prompt-maintenance

Audit Jinja2 prompt template repositories for header, include, and dependency errors.

1|2|Updated Apr 6, 2026
One-click install
npx skills add https://github.com/parisgroup-ai/imersao-ia-setup --skill prompt-maintenance
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: prompt-maintenance
Source: https://github.com/parisgroup-ai/imersao-ia-setup/tree/main/skills/prompt-maintenance
Command: npx skills add https://github.com/parisgroup-ai/imersao-ia-setup --skill prompt-maintenance

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

Centralizes maintenance of Jinja2 prompt templates by detecting missing headers, broken includes, orphaned templates, encoding issues, and include cycles so teams can avoid runtime errors and undocumented prompts.

Core Features & Use Cases

  • Comprehensive audit: Scan configured template sources, parse header metadata, map {% include %} relationships, and report structured errors and warnings.
  • Python-aware orphan detection: Scan Python code (PromptLoader, get_template, PackageLoader patterns) to find direct template references and avoid false orphan reports.
  • Catalog and sync: Generate per-source prompts.json, human-readable catalogs, and a combined catalog with a Mermaid dependency graph for documentation and CI integration.
  • Single-file validation: Validate individual templates for header format, context/output fields, encoding, and include existence for pre-commit hooks.

Quick Start

Run the prompt-maintenance audit to scan all template sources, map dependencies, and produce an errors-and-warnings report.

Frequently Asked Questions about prompt-maintenance

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

FAQPage Schema
How do I detect broken includes and orphaned Jinja2 prompt templates?

Run a comprehensive audit to scan Jinja2 template sources, parse header metadata, map include dependencies, and report structured errors and warnings for missing headers, broken includes, encoding issues, and cycles.

What is the best way to validate a single Jinja2 template before committing?

Use single-file validation to check individual Jinja2 templates for header format, context and output fields, encoding, and include existence, making it suitable for pre-commit hooks.

Does prompt template audit work with Python code references like PromptLoader and get_template?

Yes, the audit scans Python code for PromptLoader, get_template, and PackageLoader patterns to find direct template references and avoid false orphan reports during validation.

How do I generate a dependency graph for Jinja2 template includes?

Generate a combined catalog with a Mermaid dependency graph that maps Jinja2 include relationships, producing JSON and Markdown artifacts for documentation and CI integration.

Can I integrate Jinja2 template validation into CI checks and pre-deployment workflows?

Yes, you can integrate Jinja2 template validation into CI checks and pre-deployment workflows by generating per-source prompts.json files and human-readable catalogs for automated reporting and syncing.

Why do my Jinja2 prompts fail at runtime due to include cycles or missing headers?

Jinja2 prompts fail at runtime due to include cycles, missing headers, broken includes, and encoding issues because template repositories lack centralized maintenance to detect these errors before deployment.