What it is: GDPR/CCPA.
Works out the smallest useful Data Privacy Controls setup for the business in front of it, then
builds it only when asked. The default output is a short recommendation, not a
spreadsheet. Artifacts - CSV, SQL DDL, JSON Schema, Notion mapping - are produced on
request, from one field list so they cannot drift apart.
Layer: Layer 7: Protect. Fits: Scale stage. Table code: n/a.
Also use it when the user says "gdpr/ccpa", or describes the same process happening in a
spreadsheet, a document or someone inboxes.
Do not use it for: payroll calculation, tax filing, or legal advice. This skill produces
empty templates only - it never holds or processes real employee or customer data.
Use the self-contained workflow below; no parent module or integration is required for empty local templates. Record lawful basis and retention as unknown until a qualified owner supplies them; a checkbox or example row does not establish compliance.
Read the request and pick the intent before asking anything.
Ask only if this is the highest-value missing fact; otherwise proceed without an opener:
Q: What personal data do you hold?
Skip anything the user already answered, in any earlier message. Ask the rest one at a
time, and stop as soon as the remaining answers would not change the output.
Never invent an answer. If the user does not know, record it as unknown and carry on.
Hold the answers in this shape. It stays internal - it is not shown to the user unless
they ask, and it never carries a value the user did not give.
module: data-privacy-controls
intent: null # setup | advice | review | fix | build | convert | export
scale: null # Starter | Growth | Scale, only if the answer changes it
areas:
"Data": null
"Purpose": null
"Controls": null
"Current process": null
"Outcome": null
requested_outputs: [] # csv | sql | json | notion | xlsx - requested formats only
confirmed_facts: [] # only what the user actually said
open_questions: [] # the unanswered ones, in the order worth asking
If an artifact was requested, build it after resolving essential missing facts. Otherwise give a short recommendation and offer the relevant artifact.
Recommended approach: Start with an inventory of what is held and why, then attach an owner and a retention rule to each item.
Why this one: Privacy work fails without an inventory, because you cannot protect data you have not listed. The inventory comes first.
Workflow: Data category listed → Purpose recorded → Owner and access → Retention rule → Review
Once the user asks for it, derive the fields from the confirmed context and emit the
requested artifacts. For machine-readable text, keep prose outside the data; for files,
provide a usable link. Report material validation failures or limitations separately.
For a Notion output, provide the CSV and property mapping below for manual import. If notion-manual-import is separately available, it may assist with import instructions; it is optional. For requested workspace writes, verify actual tool access and the precise target, apply the authorized change, and read it back before claiming completion. Never ask for a password or token.
For an Excel-compatible CSV, use UTF-8 with a byte order mark so Excel opens the
text correctly. A CSV is not an .xlsx workbook; create .xlsx only when the user
requests a workbook.
A CSV carries no types, so after it, name the columns
that need a number, date or currency format applied.
Control,Data Category,Module,Legal Basis,Retention Period,Access Roles,Encryption,Consent Required,Owner,Last Reviewed,Status,Control ID
Employee data retention,Personal,Invoices & Billing,Contractual necessity,24 months after last activity,"People team, Finance",At rest and in transit,FALSE,Sneha Iyer,2026-01-15,Implemented,
CREATE TABLE data_privacy_controls (
control VARCHAR(255),
data_category VARCHAR(100) NOT NULL,
module VARCHAR(255),
legal_basis VARCHAR(255),
retention_period VARCHAR(255),
access_roles VARCHAR(255),
encryption VARCHAR(255),
consent_required BOOLEAN, -- NULL means applicability is unknown
owner VARCHAR(255),
last_reviewed DATE, -- NULL means no review has been recorded
status VARCHAR(100) NOT NULL,
control_id SERIAL PRIMARY KEY,
created_at TIMESTAMP DEFAULT NOW(),
updated_at TIMESTAMP DEFAULT NOW()
);
CREATE INDEX idx_data_privacy_controls_status ON data_privacy_controls (status);
{
"$schema": "https://json-schema.org/draft/2020-12/schema",
"title": "Data Privacy Controls",
"type": "object",
"additionalProperties": false,
"properties": {
"Control": { "type": "string" },
"Data Category": { "type": "string" },
"Module": { "type": "string" },
"Legal Basis": { "type": "string" },
"Retention Period": { "type": "string" },
"Access Roles": { "type": "string" },
"Encryption": { "type": "string" },
"Consent Required": { "type": ["boolean", "null"] },
"Owner": { "type": "string" },
"Last Reviewed": { "type": ["string", "null"], "format": "date" },
"Status": { "type": "string" },
"Control ID": { "type": "integer" }
},
"required": [
"Data Category",
"Status"
]
}
| CSV column | Notion property | Set after import |
|---|---|---|
| Control | Title | Use as the database title |
| Data Category | Select (add options after import) | Convert to Select, add options: "Personal", "Sensitive", "Financial", "Health", "Biometric", "Location" |
| Module | Text | Leave as Text |
| Legal Basis | Text | Leave as Text |
| Retention Period | Text | Leave as Text |
| Access Roles | Text | Leave as Text |
| Encryption | Text | Leave as Text |
| Consent Required | Select | Use Unknown / Required / Not required; a Checkbox would collapse unknown into false |
| Owner | Text | Leave as Text |
| Last Reviewed | Date | Convert to Date |
| Status | Select (add options after import) | Convert to Select, add options: "Draft", "In Review", "Approved", "Implemented", "Retired" |
| Control ID | Text (preserve source ID) | Keep imported IDs as Text; optionally add a separate Unique ID property |
The rows above are documentation examples only. Emit empty templates unless the user explicitly requests examples. Money stays currency, dates stay date,
and anything pointing at another table stays relation.
| # | Field | Type | SQL | JSON Schema | Notion | CSV example |
|---|---|---|---|---|---|---|
| 1 | Control | text | VARCHAR(255) | string | Text | Employee data retention |
| 2 | Data Category | select | VARCHAR(100) | string | Select (add options after import) | Personal |
| 3 | Module | text | VARCHAR(255) | string | Text | Invoices & Billing |
| 4 | Legal Basis | text | VARCHAR(255) | string | Text | Contractual necessity |
| 5 | Retention Period | text | VARCHAR(255) | string | Text | 24 months after last activity |
| 6 | Access Roles | text | VARCHAR(255) | string | Text | People team, Finance |
| 7 | Encryption | text | VARCHAR(255) | string | Text | At rest and in transit |
| 8 | Consent Required | nullable boolean | BOOLEAN NULL | boolean or null | Select: Unknown / Required / Not required | FALSE |
| 9 | Owner | text | VARCHAR(255) | string | Text | Sneha Iyer |
| 10 | Last Reviewed | nullable date | DATE NULL | string or null, format: date | Date | 2026-01-15 |
| 11 | Status | select | VARCHAR(100) | string | Select (add options after import) | Implemented |
| 12 | Control ID | id | SERIAL PRIMARY KEY | integer | Text (preserve source ID) | (blank) |
Data Category
Personal | Sensitive | Financial | Health | Biometric | Location
Status
Draft | In Review | Approved | Implemented | Retired
Link fields: none
Prompt
We hold a lot of employee data and cannot say who owns it.
Context first - one question per message, nothing already answered:
Q: Which categories?
A: Employee and customer contact details.
Q: Consent given?
A: For customers, yes.
Q: Is it documented?
A: No.
Recommended next step - offered, not built:
Start with an inventory of what is held and why, then attach an owner and a retention rule to each item.
Workflow: Data category listed → Purpose recorded → Owner and access → Retention rule → Review
Want the CSV, SQL, JSON Schema and Notion mapping for this?
relation for anything that points at another table, text only for free text.currency, never text. Dates are date, never free text.External writes, messages, provisioning, and publication require authorization for that
action and target; existing explicit authorization does not need to be repeated.
the requested review needs; keep generated templates empty. Do not claim deletion
from the conversation or service storage.
is acted on.
Solution: deliver manual mappings without a connection; claim a live change only
after the authorized tool operation succeeds.
Solution: ask one, wait, and drop any the first answer already covered.
Solution: build what was requested; mention the parent skill separately.
Solution: derive all four from the field list in this file, never by hand.
Solution: that is expected. Apply the property mapping table once, after import.
I want to set up gdpr/ccpa for my company.
Ask me one short question at a time, and only about what I have not already told you.
Then recommend the smallest setup that fits, and wait for me to ask before you build it.
When I ask, output CSV, SQL DDL, JSON Schema, a Notion property mapping or an Excel workbook. Data only.