skills.rest
uabbasi
uabbasiCOMMUNITY
Explore all skills by this author →
GitHub

llm-prompting

Create versioned LLM prompting frameworks with schema validation and multi-provider routing.

Updated Feb 9, 2026
Search Tags:#evaluation#governance#prompting#llm-client#llm-prompting#schema-enforcement#category-calibration
One-click install
npx skills add https://github.com/uabbasi/good-measure-giving --skill llm-prompting
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: llm-prompting
Source: https://github.com/uabbasi/good-measure-giving/tree/main/.claude/skills/llm-prompting
Command: npx skills add https://github.com/uabbasi/good-measure-giving --skill llm-prompting

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This Skill provides expert guidance on LLM prompting infrastructure, patterns, and conventions used across the project's data-pipeline and evaluation components, enabling consistent design and safer, more reliable outputs.

Core Features & Use Cases

  • Versioned Prompt System: frontmatter-based prompts with version tracking, hashing, and load/validate utilities.
  • LLM Client Architecture: multi-provider routing and task-based model selection with deterministic fallbacks.
  • Schema Enforcement: JSON validation via Pydantic models to guarantee structured outputs.
  • Category Calibration: domain-specific benchmarks injected into prompts to improve calibration.
  • Robust Quality Gating: evaluation and judge modules to ensure output reliability and governance.

Quick Start

Follow this guide to implement versioned prompts, category calibration, and schema enforcement in your LLM tooling.

Frequently Asked Questions about llm-prompting

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

FAQPage Schema
How do I enforce JSON schema validation on LLM outputs?▼

You can enforce JSON schema validation on LLM outputs by applying Pydantic models to guarantee structured outputs, ensuring the response data conforms strictly to your defined schema.

How does multi-provider routing work for LLM model selection?▼

Multi-provider routing enables task-based model selection across different LLM providers with deterministic fallbacks, automatically switching to alternative models if the primary provider fails or underperforms.

What is a versioned prompting framework and when do I need it?▼

A versioned prompting framework uses frontmatter-based prompts with version tracking and hashing to manage prompt changes over time. You need it when maintaining consistent LLM behavior across data pipelines and evaluation workflows.

How do I calibrate LLM prompts for domain-specific tasks?▼

You calibrate LLM prompts for domain-specific tasks by injecting category-based benchmarks into the prompts, which improves output accuracy and relevance for specialized domains within your evaluation components.

Can I use this prompting framework with my existing data pipeline components?▼

Yes, the prompting framework integrates with data-pipeline and llm_client components, applying schema enforcement, deterministic overrides, and category-based benchmarks without requiring external dependencies.

What are the limitations of using frontmatter-based versioning for LLM prompts?▼

Frontmatter-based versioning requires strict adherence to hard requirements for formatting, hashing, and load/validate utilities. Prompts that do not satisfy these structural constraints will fail validation within the data-pipeline and llm_client components.

Related Skills

Explore More Software Engineering Skills→
chicagopeabodydev-sudochicagopeabodydev-sudo

pydantic-skill

Define structured data contracts for LLM outputs using Pydantic BaseModel.

Community
Intermediate
wangyouanwangyouan

advanced-evaluation

Evaluate LLM outputs with direct scoring, pairwise comparison, and bias mitigation.

Community
Advanced
existential-birdsexistential-birds
75

pydantic-ai-model-integration

Configure LLM providers, fallbacks, streaming, and usage metrics.

Official
Intermediate
genesis-agentsgenesis-agents
2

Prompt Engineering

Create versioned prompt templates with validation and A/B testing for LLMs.

Community
Advanced