llm-prompting
LLM Prompting Expert
Deep expertise on the prompting infrastructure, patterns, and conventions used in this codebase.
When This Skill Activates
- Writing or modifying prompts in
data-pipeline/src/llm/prompts/ - Working on
NarrativeEvaluator,NarrativeJudge, or scoring evaluators - Debugging LLM outputs or schema validation
- Adding new LLM-powered features
- Optimizing prompt performance or cost
Prompt Infrastructure
Versioned Prompt System
More from uabbasi/good-measure-giving
frontend-design
Create distinctive, production-grade frontend interfaces with high design quality. Use this skill when the user asks to build web components, pages, artifacts, posters, or applications (examples include websites, landing pages, dashboards, React components, HTML/CSS layouts, or when styling/beautifying any web UI). Generates creative, polished code and UI design that avoids generic AI aesthetics.
11form990-expert
Deep expertise on IRS Form 990 structure, fields, and nonprofit financial analysis. Activates when working on Form 990 parsing, ProPublica API integration, or charity financial evaluation code.
1zakat-fiqh
Islamic jurisprudence expertise on zakat - the 8 categories of recipients (asnaf), scholarly interpretations across madhabs, and how to assess charity alignment with zakat eligibility. Activates when working on zakat classification, wallet tags, or donor guidance.
1webapp-testing
Test web applications using Playwright. Supports verifying frontend functionality, debugging UI behavior, capturing screenshots, and viewing browser logs. Use when testing the website or debugging UI issues.
1data-pipeline
Run the charity evaluation pipeline - extraction, 4-stage V2 workflow, Supabase patterns, versioning. Use when working on collectors, scrapers, pipeline code, database queries, or debugging data flow.
1analytics
Unified analytics (Cloudflare + Firestore + GA4). Pull traffic data, user activity, feature adoption, and giving metrics. Use when checking site performance, user behavior, or feature usage.
1