documenting-erp

Generates structured technical documentation for Divalto ERP modules from X.13 sources.

6|Updated May 11, 2026
One-click install
npx skills add https://github.com/divalto/divalto-ia-devkit --skill documenting-erp-divalto
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: documenting-erp
Source: https://github.com/divalto/divalto-ia-devkit/tree/main/plugins/divalto-devkit/skills/documenting-erp
Command: npx skills add https://github.com/divalto/divalto-ia-devkit --skill documenting-erp-divalto

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires pyyaml, markdown, and includes scripts (resource) and references (resource) components.

What problem does it solve? Writing and maintaining technical documentation for Divalto ERP modules (DAV, COMPTA, GS...) is manual, error-prone, and quickly outdated. This Skill automates the production of module documentation by extracting facts directly from living X.13 sources (dictionaries .dhsd, SQL schema, .dhsp/.dhsf code) instead of hand-written Word documents. ## Core Features & Use Cases - Automated extraction pipeline: Runs a sources -> extraction -> assembly -> rendering pipeline producing canonical YAML content models validated against schemas (module, entity, relation, process, program, glossary). - Three reading layers: Renders the same content model for three audiences (business consultants, client developers, internal Divalto developers) plus external/internal variants with or without source citations. - Multiple renderers: Ships Markdown and PDF (Chrome headless) renderers, with codified-values extraction from ISAM multichoix files and strict source-citation rules ([A VERIFIER] tracking). - Use Case: A developer needs to regenerate the DAV module documentation after an ERP version upgrade to detect drift: the Skill extracts entities like CLI, FOU, ART, enriches them with sourced business narrative, validates the model, and produces Markdown and PDF deliverables. ## Quick Start Ask Claude to generate the technical documentation for the DAV module of the Divalto ERP, providing the X.13 source path and output directory.

Frequently Asked Questions about documenting-erp

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

FAQPage Schema
How do I generate technical documentation for a Divalto ERP module?

Provide the target module (e.g. DAV), the X.13 source path, and an output directory at the initial checkpoint. The Skill then runs extraction scripts, enriches the narrative from X.13 sources, assembles and validates the YAML model, and renders Markdown and PDF deliverables autonomously.

What sources does the ERP documentation extraction use?

Extraction relies on seven X.13 sources: the .dhsd dictionary, the main screen mask .dhsf, the zoom module .dhsp, the Module Check .dhsp, the codified-values JSON, and the SQL columns and indexes JSON exports. Providing all seven yields a complete one-shot extraction.

Can the documentation be rendered for different audiences?

Yes. The renderers support three reading layers (business, schema, technical) and two audiences (externe, interne). The interne variant adds inline file:line references and a sources appendix, with output files automatically suffixed .interne.

Does the PDF renderer require specific software?

PDF rendering uses Chrome or Edge in headless mode, located via PATH or standard Windows install locations, plus the Python markdown package. The DOCERP_BROWSER environment variable can force a specific browser.

What happens when a narrative claim cannot be sourced from X.13?

Any statement not traceable to an X.13 source with a file:line citation must be listed in meta.a_verifier as an [A VERIFIER] item. The validation script rejects undocumented business descriptions for active CE fields, and the final checkpoint presents the full [A VERIFIER] list.