skills.rest
garochee33
garochee33COMMUNITY
Explore all skills by this author →
WebsiteGitHub

dsh-ingest

Rebuild the DSH knowledge graph and agent registry in SQLite and ChromaDB.

3|Updated Apr 18, 2026
Search Tags:#knowledge graph#verification#sqlite#ingestion#recovery#chromadb
One-click install
npx skills add https://github.com/garochee33/DSH --skill dsh-ingest
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: dsh-ingest
Source: https://github.com/garochee33/DSH/tree/main/kb/claude/skills/dsh-ingest
Command: npx skills add https://github.com/garochee33/DSH --skill dsh-ingest

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires sqlite3, chromadb, sentence-transformers.

What problem does it solve?

This Skill restores and refreshes the DSH node’s persistent knowledge state when the database is corrupted, new knowledge has been added, or ingestion needs to be rerun after environment changes.

Core Features & Use Cases

  • Registry repair: Recreates and upserts the Claude agent, skills, tools, and stack records in the local SQLite knowledge database.
  • Knowledge re-indexing: Re-ingests repository knowledge from kb/, logs/, docs, and agent source files into ChromaDB for semantic retrieval.
  • Verification and recovery: Checks dependency imports, skill-module loading, and akashic write/query behavior to confirm the node is ready for spore.sh activation.
  • Use case: Run this after a failed upgrade, missing knowledge base updates, or a suspected local state corruption to bring the system back to a consistent operational state.

Quick Start

Use the dsh-ingest skill to restore the local knowledge graph and verify that the node is ready for spore.sh.

Frequently Asked Questions about dsh-ingest

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

FAQPage Schema
How do I rebuild a knowledge graph in ChromaDB after local state corruption?▼

Rebuilding a knowledge graph in ChromaDB after corruption requires re-ingesting repository knowledge from source files and upserting registry records in SQLite, then validating dependency imports and query behavior to restore node readiness.

When do I need to re-index repository content for semantic retrieval?▼

You need to re-index repository content for semantic retrieval after a failed upgrade, missing knowledge base updates, suspected state corruption, or dependency changes that invalidate the existing persistent knowledge graph.

Does knowledge graph recovery require SQLite and sentence-transformers?▼

Yes, knowledge graph recovery requires SQLite, ChromaDB, and sentence-transformers, plus repository-relative scripts to complete deterministic repair, database upserts, and end-to-end verification steps.

What's the best way to verify agent registry readiness after re-ingestion?▼

The best way to verify agent registry readiness after re-ingestion is to check dependency imports, skill-module loading, and akashic write/query behavior to confirm the node is fully operational.

Why does knowledge ingestion fail after environment or dependency changes?▼

Knowledge ingestion fails after environment or dependency changes because the persistent SQLite database and ChromaDB indexes become inconsistent, requiring a full deterministic repair and re-indexing workflow to restore operational state.

Related Skills

Explore More Software Engineering Skills→
bahayonghangbahayonghang
16

memory-system

Index Markdown notes into a local SQLite vector/full-text index.

Community
Intermediate
KakiseKakise
1

kitty:annotate

Generate node summaries, semantic tags, and role descriptions for codebase graph annotations.

Community
Advanced
SteveGJonesSteveGJones
41

kb-ingest

Ingest local files, URLs, or pasted content into a knowledge base.

Community
Intermediate
letta-ailetta-ai
134

sqlite-db-truncate

Recover data from corrupted or truncated SQLite database files via binary parsing.

Official
Advanced