# Citations Grounded Answers

> Build and evaluate “grounded answers” experiences using Anthropic API Citations so users can trace each claim back to source passages.

- **Type:** Skill
- **Install:** `agentstack add skill-uygnoey-skills-from-claude-blog-citations-grounded-answers`
- **Verified:** Yes — security-reviewed for prompt injection and unsafe behavior
- **Seller:** [uygnoey](https://agentstack.voostack.com/s/uygnoey)
- **Installs:** 0
- **Category:** [AI & ML](https://agentstack.voostack.com/c/ai-and-ml)
- **Latest version:** 0.1.0
- **License:** MIT
- **Upstream author:** [uygnoey](https://github.com/uygnoey)
- **Source:** https://github.com/uygnoey/skills-from-claude-blog/tree/main/2025.06.23_introducing-citations-api/skills/citations-grounded-answers

## Install

```sh
agentstack add skill-uygnoey-skills-from-claude-blog-citations-grounded-answers
```

Requires the [AgentStack CLI](https://agentstack.voostack.com/docs/cli). Works with Claude Code, Cursor, and any MCP-compatible agent.

## About

## Instructions
Use this skill to design an application workflow that answers questions or summarizes documents with verifiable citations.

1) Define the job and citation expectations
- What tasks: summarization, complex Q&A, customer support?
- What needs a citation: every bullet, every paragraph, or only factual claims?

2) Prepare sources
- Collect PDFs and/or plain text relevant to the user request.
- Decide whether to rely on the platform’s sentence chunking or provide your own pre-chunked text.

3) Prompt for grounded outputs
- Ask for concise answers and require citations alongside claims.
- Instruct the model to avoid unsupported claims and to say “not found in sources” when needed.

4) UX: make citations legible
- Choose how to display citations (inline markers, footnotes, expandable source snippets).
- Let users jump to the cited passage.

5) Evaluate and iterate
- Sample real user queries.
- Check recall (are key claims cited) and precision (are citations relevant).
- Track failure modes: missing citations, irrelevant citations, over-quoting.

## Examples
See examples in:
- examples/grounded-qa.md

## Source
- https://claude.com/blog/introducing-citations-api

## Source & license

This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.

- **Author:** [uygnoey](https://github.com/uygnoey)
- **Source:** [uygnoey/skills-from-claude-blog](https://github.com/uygnoey/skills-from-claude-blog)
- **License:** MIT

Install and usage instructions live in the source repository linked above.

## Pricing

- **Free** — Free

## Security capabilities

Automated source analysis of v0.1.0 — what this tool can access:

- **Network access:** no
- **Filesystem access:** no
- **Shell / process execution:** no
- **Environment & secrets:** no
- **Dynamic code execution:** no

*"Yes" means the capability is present in the source — more access means more to trust, not that it is unsafe.*


## Versions

- **0.1.0** — security scan: passed — Imported from the upstream source.

## Links

- Listing page: https://agentstack.voostack.com/l/skill-uygnoey-skills-from-claude-blog-citations-grounded-answers
- Seller: https://agentstack.voostack.com/s/uygnoey
- Browse the marketplace: https://agentstack.voostack.com/browse

---
Listed on AgentStack — the marketplace for AI agent skills and MCP servers. Every listing is security-reviewed. Creators keep 70%.