forge-citation

Enforces citationable claims and validates URLs/files in AI-generated documents.

Updated Aug 23, 2026
One-click install
npx skills add https://github.com/f4rkh4d/forge-skill --skill forge-citation
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: forge-citation
Source: https://github.com/f4rkh4d/forge-skill/tree/main/skills/research/forge-citation
Command: npx skills add https://github.com/f4rkh4d/forge-skill --skill forge-citation

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Removes fabricated or non-verifiable citations from AI-generated outputs so readers can trust claims and independently verify sources.

Core Features & Use Cases

  • Citation discipline: Defines when to cite, what counts as verifiable evidence, and what not to cite (including common hallucinated-citation patterns).
  • Source-quality verification: Requires URL resolution checks, exact quote matching, and validation that referenced file paths/symbols exist.
  • Correct formatting across contexts: Provides paste-ready citation formats for Markdown, RAG chunk references, and code/document references, with explicit confidence labeling.

Quick Start

Ask your AI to rewrite the draft so every factual claim includes an inline citation with verified URL or internal file references, and all inferences are clearly labeled as inferred.

Frequently Asked Questions about forge-citation

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

FAQPage Schema
How do I add verifiable citations to AI-generated research summaries?

To add verifiable citations to AI-generated research summaries, require inline citation placement for all factual claims, validate that cited URLs resolve correctly, and ensure exact quote matching so readers can independently trace the sources.

Why does AI hallucinate fake citations and how can I prevent it in RAG answers?

AI hallucinates fake citations when it lacks source-quality verification. Prevent fabricated citations in RAG answers by validating URL resolution, checking exact quote matching, and distinguishing established facts from AI inferences with explicit confidence labeling.

What is the best way to format source attribution in Markdown and code references?

The best way to format source attribution in Markdown and code references is using paste-ready citation formats that include verified URLs, internal file path validation, and explicit confidence labeling to ensure traceability across different documentation contexts.

Can I use automated fact verification for high-stakes domains like legal and medical guidance?

Yes, automated fact verification is critical for high-stakes domains like legal, medical, and financial guidance. It enforces traceable claims by validating internal references, requiring exact quoting or faithful paraphrasing, and checking that cited sources actually exist.

How do I validate that internal file paths and symbols referenced in AI documentation actually exist?

To validate that internal file paths and symbols referenced in AI documentation actually exist, apply source-quality verification checks that confirm referenced file paths and symbols resolve correctly before publishing the generated output.