Agent skill · writing content · laurigates
ground-response
Citation-backed responses with direct quotes from source documents. Use when analyzing long docs, answering codebase/spec questions, or when response accuracy is critical.
Why this skill is useful
Provides a structured method for generating citation-backed responses, ensuring accuracy and traceability in claims from source documents.
What it needs
About 4k tokens when loaded. Last updated 2026-08-06. 49 stars on the source repository.
What this skill does
/prompt-engineering:ground-response Produce a grounded, citation-backed response — every claim traced to a source quote, unsupported claims retracted, unknowns stated explicitly. When to Use This Skill Use this skill when... Use something else when... ------------------------ --------------------------- You need factual accuracy grounded in source documents Text needs style/tone adjustment → /prose:distill Analyzing long documents (>20k tokens) where hallucination risk is high You need code review → /code-quality:code-review User asks to "cite sources" or "verify claims" You need to synthesize scattered notes → /prose:synthesize Answering questions about specs, policies, or technical docs General coding task with no source verification needed User wants auditable, traceable answers Creative writing or brainstorming (accuracy not the goal) Core Principles These three techniques are from Anthropic's official documentation on reducing hallucination. Apply all three in every response. 1. Permit Uncertainty You have explicit permission to say "I don't know" or "The source does not address this." Do not invent, speculate, or fill gaps with plausible-sounding information. When the source is silent on a topic, say so. When the source is ambiguous, state the ambiguity. 2. Extract Direct Quotes First Before analyzing or answering, extract word-for-word quotes from the source material that are relevant to the task. This grounds your reasoning in actual text, not recalled impressions. For documents >20k tokens, this step is critical — extract before you analyze. 3. Verify Claims Against Quotes After formulating your response, audit every claim. Each claim must have a supporting quote. If a claim lacks a supporting quote, retract it. Mark retracted claims with [RETRACTED — no supporting quote found]. This makes your response auditable. …
How to use it
Reference it in AdaL, Claude Code, Cursor or any coding agent — nothing to install:
@skills laurigates/prompt-engineering-ground-response