Citations Grounded Answers
Build and evaluate “grounded answers” experiences using Anthropic API Citations so users can trace each claim back to source passages.
Install
$ agentstack add skill-uygnoey-skills-from-claude-blog-citations-grounded-answers ✓ scanned · ✓ verified, works with Claude Code, Cursor, and more.
Security review
✓ PassedNo issues found. Passed automated security review. · v0.1.0 How review works →
- ✓ Prompt-injection patterns
- ✓ Secret / credential exfiltration
- ✓ Dangerous shell & filesystem operations
- ✓ Untrusted network calls
- ✓ Known-malicious package signatures
What it can access
- ✓ Network access No
- ✓ Filesystem access No
- ✓ Shell / process execution No
- ✓ Environment & secrets No
- ✓ Dynamic code execution No
From automated source analysis of v0.1.0. “Used” means the capability is present in the source — more access means more to trust, not that it’s unsafe.
Verified badge
Passed review? Show it. Paste this badge into your README, it links to the public security report.
Links to your public security report.[](https://agentstack.voostack.com/security/report/skill-uygnoey-skills-from-claude-blog-citations-grounded-answers) Reliability & compatibility
Declared compatibility
Compatibility is declared by the source manifest. End-to-end runtime verification is coming, see below.
We're building live execution health for every listing: tool-call success rate, median latency, uptime, and last-checked timestamps, measured, not self-reported. It isn't live yet, so we don't show numbers we can't stand behind.
How agent discovery & health will work →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
- Source: uygnoey/skills-from-claude-blog
- License: MIT
Install and usage instructions live in the source repository linked above.
Reviews
No reviews yet, be the first.
Write a review
Versions
- v0.1.0 Imported from the upstream source.