T00:00:00Z","type":"task","id":"root"},{"id":"child","parentId":"root","type":"step","status":"RUNNING","timestamp":"2026-08-27T00:00:01Z"}]});

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.
TRACE_INVALID400NoThe request payload failed this skill's input validation.
TRACE_LIMIT_EXCEEDED429NoA size, quota, rate, or time limit was exceeded.

Other limits

LimitValue
Recommended inline bytes32 KiB

Limitations

  • Does not retrieve distributed traces
  • Does not diagnose latency
  • Does not validate full OpenTelemetry semantics
  • Pulling traces from a backend
  • Scoring latency SLOs

How to call

POST /v1/execute (requires authentication)

Request bodyjson
{
  "skillKey": "agent.execution_trace_validate",
  "input": {
    "events": [
      {
        "status": "STARTED",
        "timestamp": "2026-08-27T00:00:00Z",
        "type": "task",
        "id": "root"
      },
      {
        "id": "child",
        "parentId": "root",
        "type": "step",
        "status": "RUNNING",
        "timestamp": "2026-08-27T00:00:01Z"
      }
    ]
  }
}

Examples

A parent and a later child form a valid forest

Inputjson
{
  "events": [
    {
      "status": "STARTED",
      "timestamp": "2026-08-27T00:00:00Z",
      "type": "task",
      "id": "root"
    },
    {
      "id": "child",
      "parentId": "root",
      "type": "step",
      "status": "RUNNING",
      "timestamp": "2026-08-27T00:00:01Z"
    }
  ]
}
Expected outputjson
{
  "eventCount": 2,
  "durationMs": 1000,
  "valid": true,
  "clockSkewMs": 0,
  "diagnostics": [],
  "rootCount": 1,
  "maxDepth": 2
}
Tip
One root, depth 2, no diagnostics.

A two-node parent cycle is invalid

Inputjson
{
  "events": [
    {
      "id": "a",
      "parentId": "b",
      "type": "task",
      "status": "STARTED",
      "timestamp": "2026-08-27T00:00:00Z"
    },
    {
      "id": "b",
      "parentId": "a",
      "type": "task",
      "status": "RUNNING",
      "timestamp": "2026-08-27T00:00:01Z"
    }
  ]
}
Expected outputjson
{
  "eventCount": 2,
  "durationMs": 1000,
  "valid": false,
  "clockSkewMs": 0,
  "diagnostics": [
    {
      "code": "CYCLE",
      "severity": "ERROR",
      "message": "The parentId graph contains a cycle.",
      "path": "/events/0/parentId",
      "source": "squillify",
      "details": {}
    },
    {
      "code": "TIMESTAMP_INVERSION",
      "severity": "ERROR",
      "message": "A child timestamp is earlier than its parent beyond clockSkewMs.",
      "path": "/events/0/timestamp",
      "source": "squillify",
      "details": {}
    }
  ],
  "rootCount": 0,
  "maxDepth": 0
}
Tip
CYCLE is an ERROR, so valid is false.
  • Reject a cyclic parent graph before replay
  • Allow a child timestamp that is slightly earlier than its parent within clockSkewMs

Avoid for

  • Pulling traces from a backend
  • Scoring latency SLOs

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

analysisagentvalidation