verify

Validate artifacts against specifications or tests and produce a PASS/FAIL verdict with evidence.

4|1|Updated Jan 24, 2026
One-click install
npx skills add https://github.com/synaptiai/agent-capability-standard --skill verify-synaptiai
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: verify
Source: https://github.com/synaptiai/agent-capability-standard/tree/main/skills/verify
Command: npx skills add https://github.com/synaptiai/agent-capability-standard --skill verify-synaptiai

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes scripts (resource) and references (resource) components.

What problem does it solve?

Validate artifacts against specifications, tests, or invariants and provide a clear PASS/FAIL verdict with actionable evidence.

Core Features & Use Cases

  • Ground truth validation: compare artifacts against a spec, test suite, or invariants and produce a verifiable verdict.
  • Evidence anchoring: attach exact file references, test outputs, and logs to each result for auditable traceability.
  • Flexible inputs: accept a spec or tests descriptor, a target artifact, and optional constraints (timeout, schema, or filter criteria).

Quick Start

Verify a modified artifact against its spec and tests to obtain a PASS/FAIL verdict with supporting evidence.

Frequently Asked Questions about verify

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I validate a data artifact against a schema specification?

To validate a data artifact against a schema specification, you provide the target artifact and the spec to produce a verifiable PASS or FAIL verdict with supporting evidence anchors for full traceability.

What is evidence anchoring when running automated tests?

Evidence anchoring attaches exact file references, test outputs, and logs to each validation result, providing auditable traceability when verifying artifacts against invariants.

Can I enforce timeout constraints when verifying code changes?

Yes, you can enforce timeout constraints when verifying code changes. The validation process accepts optional constraints including timeout, check types, and filter criteria alongside the required spec and artifact inputs.

Does this validation approach work for both software projects and data pipelines?

Yes, this validation approach works for software projects and data pipelines. It is applicable to code changes, configurations, and data artifacts, comparing them against test suites or invariants to output a structured verdict.

What is the best way to automate invariant checks for configuration files?

The best way to automate invariant checks for configuration files is to pass a tests descriptor and the target configuration artifact into the validation process to obtain a structured PASS or FAIL verdict with evidence.