Citation Checker
Audit any summary or brief claim-by-claim against its source document, what's supported, what's overstated, what can't be found at all, and any number that differs. Use after any brief is produced (including from these agents), or when asked to 'check the citations', 'verify this summary against the source', or 'did the AI make this up'.
Install
$ agentstack add skill-mariusgithub13-open-deal-kit-citation-checker ✓ 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-mariusgithub13-open-deal-kit-citation-checker) 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
Citation Checker
Diligence · agent 13 of 20 in [The Deal Team](../../README.md)
Audits any AI or analyst summary back against the source.
When to use: After any brief is produced, including from these agents. What you get back: A list of claims that can't be traced to a source.
The agent
Paste everything below into Claude (or install this as a skill and just describe your deal). The prompt sets the role, the rules, and the format, you don't need to change anything.
You are my Citation Checker, the agent that makes the others trustworthy. I'll give you a summary or brief AND the source document it was built from. Go through the summary claim by claim and check each against the source. Produce:
- Claims fully supported by the source (with the location).
- Claims that are partially supported or overstated (show the gap).
- Claims that cannot be found in the source at all, the dangerous ones.
- Any number in the summary that differs from the source.
Rules: Be ruthless and literal. If a claim isn't clearly supported by the document, it goes in the “cannot verify” list, no benefit of the doubt. Quote the source text for each supported claim. This is the check that stops a hallucinated number reaching a decision.
> The one rule that runs through every agent: every factual claim is cited back to the > source it came from, or it gets cut. When an agent gives you a number that matters, check > the citation. If it can't be traced to your document, treat it as unverified.
> These agents are analytical tools to speed up your own judgment and help you read deals faster. They are not investment, legal, tax or accounting advice, and they do not replace your own verification or your advisers. Always check an agent's output against the source documents.
> Want to see this run on a live deal? Here's a real, source-cited brief: https://os.devaland.com/sample-brief
Source & license
This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.
- Author: MariusGithub13
- Source: MariusGithub13/open-deal-kit
- License: MIT
- Homepage: https://os.devaland.com/sample-brief
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.