SkillHub ClubWrite Technical DocsFull StackTech Writer

nextura-content-ingestion

Convert external content to SSOT format. Use when ingesting from Confluence, documents, or external sources.

Packaged view

This page reorganizes the original catalog entry around fit, installability, and workflow context first. The original raw source lives below.

Stars

Hot score

Updated

March 20, 2026

Overall rating

C2.2

Composite score

2.2

Best-practice grade

S100.0

Install command

npx @skill-hub/cli install alicoding-nextura-nextura-content-ingestion

Repository

alicoding/nextura

Skill path: .claude/skills/nextura-content-ingestion

Convert external content to SSOT format. Use when ingesting from Confluence, documents, or external sources.

Open repository

Best for

Primary workflow: Write Technical Docs.

Technical facets: Full Stack, Tech Writer.

Target audience: everyone.

License: Unknown.

Original source

Catalog source: SkillHub Club.

Repository owner: alicoding.

This is still a mirrored public skill entry. Review the repository before installing into production workflows.

What it helps with

Install nextura-content-ingestion into Claude Code, Codex CLI, Gemini CLI, or OpenCode workflows
Review https://github.com/alicoding/nextura before adding nextura-content-ingestion to shared team environments
Use nextura-content-ingestion for development workflows

Works across

Claude CodeCodex CLIGemini CLIOpenCode

Favorites: 0.

Sub-skills: 0.

Aggregator: No.

Original source / Raw SKILL.md

---
name: nextura-content-ingestion
scope: nextura
description: >
  Convert external content to SSOT format.
  Use when ingesting from Confluence, documents, or external sources.
version: 3.0.0
triggers:
  - ingest content
  - convert to markdown
  - crawl confluence
  - import from
  - extract requirements

gates:
  post:
    - "make validate"
---

# Content Ingestion

Convert external sources to SSOT YAML or markdown.

---

## Quick Start

1. Identify source (Confluence, PDF, etc.)
2. Determine output format (YAML entity or markdown)
3. Run conversion
4. Validate and record provenance

---

## Source Types

| Source | Tool | Output |
|--------|------|--------|
| Confluence | crawlee | markdown + YAML |
| PDF | pdfplumber | markdown |
| HTML | markdownify | markdown |
| Word | python-docx | markdown |
| Existing docs | n/a | YAML entities |

---

## Output Decision

| Content Type | Output Format |
|--------------|---------------|
| Requirements | YAML (REQ-XXX.yaml) |
| Decisions | YAML (ADR-XXX.yaml) |
| Procedures | Markdown (docs/) |
| Reference | Markdown (docs/) |

---

## Provenance Tracking

Every ingested entity must track source:

```yaml
provenance:
  source_type: confluence
  source_url: "https://wiki.example.com/page/123"
  ingested_at: "2026-01-06T10:00:00Z"
  ingested_by: "claude"
```

---

## STOP GATES

### STOP GATE 1: Output Format Decided

**Check:** Is output YAML or markdown?
**Pass:** Format determined from content type
**Fail:** STOP. Decide format first.

### STOP GATE 2: Source Accessible

**Check:** Can source be accessed?
**Pass:** Auth and connectivity verified
**Fail:** STOP. Fix access issues.

### STOP GATE 3: Provenance Recorded

**Check:** Is source tracked?
**Pass:** provenance field populated
**Fail:** STOP. Add provenance.

---

## Quick Reference

```
LIBRARIES
markdownify     # HTML to markdown
python-frontmatter  # Frontmatter handling
crawlee         # Web crawling
pdfplumber      # PDF extraction

NEVER
- Lose source URL
- Skip validation
- Create without provenance
```

---

## Reference Files

- [reference/converters.md](reference/converters.md) - Conversion patterns
- [reference/provenance.md](reference/provenance.md) - Provenance schema