skills.rest
lhl
lhlCOMMUNITY
Explore all skills by this author →
WebsiteGitHub

realitycheck-check

Fetch sources, run three-stage evaluations, extract claims, and register results.

38|Updated Jan 20, 2026
Search Tags:#provenance#claims-analysis#source-evaluation#realitycheck#evidence-trails#data-registry
One-click install
npx skills add https://github.com/lhl/realitycheck --skill realitycheck-check
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: realitycheck-check
Source: https://github.com/lhl/realitycheck/tree/main/integrations/amp/skills/realitycheck-check
Command: npx skills add https://github.com/lhl/realitycheck --skill realitycheck-check

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This Skill automates end-to-end reality-check analyses of a source, guiding users through data fetch, three-stage evaluation, claim extraction, and provenance-aware registration in a centralized database.

Core Features & Use Cases

  • End-to-end analysis: fetch content, perform descriptive/evaluative/dialectical stages, extract claims, and register results.
  • Provenance-first tracking: maintain traceable reasoning trails and evidence links.
  • Multi-source comparison: support side-by-side analysis of multiple sources and synthesized conclusions.

Quick Start

Configure your environment to point Reality Check data at your repository. Then add a source and run the analysis: rc-db source add --id SRC-01 --title "Example Article" --type ARTICLE --url "https://example.com/article" --analysis-file analysis/sources/SRC-01.md; rc-validate; rc-export yaml sources -o sources.yaml.

Frequently Asked Questions about realitycheck-check

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

FAQPage Schema
How do I automate source evaluation and claims analysis end to end?▼

Multi-source comparison synthesizes conclusions by running side-by-side analyses across fetched sources, extracting claims from each, and registering the synthesized results with traceable provenance in the database.

How does provenance tracking work during a reality check?▼

Provenance tracking maintains traceable reasoning trails and evidence links by registering extracted claims and three-stage evaluation results directly into a centralized metadata database.

How do I register a source for claims analysis before running validation?▼

You register a source by configuring your data environment, adding the source with an ID, title, type, and URL, linking an analysis file, and then running validation and export commands.

What is the three-stage evaluation process for analyzing source claims?▼

The three-stage evaluation process for analyzing source claims consists of descriptive, evaluative, and dialectical stages, which structure the extraction and synthesis of claims from the fetched content.

Related Skills

Explore More Data & Analytics Skills→
forcedotcomforcedotcom
803

building-omnistudio-flexcard

Generate and validate OmniStudio FlexCard OmniUiCard metadata with Integration Procedure bindings.

Official
Advanced
gongye19gongye19

hybrid-fastapi-retrieval

Retrieve provenance-aware evidence from a deployed hybrid FastAPI service.

Community
Intermediate
lhllhl
38

check

Run three-stage Reality Check analyses on web sources with Python and RC-CLI tools.

Community
Advanced
lhllhl
38

analyze

Analyze sources or claims through descriptive, evaluative, and dialectical stages.

Community
Intermediate