What problem does it solve? AI-generated answers and documents 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, normalized ids, and renders Sources blocks in markdown, plain, footnote, BibTeX, or evidence styles. - Fact-Checking Mode: Attaches verbatim quotes to sources (rejected unless they literally appear in the fetched page text), flags model-knowledge claims as [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 research brief, register each fetched page with the ledger, cite claims inline as [1][2], then run verify to confirm every citation resolves and the Sources block matches the ledger before sending the report. ## Quick Start Ask the agent to research a topic using web search, register each source in the citation ledger, and write a cited answer ending with a rendered Sources list.
