customer-data-export
Provides a compliant template for managing customer data export and deletion requests (DSAR).
Install
mkdir -p .claude/skills/customer-data-export && curl -L -o skill.zip "https://agentskills.codes/api/skills/download/16964" && unzip -o skill.zip -d .claude/skills/customer-data-export && rm skill.zipInstalls to .claude/skills/customer-data-export
Activation
This is the description your AI agent reads to decide when to run this skill — the better it matches your request, the more reliably it fires.
Use when performing customer data export — template for handling customer data export requests (data portability). Covers request validation, data source identification, extraction and assembly, format standardization, secure delivery, verification, and audit trail maintenance to fulfill data subject access requests compliantly.Key capabilities
- →Validate customer data export requests
- →Identify data sources containing customer data
- →Extract profile, transaction, communication, and activity data
- →Assemble data into specified formats (JSON, CSV, PDF)
- →Securely deliver export packages via various methods
- →Maintain a complete audit trail of the export process
How it works
The skill follows a six-phase workflow: request validation, data source identification, data extraction, assembly and format, secure delivery, and audit trail maintenance, using a structured checklist for each phase.
Inputs & outputs
When to use customer-data-export
- →Perform data subject access requests
- →Handle data portability exports
- →Audit compliance documentation
About this skill
Customer Data Export Skill
Process data export for customer {{ customer_id }} — request type: {{ request_type }} under {{ regulation }}.
Workflow
Phase 1 — Request Validation
REQUEST DETAILS
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
[ ] Request ID: ___
[ ] Customer ID: {{ customer_id }}
[ ] Request type: {{ request_type }}
[ ] Regulation: {{ regulation }}
[ ] Date received: ___
[ ] Response deadline: ___ (regulatory: ___ days)
[ ] Identity verified: [ ] YES — method: ___
[ ] Request scope:
[ ] All personal data
[ ] Specific data categories: ___
[ ] Specific date range: ___
Phase 2 — Data Source Identification
DATA SOURCE MAP
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
[ ] Data sources containing customer data:
System | Data Type | Volume | Owner
____________________|__________________|_________|______
| | |
| | |
| | |
[ ] Third-party systems with customer data:
- ___: contact for retrieval: ___
- ___: contact for retrieval: ___
[ ] Data excluded from export (with justification):
- ___: reason: ___
- ___: reason: ___
Phase 3 — Data Extraction
EXTRACTION CHECKLIST
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
[ ] Profile data extracted: [ ] YES
[ ] Transaction/order history extracted: [ ] YES
[ ] Communication history extracted: [ ] YES
[ ] Activity/usage logs extracted: [ ] YES
[ ] Preferences/settings extracted: [ ] YES
[ ] User-generated content extracted: [ ] YES
[ ] Third-party data retrieved: [ ] YES
[ ] Derived/inferred data included: [ ] YES [ ] NO (justification: ___)
DATA CLEANING
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
[ ] Other customers' data removed from export
[ ] Internal-only fields excluded
[ ] Trade secrets / proprietary data excluded (if applicable)
[ ] Data de-identified where required
Phase 4 — Assembly and Format
EXPORT ASSEMBLY
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
[ ] Export format:
[ ] JSON (machine-readable)
[ ] CSV (tabular data)
[ ] PDF (human-readable summary)
[ ] Combined package (all formats)
[ ] File structure:
export-{{ customer_id }}/
profile.json
transactions.csv
communications.json
activity.json
content/
summary.pdf
[ ] Total export size: ___ MB
[ ] Export package encrypted: [ ] YES — method: ___
[ ] Checksum generated: ___
Phase 5 — Secure Delivery
DELIVERY
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
Delivery method (choose one):
[ ] Secure download link (time-limited: ___ hours)
[ ] Encrypted email attachment
[ ] Self-service portal download
[ ] Physical media (for large exports)
[ ] Delivery executed — timestamp: ___
[ ] Delivery confirmation received: [ ] YES
[ ] Download link expiration: ___
[ ] Export data purged from staging after delivery: [ ] YES
Phase 6 — Audit Trail
AUDIT RECORD
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
[ ] Request received: ___
[ ] Identity verified: ___
[ ] Data extracted: ___
[ ] Export delivered: ___
[ ] Total processing time: ___ days (deadline: ___ days)
[ ] Deadline met: [ ] YES [ ] NO (reason: ___)
[ ] Audit record stored: [ ] YES — retention: ___ years
[ ] Customer notified of completion: [ ] YES
Counter-Rationalizations
| Shortcut | Counter | Why |
|---|---|---|
| "We can skip some steps for this case" | Adapt the workflow steps, don't skip them | Skipped steps are where incidents and oversights originate |
| "The user seems to already know what to do" | Complete all workflow phases with the user | The workflow catches blind spots that experience alone misses |
| "This is a minor case, full process is overkill" | Scale the process down, don't turn it off | Minor cases become major when unstructured; the process scales, not disappears |
| "I'll fill in the details later" | Complete each section before moving on | Deferred details are forgotten; real-time capture is more accurate |
| "The template output isn't necessary" | Always produce the structured output format | Structured output enables comparison, audit trails, and handoff to other teams |
Output Format
Produce a data export fulfillment report with:
- Request summary (customer, type, regulation, timeline)
- Data sources (systems queried, data categories included)
- Export contents (file listing, format, size)
- Delivery confirmation (method, timestamp, verification)
- Audit trail (complete timeline from request to fulfillment)
When not to use it
- →When skipping steps for minor cases
- →When the user seems to already know what to do
- →When deferring details to fill in later
Limitations
- →Requires AWS (or cloud provider) connection
- →Requires customer_id and request_type as input
- →Requires structured output format for comparison and audit trails
How it compares
This skill provides a compliant and auditable workflow for handling customer data export requests, ensuring all regulatory requirements are met and documented, unlike ad-hoc data retrieval.
Compared to similar skills
customer-data-export side by side with the closest alternatives in the catalog.
| Skill | Installs | Updated | Safety | Difficulty |
|---|---|---|---|---|
| customer-data-export (this skill) | 0 | 5mo | No flags | Intermediate |
| modal | 5 | 8mo | Review | Intermediate |
| windows-builder | 3 | 6mo | No flags | Advanced |
| lambda | 12 | 7mo | Review | Intermediate |
Try saying
Example prompts that trigger this skill in your AI assistant.
More by cloudthinker-ai
View all by cloudthinker-ai →You might also like
modal
davila7
Run Python code in the cloud with serverless containers, GPUs, and autoscaling. Use when deploying ML models, running batch processing jobs, scheduling compute-intensive tasks, or serving APIs that require GPU acceleration or dynamic scaling.
windows-builder
hashicorp
Build Windows images with Packer using WinRM communicator and PowerShell provisioners. Use when creating Windows AMIs, Azure images, or VMware templates.
lambda
itsmostafa
AWS Lambda serverless functions for event-driven compute. Use when creating functions, configuring triggers, debugging invocations, optimizing cold starts, setting up event source mappings, or managing layers.
eventbridge
itsmostafa
AWS EventBridge serverless event bus for event-driven architectures. Use when creating rules, configuring event patterns, setting up scheduled events, integrating with SaaS, or building cross-account event routing.
prowler-sdk-check
prowler-cloud
Creates Prowler security checks following SDK architecture patterns. Trigger: When creating or updating a Prowler SDK security check (implementation + metadata) for any provider (AWS, Azure, GCP, K8s, GitHub, etc.).
amazon-alexa
asnk633
Integracao completa com Amazon Alexa para criar skills de voz inteligentes, transformar Alexa em assistente com Claude como cerebro (projeto Auri) e integrar com AWS ecosystem (Lambda, DynamoDB, Polly, Transcribe, Lex, Smart Home).