skills.rest
Kaleb-Rupe
Kaleb-RupeCOMMUNITY
Explore all skills by this author →
𝕏@MightieMagsGitHub

Prompting

Generates structured prompts from Handlebars templates and YAML data sources.

Updated Jul 10, 2026
Search Tags:#prompt engineering#yaml#bun#meta-prompting#prompt generation#handlebars#template rendering
One-click install
npx skills add https://github.com/Kaleb-Rupe/aurora --skill prompting-kaleb-rupe
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: Prompting
Source: https://github.com/Kaleb-Rupe/aurora/tree/main/claude/skills/Utilities/Prompting
Command: npx skills add https://github.com/Kaleb-Rupe/aurora --skill prompting-kaleb-rupe

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires handlebars, yaml.

What problem does it solve? Writing consistent, high-quality prompts by hand is repetitive and error-prone, especially when the same structures (agent briefings, workflows, evaluation rubrics) must be regenerated with different data. This Skill centralizes prompt engineering standards and provides a Handlebars-based templating engine so prompts are composed programmatically from reusable templates and YAML data. ## Core Features & Use Cases - Template Rendering Engine: RenderTemplate.ts compiles Handlebars templates with YAML or JSON data, supporting custom helpers (uppercase, join, pluralize, json, codeblock, and more) and partials. - Template Validation: ValidateTemplate.ts checks syntax, unbalanced blocks, and missing variables against a data file before rendering. - Prompt Engineering Standards: Standards.md documents Claude 4.x best practices, markdown-only structure rules, context engineering, and an ultimate prompt template validated by research. - Use Case: Generate a full agent briefing by running RenderTemplate.ts with the Briefing.hbs primitive and a YAML file describing the agent, task, and output format, producing a consistent structured prompt without manual writing. ## Quick Start Ask the AI to render the Briefing template with your agent and task data using the Prompting skill's RenderTemplate tool to produce a structured prompt.

Frequently Asked Questions about Prompting

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

FAQPage Schema
How do I render a Handlebars prompt template with YAML data?▼

Run RenderTemplate.ts with Bun, passing --template for the .hbs file and --data for the YAML or JSON file. Add --output to write the result to a file or --preview to print it to the console.

How do I validate a Handlebars template before rendering?▼

Use ValidateTemplate.ts with the --template flag to check syntax, unbalanced blocks, and extracted variables. Pass --data with a YAML file and --strict to treat missing variables as errors instead of warnings.

What template syntax does this prompt templating system use?▼

It uses Handlebars notation: {{variable}} for interpolation, {{#each}} and {{#if}} for iteration and conditionals, and {{> partial}} for reusable components. Custom helpers like uppercase, join, pluralize, json, and codeblock are registered in the rendering engine.

Does this system support both YAML and JSON data files?▼

Yes, the data loader in RenderTemplate.ts parses files ending in .json with JSON.parse and all other files with a YAML parser. Both formats can be used interchangeably as template data sources.

Why should prompts use markdown instead of XML tags?▼

The standards documentation mandates markdown headers for all prompt structure because they maximize readability, require no special parsing, and clearly emphasize ordering. XML-style tags are explicitly prohibited in skill files, workflows, and templates.

What are the limitations of logic in Handlebars templates?▼

Handlebars is logic-less by design, so complex business logic must live in TypeScript rather than templates. Templates handle structure and formatting only, with helpers covering simple transformations like case conversion and truncation.

Related Skills

Explore More Software Engineering Skills→
davduncdavdunc

Prompting

Generate structured prompts from data using Handlebars-based templates and predefined primitives.

Community
Advanced
EntityProcessEntityProcess
15

agentv-eval-orchestrator

Orchestrate AgentV evaluations by simulating LLM responses without API keys.

Official
Intermediate
Ankh-StudioAnkh-Studio

prompt

Evaluate natural language prompts against a structured rubric with weighted scores.

Official
Intermediate
eklyukineklyukin

senior-prompt-engineer

Designs and optimizes LLM prompts, RAG pipelines, and agentic systems for AI products.

Community
Intermediate