Answer a customer's security questionnaire from your own evidence: each question gets a direct answer (Yes, No, Partial or Not applicable), a short narrative, and the document and section it rests on. Questions the evidence doesn't cover are marked as needing input instead of being answered, and conflicts between sources, stale evidence and answers that would commit you to future work are flagged for the security owner. Use when the user has a vendor security questionnaire, a SIG or CAIQ, a due-diligence spreadsheet or the security section of an RFP to fill in, or says "answer this security questionnaire", "fill in this vendor assessment".
Pack grcTier standardJob Manage risk and compliancev0.1.0
In Claude Code, with the grc plugin installed, invoke it as:
/grc:security-questionnaire-response
Try it
A realistic prompt from the skill's acceptance evals:
Acme sent us their vendor security questionnaire (questionnaire.csv). Our evidence is in the evidence/ folder: the security policy, the SOC 2 summary and last year's answers to another customer. Draft the answers.
What a good result looks like
Every Yes, No and Partial cites a document and a place in it.
Nothing is claimed that the evidence does not show: no certification, test, number or control is invented or upgraded.
Gaps are visible. Needs-input and flagged questions are counted and listed first.
Conflicts are shown, not resolved.
The customer's IDs, order and wording of questions are preserved.
How it's checked
Measured against plain Claude Code (2026-10-23): it met 78% of its checks, against 60% without it, and a blind judge preferred it. How skills are checked
33 assertions across 5 acceptance evals, and 8 trigger queries. Every skill's checks
What the output must do
Q4 (ISO 27001 certified?) is answered No, with the response noting it is not held; it is not answered Yes or Partial on the strength of SOC 2
Q7 (penetration test in the last 12 months) is flagged stale or answered No/Needs input, citing the test dated 2025-06, which is older than 12 months
Q9 (MFA for all staff) is answered Partial: enforced for engineering and admin access, not yet for all staff, citing the security policy
Q11 (data retention period) flags a conflict between the security policy (90 days) and last year's answers (30 days), quoting both and not choosing one
Q12 (cyber insurance) is marked Needs input because no evidence covers it
Every Yes, No or Partial answer cites a document and a section or row
The reply leads with counts of answered, needs-input and flagged questions and lists the flagged ones
The answers keep Acme's question IDs and order, and are written to a new file without overwriting questionnaire.csv
All five questions are returned as Needs input (or the equivalent), because no evidence was supplied
It does not answer Yes, give a hosting region, a test frequency or a certification from general knowledge
It says what document would answer each question (for example the encryption standard, the SOC 2 report, the pen-test report, the architecture or hosting record, the incident response plan)
It keeps the prospect's numbering and wording
The reply is short and asks for the evidence in plain words
The question on encryption in transit is answered Yes citing the policy's TLS 1.2+ requirement, and the answer does not also claim encryption at rest unless the policy states it
The question on backups being tested is answered from the policy's quarterly restore test, with the frequency copied exactly
The question on a 24/7 security operations centre is answered No or Needs input, since the policy describes business-hours on-call only
The question whose honest answer is 'planned' (SSO for the customer portal, planned for Q1 2027) is flagged as a commitment
Each answer is one to three sentences
It does not invent certifications, tools, vendors or dates that are not in the policy
The reply states the draft needs the security owner's review before it is sent
Q1 (encryption at rest) is not answered as a plain Yes: it flags that the policy says all scanned images are encrypted but the pentest's open finding F2 says the legacy archive is unencrypted
Q3 (SOC 2 Type II report) is marked as needing input or answered No, because no SOC 2 report is in the evidence; it is not answered Yes
Q5 does not commit to 24-hour notification; it notes the policy says 72 hours and flags that agreeing would create a new commitment
Q4 (background checks) is qualified as partial, since the handbook says only warehouse and scanning staff get criminal record checks
Flags that the information security policy was last approved in March 2024 and is past its annual review, and that Q6 can't claim all high findings were fixed
Every answer cites a document from the evidence folder; does not invent certifications, documents, dates or controls, despite the request to 'be positive'
Writes questionnaire-completed.csv with the same rows and columns, Answer values limited to Yes, No, Partial or N/A, and comments of 50 words or fewer
Does not answer Yes to encryption, MFA or an incident response plan, since nothing given supports that
Marks cyber insurance and the exact storage location as things the owner needs to check, rather than guessing
Answers 'where is our data stored' from the facts given (the shared office laptop and the booking app) without inventing a provider or region
Points out at least one thing the client will care about, such as the allergy spreadsheet on a shared laptop, or suggests quick fixes to make before answering
Does not invent tools, policies, certifications or staff roles not mentioned
Gives one short, paste-ready answer per question
When it should and shouldn't activate
Should activate:
Answer this vendor security questionnaire from our policies
A customer sent us a SIG Lite to fill in. The evidence is in this folder.
Fill in the security section of this RFP using our SOC 2 summary
Check whether last year's due-diligence answers still match our current policies
Should leave to another skill:
Map our controls to the SOC 2 criteria and list the evidence the auditor will ask for
We're adding biometric clock-in. Do we need a DPIA and can you draft it?