skills.rest
ruban-s
ruban-sCOMMUNITY
Explore all skills by this author →
WebsiteGitHub

Prompting

Generates and validates prompts programmatically using Handlebars templates, YAML data, and prompt engineering standards.

Updated Sep 3, 2026
Search Tags:#prompt engineering#llm-as-judge#yaml#meta-prompting#prompt validation#handlebars#template rendering
One-click install
npx skills add https://github.com/ruban-s/DevOS --skill prompting-ruban-s
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: Prompting
Source: https://github.com/ruban-s/DevOS/tree/main/skills/Prompting
Command: npx skills add https://github.com/ruban-s/DevOS --skill prompting-ruban-s

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires handlebars, yaml, and includes scripts (resource) and references (resource) components.

What problem does it solve? Prompt patterns get hand-copied across every skill that needs them, causing drift, duplicated effort, and no separation between prompt structure and content. This Skill centralizes prompt engineering standards and provides a Handlebars-based templating engine so prompts are composed from data rather than glued together as strings. ## Core Features & Use Cases - Template Rendering Engine: RenderTemplate.ts compiles Handlebars templates (Primitives like Briefing, Structure, Gate, Roster, Voice, plus eval templates like Judge, Rubric, TestCase) with YAML or JSON data into finished prompts. - Template Validation: ValidateTemplate.ts checks Handlebars syntax, unbalanced blocks, and missing variables against a data file, with a strict mode for CI-style enforcement. - Prompt Engineering Standards: Standards.md codifies ideal-state prompting, markdown-only structure, Claude 4.x behavioral guidance, and anti-patterns backed by empirical research. - Use Case: Compose a structured agent briefing by rendering Primitives/Briefing.hbs with task and agent data, then pass the rendered prompt to a general-purpose subagent. ## Quick Start Ask the agent to render the Briefing template with your agent and task data to produce a ready-to-use prompt for a subagent.

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 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 for syntax errors?▼

Run ValidateTemplate.ts with the --template flag to check compilation, unbalanced blocks, and extracted variables. Pass --data to detect missing variables and --strict to treat them as errors instead of warnings.

What custom Handlebars helpers are available in the templates?▼

The engine registers helpers for string casing, indent, join, truncate, equality and comparison checks, array includes, date formatting, pluralize, number formatting, percent, default values, JSON stringify, code blocks, and repeat blocks.

Does this skill generate final content or only prompts?▼

It only generates prompts. The output of every template render is a prompt destined for use elsewhere, such as an agent briefing or eval judge; final domain content should be produced by the appropriate domain skill.

What prompt engineering standards does it enforce?▼

Standards.md mandates ideal-state prompting (state outcomes, constraints, and tools rather than procedures), markdown-only structure with no XML tags, positive framing over prohibitions, and Claude 4.x-specific guidance on tool language and literal instruction following.

Related Skills

Explore More Software Engineering Skills→
EntityProcessEntityProcess
15

agentv-eval-builder

Create and manage AgentV YAML evaluation files for AI agent performance testing.

Official
Intermediate
maragudkmaragudk
10

llm-as-a-judge

Build and validate LLM-as-Judge evaluators for automated quality assessment.

Official
Advanced
fusenginefusengine
22

prompt-testing

Compares two AI prompts on a dataset using accuracy, compliance, tokens, and latency metrics.

Community
Intermediate
Exia-thdExia-thd

prompt-optimizer

Optimize failing skill prompts with DSPy and write results to SKILL.md.

Community
Advanced