What problem does it solve? AI-generated answers and reports often contain hallucinated or unverifiable citations because URLs are reconstructed from memory. This Skill eliminates that risk by assigning each retrieved source a stable numeric id in a persistent ledger, so the model only ever emits integers it was handed and the URL mapping is rendered mechanically. ## Core Features & Use Cases - Citation Ledger: Registers URLs at retrieval time with idempotent, URL-normalized ids, then renders Perplexity-style inline [n] citations and a Sources block in markdown, plain, footnotes, bibtex, or evidence styles. - Fact-Checking Mode: Attaches verbatim quotes to each source (rejected unless they literally appear in the fetched page text), flags model-knowledge claims with [unverified], and enforces an evidence gate during verification. - Draft Verification: Checks drafts for unknown citation ids, mismatched Sources blocks, and minimum citation coverage thresholds before delivery. - Use Case: While writing a market research report from web searches, register each fetched page with the ledger, cite claims inline as you draft, then run verify to confirm every citation resolves and the Sources block matches the ledger. ## Quick Start Ask the agent to research a topic using web search and deliver an answer where every factual claim carries an inline numbered citation followed by a rendered Sources list.
