- Home
- Skills
- Workflow Automation
- dpp supplier evidence normalizer
Works with the AI Agents you already use
dpp supplier evidence normalizer
Normalize messy supplier CSVs into audit-ready Digital Product Passport records with strict field-level provenance.
$15
dpp supplier evidence normalizer
Example session with this skill installed
Process the attached supplier_data_v2.csv and mapping_spec.json. Focus on material composition and recyclability claims for the 'EcoFrame' product line.
- Read your context and instructions
- Compiled the dpp supplier evidence
I have normalized the supplier data for the 'EcoFrame' product line. I identified two conflicting claims regarding recycled aluminum content and mapped four verified attributes to the DPP schema.
DPP Evidence Normalization Report
| Field | Normalized Value | Source ID | Status | Provenance/Note |
|---|---|---|---|---|
| Material: Aluminum | [CONFLICT] | CSV_Row_12, CSV_Row_45 | Flagged | Row 12 claims 40%, Row 45 claims 65%. |
| Coating Type | Powder Coat (PE) | CSV_Row_14 | Verified | Matches spec sheet hash sha256:e3b0c442... |
| Recyclability Index | 0.85 | CSV_Row_22 | Verified | Unit: Ratio (0-1). |
| Repairability Score | UNKNOWN | N/A | Missing | No data found in columns 'Ease of Repair' or 'Score'. |
| Manufacturer ID | MF-99821 | CSV_Row_01 | Verified | Preserved original supplier ID. |
Missing Evidence Requests
- Conflict Resolution: Provide secondary verification (ISO 14021) for recycled aluminum percentage.
- Missing Field: 'Repairability Score' or disassembly instructions are required for the 'EcoFrame' line.
- Documentation: Missing technical data sheet for the 'BioPolymer' sealant mentioned in the BOM.
Next steps
- Resolve the aluminum content discrepancy with the supplier using the flagged Row IDs.
- Request the BioPolymer technical data sheet to complete the sealant provenance.
- Run
scripts/normalize.py --finalonce the missing attributes are received to update the record.
Connects securely to your tools. The creator never sees your data.
About this skill
The problem
Supplier data exports for Digital Product Passports (DPP) are usually inconsistent, messy, and riddled with conflicting claims. Manually mapping CSV fields while maintaining strict provenance for regulatory compliance is slow and prone to human error.
What it does
- Maps raw supplier CSV exports to standardized product records without losing original identifiers.
- Flags conflicting claims between different data sources instead of automatically picking one.
- Generates specific missing-evidence requests to send back to suppliers.
- Maintains field-level provenance including document hashes and cell coordinates.
- Distinguishes between supplied observations and verified live test results.
Frameworks & tools
Python (scripts/normalize.py), CSV, JSON fixtures.
Why this beats prompting it yourself
Standard LLM prompts tend to "hallucinate" missing data or smooth over contradictions to be helpful. This skill enforces strict evidence discipline, ensuring that unknowns and contradictions are preserved as required for audit-grade DPP records.
Use cases
- Processing diverse supplier sustainability exports into a unified schema.
- Identifying gaps in technical documentation for circular economy regulations.
- Auditing supply chain data for conflicting material composition claims.
- Preparing clean data for Digital Product Passport registry uploads.
Known limitations
Does not perform OCR; PDFs and workbooks must be converted to CSV first. It does not determine regulatory applicability or legal certification status.
Requires pre-extracted CSV data; no native PDF OCR. Scope limited to normalization and evidence tracking, not legal certification or regulatory applicability checks.
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 1 month ago
Requires
Permissions
No special permissions declared or detected