Set up
Try a plugin
The Operations plugin ships with /risk-assessment and other operations skills as a starting point. /risk-assessment scores each risk by likelihood and impact and lists mitigations with owners. If your admin manages plugins and this plugin isn't available yet, skip this step. The prompt below works without it.
/risk-assessmentIdentify, assess, and mitigate operational risks./vendor-reviewEvaluate a vendor — cost analysis, risk assessment, and recommendation.Connect your tools
Claude is more powerful when it works directly with your systems. You control permissions and access. Learn about tool access(opens in new tab).
Add a connector(opens in new tab) for each tool you want Claude to use.
Set your working folder
Drag the files you'll use (the vendor's SOC 2, their questionnaire responses, the DPA and MSA, your risk framework) into one folder on your machine, then give Claude access to it(opens in new tab) in the Claude desktop app. Claude reads from it and writes the scored memo and mitigation list back to it. If you run vendor reviews regularly, create a project(opens in new tab) from that folder so your framework, instructions, and memory stay attached.
The prompt
Copy this into Claude
Score this vendor's SOC 2, security questionnaire, DPA, and MSA against our risk framework. Write the review memo with a clear go or no-go and the required mitigations with owners. Cite the source document and section for every finding.
Why this works
List the sources to read together. "SOC 2, questionnaire, DPA, and MSA" tells Claude to cross-read security evidence and contract terms together, so a control gap and a missing contract clause show up as one finding, not two reviews.
Use your own risk criteria. "Against our risk framework" points the scoring at the document in the folder, so the tier and the go/no-go reflect your thresholds for data sensitivity and access.
Ask for a go or no-go recommendation. "Clear go or no-go" plus "required mitigations with owners" makes the memo something procurement can act on, not a list of observations someone still has to interpret.
Citations make it auditable. "Cite the source document and section" means every finding traces back to a page in the SOC 2 or a clause in the DPA, so security and legal can verify without re-reading the packet.
Get a better draft
Add an example to match. Drop an example you like into the folder and Claude matches your structure and voice.
Ask it to flag uncertainty. Add "flag anything you're not confident about" so you know where to look first when you review the draft.
Make Claude work for you
Tell Claude your own rules for this task, such as your deal-breaker controls and your memo format, then save what you've done as a skill of your own. A few minutes of conversation and it runs with your standards from then on.
Make what we've done in this task so far into a skill called /vendor-risk.
Review the skill, and save it if Claude hasn't already.
Make it repeatable
Run it on every new vendor
Give Claude access to your whole Vendors folder, so it can see each vendor you add. Ask Claude to set up a scheduled task, or open Scheduled in the sidebar, and /vendor-risk runs every weekday morning on any new risk-review folder under Vendors.
Set up a scheduled task for weekdays at 9am: check Vendors for any new risk-review folder, run /vendor-risk against the docs inside, and write the scored memo and mitigation list to that folder.
Runs /vendor-risk on every new risk-review folder under Vendors and writes the scored memo and mitigation list back to it.
To use a folder on your computer during a scheduled task, keep your computer on and awake with the Claude desktop app open so Claude can access it.
Share with your teammates
Your /vendor-risk skill now carries your risk tiers, your deal-breaker controls, and your memo format. Share it so procurement, security, and legal score every vendor the same way and the approval chain reads a consistent memo no matter who ran the review.