Law & compliance · Review & audit
data-governance
/data-governance
Data lineage, classification (PII/Confidential), and integrity checks (checksums). Use when: data governance.
- Author
- andreibesleaga ↗
- Repository
- gabbe ↗
- Licence
- CC-BY-4.0
- Last repository change
- 24.10.2026
Assessment and security
90/ 100Class: good
Format25 / 25
Frontmatter with name and description, valid name, description up to 1,024 characters, name matching the folder.
Discoverability25 / 25
Description explains when to use the skill, has a reasonable length and uses third person.
Content25 / 35
At least 150 words and at most 500 lines, headings, step lists, examples or code.
Hygiene15 / 15
No placeholders such as TODO, no Windows paths, with a licence.
Riskno signals detected in the scan
- Files in this package
- 1
- Scripts
- 0
- HTML comments
- 0
- URLs in SKILL.md
- 0
Deprecation
No signals detected. Repository changed on 24.10.2026, without references to retired models or APIs.
Licence
CC-BY-4.0, otwarta.
What it does and when to use it
Data lineage, classification (PII/Confidential), and integrity checks (checksums). Use when: data governance.
Original author description
Data lineage, classification (PII/Confidential), and integrity checks (checksums). Use when: data governance.
How it works
- Goal
- Steps
- 1. Classification
- 2. Integrity Patterns
- 3. Lineage
- 4. Retention & Deletion (GDPR/CCPA)
- Security & Guardrails
Original SKILL.md headings · 42 lines, 371 words
SKILL.md preview
--- name: data-governance description: "Data lineage, classification (PII/Confidential), and integrity checks (checksums). Use when: data governance." license: CC-BY-SA-4.0 metadata: source: "agents/skills/data/data-governance.skill.md" tags: "data" core: "false" context_cost: "low" --- # data-governance Skill ## Goal Data must be classified, tracked, and verifiable. ## Steps ## 1. Classification Before storing any field, tag it: - **Public**: Safe to release (e.g., Product Descriptions). - **Internal**: Employee-only (e.g., Org Charts). - **Confidential**: Business secrets (e.g., Sales Forecasts). - **Restricted/PII**: SSN, Credit Cards, Medical Records. **Must be Encrypted at Rest**. ## 2. Integrity Patterns - **Checksums**: Store `md5/sha256` of files to detect bit-rot or tampering. - **Foreign Keys**: Enforce referential integrity in the DB. No orphans. - **Versioning**: Never overwrite critical data. Use `v1`, `v2` or Event Sourcing `AppendedOnly`. ## 3. Lineage - Answer: "Where did this specific value in the dashboard come from?" - Track: Source System -> ETL Job -> Warehouse -> BI Tool. ## 4. Retention & Deletion (GDPR/CCPA) - **TTL**: Auto-delete logs after X days. - **Right to be Forgotten**: Implementation of a `HardDeleteUser` workflow that purges PII from all tables/backups (crypto-shredding). ## Security & Guardrails ### 1. Skill Security (Data Governance) - **Classification Tampering Prevention**: Restrict permissions to modify data classification tags (Public, Internal, Confidential, PII). Only authorized governance roles should alter these definitions. - **Immutability of Audit Logs**: Ensure that data lineage and access logs are stored in append-only, immutable storage to prevent tampering by malicious actors. ### 2. System Integration Security - **Encryption Enforcement**: Systems integrating with governed data must enforce Encryption at Rest for any data classified as Restricted/PII. - **Access Control Verification**: Governance tools must integrate with identity providers (IAM/SSO) to continuously verify that only users with the correct clearance access sensitive datasets. - **Automated Compliance Checks**: Implement automated scanning in CI/CD pipelines to block deployments that violate data retention or geographical residency rules (e.g., GDPR data leaving the EU). ### 3. LLM & Agent Guardrails - **Data Exfiltration Prevention**: Agents analyzing data lineage or governance policies must be blocked from exporting raw PII or Confidential data in their outputs or external API calls. - **Context Boundary Enforcement**: When an LLM queries metadata or schemas, ensure the context window does not inadvertently ingest actual user data or sensitive records. - **Hallucination Mitigation for Compliance**: LLM-generated compliance reports must be verified against hardcoded rules. An agent must not "hallucinate" compliance approval for a system failing legal checks.
Versions
| Repository | Score | Licence |
|---|---|---|
| This page · andreibesleaga/gabbe | 90 | CC-BY-4.0 |
| wrongstack/wrongstack | 100 | MIT |
| criptogus/agent-evolve-network | 90 | Apache-2.0 |
| cbrock84/headcount | 90 | MIT |
Database snapshot: 13.11.2026 · package version 5de66e85ce7d (SHA-256 digest of the entire package)
Downloads in the last 30 days: 0 · ranking
Report a problem with this skill: harmful content, incorrect descriptions or an author’s removal request.
Similar skills
- 90lineage-pii-and-governance
Applies governance, lineage, ownership, and sensitive-data controls to data changes. Use when a pipeline touches published datasets, regulated information, or shared business metrics. - 100data-governance-agent
Activates DataGovernanceAgent for enterprise data governance strategy and implementation. Use when you need a data catalog design, data lineage mapping, PII classification and handling policy, data quality scoring framework, GDPR/CCPA data retention and deletion policies, or a… - 90enterprise-data-governance
Use this skill when implementing data governance frameworks: classification, cataloging, lineage, quality, and retention. This skill enforces: data classification, schema registry, lineage tracking, quality monitoring. Do NOT use for: database administration, ETL implementation,… - 100data-governance-as-code
Data governance as code for warehouses built on Iceberg, Parquet and SQL: a metadata file tested against the catalog, personal data found and measured, column lineage from pipeline events, access policies in tested Rego enforced on every query, retention, consent and erasure,… - 100data-lineage-tracker
Track data lineage tracker operations. Auto-activating skill for Data Pipelines. Triggers on: data lineage tracker, data lineage tracker Part of the Data Pipelines skill category. Use when working with data lineage tracker functionality. Trigger with phrases like "data lineage… - 100data-governance-as-code
Data governance as code for warehouses built on Iceberg, Parquet and SQL: a metadata file tested against the catalog, personal data found and measured, column lineage from pipeline events, access policies in tested Rego enforced on every query, retention, consent and erasure,…