hydramem-ingest
Adds documentation to a local knowledge base, enabling efficient semantic search through chunking and embedding.
Install
mkdir -p .claude/skills/hydramem-ingest && curl -L -o skill.zip "https://agentskills.codes/api/skills/download/17969" && unzip -o skill.zip -d .claude/skills/hydramem-ingest && rm skill.zipInstalls to .claude/skills/hydramem-ingest
Activation
This is the description your AI agent reads to decide when to run this skill — the better it matches your request, the more reliably it fires.
Ingest one or more Markdown files into the HydraMem knowledge base. Chunks the documents, generates embeddings, extracts entities, and stores everything locally. No data leaves the machine.Key capabilities
- →Ingest single Markdown files into the knowledge base.
- →Ingest directories of Markdown files recursively.
- →Chunk documents for processing.
- →Generate embeddings for ingested content.
- →Extract entities from Markdown files.
How it works
The skill processes Markdown files by chunking them, generating embeddings, extracting entities, and storing all data locally within the HydraMem knowledge base.
Inputs & outputs
When to use hydramem-ingest
- →Add documentation to knowledge base
- →Ingest project docs folder
- →Update searchable project knowledge
- →Prepare docs for AI context
About this skill
hydramem-ingest
Use this skill when the user wants to add documents to the knowledge base.
When to invoke
- "Add this file to my knowledge base."
- "Ingest all docs in the
./docsfolder." - After creating or updating a Markdown document that should be searchable.
Workflow
Single file
ingest_markdown(file_path=<path>, project=<project>)
Directory
ingest_directory_tool(directory=<path>, project=<project>, recursive=true)
After ingestion
- Report the number of chunks and entities created.
- Suggest running
hydramem-gardento let the Night Gardener build relations between the new content and existing knowledge.
Notes
- Only
.mdfiles are processed. - Re-ingesting the same file is safe (chunks are upserted by hash).
- Large directories (>100 files) may take a few minutes; embeddings are
generated locally via
nomic-ai/nomic-embed-text-v1.5.
When not to use it
- →When the user wants to process files other than `.md`.
- →When the user wants to transmit data externally.
- →When the user does not want to add documents to the knowledge base.
Prerequisites
Limitations
- →Only `.md` files are processed.
- →All data is stored locally; no external transmission.
- →Large directories may take a few minutes to process.
How it compares
This skill provides a local, secure method for ingesting Markdown documents into a knowledge base, ensuring no data leaves the machine, unlike cloud-based ingestion services.
Compared to similar skills
hydramem-ingest side by side with the closest alternatives in the catalog.
| Skill | Installs | Updated | Safety | Difficulty |
|---|---|---|---|---|
| hydramem-ingest (this skill) | 0 | 27d | No flags | Beginner |
| agent-memory-mcp | 8 | 6mo | Review | Intermediate |
| qdrant-vector-search | 18 | 8mo | Review | Advanced |
| langchain | 26 | 8mo | Review | Intermediate |
Try saying
Example prompts that trigger this skill in your AI assistant.
You might also like
agent-memory-mcp
davila7
A hybrid memory system that provides persistent, searchable knowledge management for AI agents (Architecture, Patterns, Decisions).
qdrant-vector-search
zechenzhangAGI
High-performance vector similarity search engine for RAG and semantic search. Use when building production RAG systems requiring fast nearest neighbor search, hybrid search with filtering, or scalable vector storage with Rust-powered performance.
langchain
zechenzhangAGI
Framework for building LLM-powered applications with agents, chains, and RAG. Supports multiple providers (OpenAI, Anthropic, Google), 500+ integrations, ReAct agents, tool calling, memory management, and vector store retrieval. Use for building chatbots, question-answering systems, autonomous agents, or RAG applications. Best for rapid prototyping and production deployments.
cocoindex
cocoindex-io
Comprehensive toolkit for developing with the CocoIndex library. Use when users need to create data transformation pipelines (flows), write custom functions, or operate flows via CLI or API. Covers building ETL workflows for AI data processing, including embedding documents into vector databases, building knowledge graphs, creating search indexes, or processing data streams with incremental updates.
rag-implementation
wshobson
Build Retrieval-Augmented Generation (RAG) systems for LLM applications with vector databases and semantic search. Use when implementing knowledge-grounded AI, building document Q&A systems, or integrating LLMs with external knowledge bases.
hybrid-search-implementation
wshobson
Combine vector and keyword search for improved retrieval. Use when implementing RAG systems, building search engines, or when neither approach alone provides sufficient recall.