Agent skill

trust-research

Execute high-fidelity research with hallucination guard, citation checks, and confidence scoring; use when asked to summarize or analyze sources with strict accuracy.

View SKILL.md on GitHub Repository
Stars 163
Forks 31

Install this agent skill to your Project

npx add-skill https://github.com/majiayu000/claude-skill-registry/tree/main/skills/devops/trust-research

SKILL.md

Trust Research

Use this skill to produce evidence-grounded research outputs.

Workflow

  1. Retrieve sources and extract claims.
  2. Validate each claim against its citation.
  3. Run consistency checks across summaries.
  4. Produce a confidence score and flag gaps.

Output expectations

  • Provide citations for all claims.
  • Include a confidence assessment and unresolved questions.

Didn't find tool you were looking for?

Be as detailed as possible for better results