skills.rest
GleisonOliveira
GleisonOliveiraCOMMUNITY
Explore all skills by this author →
Website𝕏@classefinalGitHub

reversa-docs

Generates a self-contained HTML mini-site with 3D architecture, dashboards, and feature pages from extracted project knowledge.

Updated May 22, 2026
Search Tags:#html generation#documentation#dashboards#orchestration#legacy code#reverse engineering#3d visualization
One-click install
npx skills add https://github.com/GleisonOliveira/dockerpilot-mcp --skill reversa-docs-gleisonoliveira
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: reversa-docs
Source: https://github.com/GleisonOliveira/dockerpilot-mcp/tree/main/.agents/skills/reversa-docs
Command: npx skills add https://github.com/GleisonOliveira/dockerpilot-mcp --skill reversa-docs-gleisonoliveira

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve? Teams that reverse-engineer a legacy project end up with scattered analysis artifacts (soul.md, chronicle.md, SDD specs) that are hard to navigate and share. This Skill turns that extracted knowledge into a self-contained, navigable HTML mini-site in _reversa_docs/ that works offline and opens with a double click. ## Core Features & Use Cases - Four-agent pipeline: Orchestrates Mapper (3D architecture and module pages), Analyst (metrics and timeline dashboards), Storyteller (glossary, deck, feature pages), and Publisher (index, navigation, vendor bundling, smoke test) in a fixed sequence. - Offline and file:// compatible: Bundles Three.js, D3, and Highcharts locally in assets/vendor/ and injects data via assets/js/data.js, so no server or internet connection is needed to view the site. - Guided configuration and safe regeneration: Runs a short interview (reader profile, depth, visual style) persisted to .config.json, supports --auto mode, and creates timestamped backups before any destructive regeneration. - Use Case: After running the Reversa core extraction on a legacy codebase, invoke this Skill to produce an interactive documentation site with a 3D Code City, dependency dashboards, and per-feature pages for onboarding a new developer. ## Quick Start Ask your AI agent to run /reversa-docs to generate the interactive documentation mini-site for this project, then open _reversa_docs/index.html in a browser.

Frequently Asked Questions about reversa-docs

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

FAQPage Schema
How do I generate an interactive HTML documentation site from a legacy codebase?▼

Run the Reversa core extraction first to produce soul.md, chronicle.md, and SDD specs, then invoke /reversa-docs. It orchestrates four agents that render architecture, metrics, glossary, and feature pages into a self-contained `_reversa_docs/` mini-site.

How to create a 3D code architecture visualization that works offline?▼

This Skill downloads Three.js, D3, and Highcharts into a local `assets/vendor/` folder and injects data through `assets/js/data.js`, so the 3D Code City and dashboards work via file:// with no server or internet connection.

Does the generated documentation site require a web server to open?▼

No. The Publisher agent embeds all data in JavaScript files and vendors all libraries locally, so you can open `_reversa_docs/index.html` with a double click. A local http.server is only suggested for hot-reload during editing.

What happens if the Reversa extraction artifacts are missing?▼

The Skill detects available sources against expected_sources.yaml and omits dependent pages gracefully. If no sources exist at all, it offers to generate only a minimal index page or prompts you to run /reversa first.

Can I regenerate only part of the documentation site?▼

Yes. On subsequent runs the Skill reads `.state.json` and offers options to regenerate everything, a single agent's pages, or one specific page. A timestamped backup is always created before any destructive write.

What are the limitations of the file:// based HTML documentation approach?▼

Pages cannot use fetch() for local files because CORS blocks null origins, so all data must be embedded in JavaScript. CDN script tags are also disallowed, requiring all libraries to be vendored locally during generation.

Related Skills

Explore More Software Engineering Skills→
lacsousalacsousa

reversa-docs

Generates a self-contained HTML mini-site documenting project architecture, metrics, and features.

Community
Advanced
slashwhyslashwhy
5

architectural-documentation

Generate templates for implementation plans, ADRs, API specifications, and migration guides.

Official
Basic
Markson22Markson22

reversa-docs-analyst

Convert software project quantitative data into visual dashboards and timelines.

Community
Advanced
hnabyz-bothnabyz-bot

moai-docs-generation

Generate API references and user manuals from source code using Sphinx, MkDocs, TypeDoc, or Docusaurus.

Community
Intermediate