Agent skill

research/grounding-auditor

Audit outputs against provided sources, enforce grounding, and log an audit trail. Use when strict source fidelity is required.

Stars 163
Forks 31

Install this agent skill to your Project

npx add-skill https://github.com/majiayu000/claude-skill-registry/tree/main/skills/design/researchgrounding-auditor

SKILL.md

Grounding Auditor

Capabilities

  • verify_claims: check outputs against trusted sources.
  • cross_check: compare across multiple sources for consistency.
  • log_audit: store audit events and unsupported claims.

Dependencies

  • tangible-memory
  • reliability-budget (optional accuracy SLOs)

Inputs

  • outputs with citations, source chunks/paths.

Outputs

  • audit report, unsupported items, stored log record.

Expand your agent's capabilities with these related and highly-rated skills.

Didn't find tool you were looking for?

Be as detailed as possible for better results