More screenshots
Works with the AI Agents you already use
Citation Integrity Sweep
Sweep a reference list against its sources: catch missing, uncited, and unverified entries before submission.
$5
Citation Integrity Sweep
Example session with this skill installed
Apply the skill to: Merged manuscript with 41 references.
- Read your context and instructions
- Compiled the citation integrity sweep
Worked example: A manuscript merged from three co-author sections carried 41 references, with formatting that looked uniform because one tool had restyled the whole list. Findings: Two-direction matching found 3 citations with no list entry and 2 list entries never cited. Existence checks found 1 entry with a wrong year, 2 with swapped author initials, and 1 entry that could not be found after two searches. Claim-fit checks found 4 citations used for claims their sources did not make, all on general-topic grounds. One preprint and its published version were listed as separate sources for the same finding. Outcome: The corrected list had 39 entries: 1 unverified entry removed, duplicates merged, years and initials fixed, and 4 citations replaced or claims softened. The final two-direction match passed, and the sweep table was kept with the submission files for co-author checking. This is a worked example produced by applying the skill protocol, not a guarantee of results on new data.
Connects securely to your tools. The creator never sees your data.
About this skill
Reference lists accumulate errors through copying, version drift, and hurried formatting, and a single fabricated or misdescribed reference can undermine trust in an otherwise careful document. The bottleneck is checking citations against sources rather than against each other. Formatting tools make lists look clean while author names, years, and venues quietly diverge from the actual publications. This skill gives you a full protocol: trigger and scope, an inputs and outputs contract, ordered steps with checks, a decision table, a fill-in template, a checklist, a scoring rubric, a worked example, edge cases, and a pre-delivery quality gate. It also includes a runnable script under scripts/ so the core scoring or checking step can be repeated on new data without redoing the judgement by hand. The focus throughout is bottleneck fixes and workflows that a short free checklist would not cover: what to check first and second, which thresholds change the action, and when to stop and narrow the scope.
A sweep checks bibliographic accuracy and fit between citation and claim; it does not judge the quality of the cited work itself. Retraction status must be checked against a current source at submission time. Results depend on input quality: missing inputs, small samples, or unverified sources limit how strongly conclusions can be stated. The skill helps you state those limits honestly rather than hiding them.
How to use
- 1
Connect your agent to the Agensi MCP
Copy the prompt and paste it into Claude, ChatGPT, Cursor or any agent that supports MCP. It sets up the connection for you. Manual setup
- 2
Sign in to Agensi
Your agent shows a sign-in link. Sign in and click Allow.
- 3
Ask for what you need
Your agent loads this skill and uses it on your task. It always asks before any payment.
Reviews
No reviews yet
Be one of the first to try it. Every listed skill goes through the trust checks below.
Security scanned
Checked by our 8-point scan before listing
Fresh listing
Recently published to Agensi
Money-back guarantee
Doesn't do what its page promises? You get your money back.
Trust & safety
Security scan
Security scan passed 23 days ago