verify / research

Validate research playbook outcomes against declared truths and artifacts.

Updated Aug 27, 2026
One-click install
npx skills add https://github.com/Collectively-Gary/GaryOS --skill verify-research
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: verify / research
Source: https://github.com/Collectively-Gary/GaryOS/tree/main/data/skills/verify/research
Command: npx skills add https://github.com/Collectively-Gary/GaryOS --skill verify-research

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

This Skill verifies that a research step’s stated truths, artifacts, and evidence actually match the published or local inputs so you can trust downstream decisions.

Core Features & Use Cases

  • Truths validation against evidence: Checks that each declared plan Truth is observable in the target content for default research (published URL or local file).
  • Receipt verification by learning variant: Confirms GitHub rejection/calibration issue content matches the draft reports (with normalization) and that dataset artifacts are consistent with their manifest.
  • Operator-gated failure modes: Converts missing files, non-200 publications, drift, and schema mismatches into clear gate requests with recommended remediation.

Quick Start

Use the verify/research skill to validate a playbook: research action by checking its external_refs (published URL, local file, GitHub issue receipts, or dataset artifacts) and producing a verified/partial/failed verdict.

Frequently Asked Questions about verify / research

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

FAQPage Schema
How do I verify research evidence matches published truths and artifacts?

Research evidence verification validates each declared truth against target content, checking published URLs or local files. It ensures artifacts and receipts align with actual inputs, producing verified, partial, or failed verdicts for downstream trust.

What is the best way to check dataset integrity and manifest consistency?

Dataset integrity checking confirms artifact files match their declared manifest schemas. It spot-checks calibration reports and dataset files against normalization rules, catching drift and schema mismatches before they impact decisions.

How do I validate GitHub issue receipts against draft rejection reports?

GitHub receipt verification confirms rejection and calibration issue content matches draft reports under defined normalization rules. It checks learning variants to ensure published issue receipts accurately reflect original draft content.

What happens when research verification encounters missing files or schema mismatches?

Missing files, non-200 publications, drift, and schema mismatches trigger operator-gated failure modes. Verification converts these into clear gate requests with recommended remediation, requiring operator decision before proceeding.

Can I use research verification for local files or only published URLs?

Research verification supports both published URLs and local files as default research targets. It checks external refs across both source types, ensuring truths are observable in the target content regardless of source.