Engineering
import-content avatar

import-content

Manually import markdown files into the Kurt database, fix ingestion errors, and manage document metadata via local file system synchronization.

Introduction

The import-content skill serves as a critical manual fallback and operational tool for the Kurt content pipeline. It is designed for technical users who need to bypass failed automatic web ingestion by directly importing pre-processed markdown files from the local source directory into the Kurt SQLite database. This ensures that content remains synchronized even when WebFetch or automated hooks encounter network issues or parsing failures. It bridges the gap between raw local files and the database-indexed content required for downstream workflows like the content-writing-skill, ensuring high-quality metadata extraction through YAML frontmatter.

  • Fixes ERROR records in the Kurt database by linking them to corrected local markdown source files.

  • Performs bulk imports for large datasets, migrations, or backup restoration via shell scripting.

  • Automates metadata extraction from YAML frontmatter, supporting fields like title, description, author, and published_date.

  • Integrates with PostToolUse hooks to watch the /sources/ directory and automatically update document records after manual edits.

  • Enables precise indexing of manually created files that were not originally captured by site crawlers.

  • Ensure all markdown files contain valid YAML frontmatter at the top of the file to populate the database schema correctly.

  • Use the provided Python scripts in .claude/scripts/ to bridge document IDs with local file paths during bulk recovery operations.

  • When performing manual ingestion, follow up with the kurt index command to trigger the document intelligence pipeline for newly imported content.

  • The tool is strictly limited to files within the local source paths; ensure file permissions allow the agent to read source files.

  • If the pyyaml library is missing, metadata extraction will fail silently; ensure the Kurt environment is fully initialized via pip install kurt-core.

  • This utility is intended for advanced content management and recovery; always verify database status with kurt content list after performing bulk actions.

Repository Stats

Stars
2
Forks
0
Open Issues
0
Language
Python
Default Branch
main
Sync Status
Idle
Last Synced
May 3, 2026, 08:27 PM
View on GitHub
import-content | Skills Hub