skills.rest
anneschuth
anneschuthCOMMUNITY
Explore all skills by this author →
WebsiteGitHub

review-pr-diff

Generate Dutch-language pull request summaries from JSON diffs of Polder dataset fetcher runs.

Updated May 9, 2026
Search Tags:#diff-review#public-sector#pr-summary#ci-automation#dutch-government#data-compliance#change-flagging
One-click install
npx skills add https://github.com/anneschuth/polder --skill review-pr-diff
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: review-pr-diff
Source: https://github.com/anneschuth/polder/tree/main/.claude/skills/review-pr-diff
Command: npx skills add https://github.com/anneschuth/polder --skill review-pr-diff

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Manually summarizing daily diffs of the Dutch government Polder dataset into clear, actionable pull request bodies is time-consuming and error-prone, especially when flagging high-stakes organizational changes and sensitive personal data modifications that require human review.

Core Features & Use Cases

  • Organization-grouped summaries: Automatically groups all diff changes by their associated government organization for clear, contextual PR reviews.
  • High-stakes change flagging: Surfaces critical changes like organization dissolutions and mandate end dates in a dedicated top-level table for immediate attention.
  • Compliance and confidence tracking: Flags low-confidence LLM-generated proposals and modifications to sensitive AVG (GDPR) personal data fields for mandatory human review, with clear source citations for all changes.
  • Use case: For the daily automated fetcher run of the Polder dataset, use this skill to instantly generate a PR summary that highlights the dissolution of a ministry, an ended secretary-general mandate, and any unvalidated personal data changes for compliance review.

Quick Start

Use the review-pr-diff skill on the daily generated diff.json file to produce a ready-to-use PR body for the Polder dataset update, saved directly to pr-body.md.

Frequently Asked Questions about review-pr-diff

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I generate Dutch PR summaries from daily dataset diff JSON files?▼

PR summaries for dataset diffs are generated by parsing JSON diff outputs, grouping changes by government organization, and flagging high-stakes modifications like ministry dissolutions. The output is a structured markdown file with dedicated tables for compliance tracking and mandatory human review.

Can I automatically flag sensitive AVG personal data changes in government dataset pull requests?▼

Sensitive AVG personal data changes are flagged by applying project-specific GDPR field rules during diff processing. Modifications to sensitive fields are isolated into a dedicated markdown table with mandatory human review flags and clear source citations to maintain data compliance.

What is the best way to highlight organization dissolutions and mandate end dates in a data compliance PR?▼

High-stakes changes like organization dissolutions and mandate end dates are highlighted by grouping them into a dedicated top-level table within the PR summary markdown. This structure ensures immediate visibility for reviewers checking daily public sector dataset updates.

Does CI automation support generating markdown PR bodies from Polder Dutch government dataset fetcher runs?▼

CI automation supports generating markdown PR bodies from Polder Dutch government dataset fetcher runs by processing the daily diff.json output. The workflow produces a ready-to-use pr-body.md file containing organization-grouped summaries, confidence-flagged proposals, and compliance review flags.

How do I flag low-confidence LLM-generated proposals in a pull request summary?▼

Low-confidence LLM-generated proposals are flagged by applying confidence tracking during diff parsing and isolating unvalidated proposals into a specific markdown table. These entries receive confidence flags and source citations, clearly indicating which data requires mandatory human review before merging.

What limitations exist when summarizing daily public sector dataset diffs for compliance review?▼

Limitations include the strict dependency on predefined project-specific AVG sensitive field rules for accurate compliance flagging. Additionally, all unvalidated LLM proposals and sensitive personal data modifications require mandatory human review before the generated PR summary can be safely merged into the main branch.

Related Skills

Explore More Data & Analytics Skills→
anneschuthanneschuth

parse-organogram

Extracts Dutch ministerial organogram hierarchies and personnel assignments into JSON proposals.

Community
Intermediate
in-the-loop-labsin-the-loop-labs
48

user-critic

Fetch pair-review comments and apply code changes in local or PR contexts.

Official
Intermediate
expanso-ioexpanso-io

expanso-encryption-patterns

Encrypt sensitive fields like card numbers and PII using AES-GCM.

Official
Advanced
aalmadaaalmada
15

scaffold-aggregate

Scaffold event-sourced aggregates with Apply methods and Marten configuration.

Community
Advanced