How do I install the Embedding Ops skill?

Run npx skillmds@latest add d-o-hub/embedding-ops in your terminal (requires Node.js), paste this page's agent-chat prompt into Claude, Cursor, or any MCP-connected agent, or download the SKILL.md file and copy it into your agent's skills directory.

Is Embedding Ops safe to use?

This skill has not completed SkillMD's automated safety review yet. SkillMD never runs a skill's scripts for you; review the SKILL.md before installing.

Which AI agents work with Embedding Ops?

This skill is tagged as working with Claude Code, Claude.ai, OpenAI Codex. SKILL.md is an open format, so most agents that read a skills directory can load it too.

Is Embedding Ops free to use?

Yes. Installing skills from SkillMD is free, and the skill stays under its author's original license.

Who published Embedding Ops?

d-o-hub (@d-o-hub) published this skill. Their other Agent Skills are listed on their SkillMD profile.

Embedding Ops by d-o-hub — Agent Skill

Name: Embedding Ops
Author: d-o-hub

File contents

Embedding Operations

When to Use

Configuring embedding providers (OpenAI, Cohere, Ollama, local)
Testing embedding connectivity and quality
Benchmarking provider performance
Rebuilding embedding indices
Debugging semantic search issues

CLI Commands

Command	Purpose
`do-memory-cli embedding config`	Show current embedding configuration
`do-memory-cli embedding test`	Test embedding provider connectivity
`do-memory-cli embedding list-providers`	List available providers
`do-memory-cli embedding benchmark`	Benchmark provider latency/throughput
`do-memory-cli embedding rebuild`	Rebuild embedding index from episodes
`do-memory-cli embedding enable`	Enable embeddings (session only)
`do-memory-cli embedding disable`	Disable embeddings (session only)

MCP Tools

Tool	Parameters	Purpose
`configure_embeddings`	provider, model, dimension, api_key_env	Configure embedding provider
`query_semantic_memory`	query, limit, threshold	Semantic similarity search
`test_embeddings`	text	Test embedding generation
`generate_embedding`	text, provider	Generate embedding vector
`search_by_embedding`	embedding, limit	Search by raw vector
`embedding_provider_status`	-	Check provider health

Configuration

Set in config file or environment:

[embeddings]
enabled = true
provider = "openai"  # openai | cohere | ollama | local
model = "text-embedding-3-small"
dimension = 1536
api_key_env = "OPENAI_API_KEY"

Provider Setup

OpenAI

export OPENAI_API_KEY="sk-..."
do-memory-cli embedding config
do-memory-cli embedding test

Ollama (local)

ollama pull nomic-embed-text
# Config: provider = "ollama", model = "nomic-embed-text", dimension = 768

Troubleshooting

Test fails: Check API key env var is set, provider is reachable
Slow search: Run benchmark to identify latency; consider local provider
Poor results: Check dimension matches model; rebuild index after provider change

Known Limitations

enable/disable commands affect current session only (no persistence)
--semantic-search flag on episode list is declared but not yet wired
HNSW index save() is a no-op when hnsw feature is enabled

---name: embedding-opsdescription: Configure, test, benchmark, and manage embedding providers for semantic search and vector operations---# Embedding Operations## When to Use- Configuring embedding providers (OpenAI, Cohere, Ollama, local)- Testing embedding connectivity and quality- Benchmarking provider performance- Rebuilding embedding indices- Debugging semantic search issues## CLI Commands| Command | Purpose ||---------|---------|| `do-memory-cli embedding config` | Show current embedding configuration || `do-memory-cli embedding test` | Test embedding provider connectivity || `do-memory-cli embedding list-providers` | List available providers || `do-memory-cli embedding benchmark` | Benchmark provider latency/throughput || `do-memory-cli embedding rebuild` | Rebuild embedding index from episodes || `do-memory-cli embedding enable` | Enable embeddings (session only) || `do-memory-cli embedding disable` | Disable embeddings (session only) |## MCP Tools| Tool | Parameters | Purpose ||------|-----------|---------|| `configure_embeddings` | provider, model, dimension, api_key_env | Configure embedding provider || `query_semantic_memory` | query, limit, threshold | Semantic similarity search || `test_embeddings` | text | Test embedding generation || `generate_embedding` | text, provider | Generate embedding vector || `search_by_embedding` | embedding, limit | Search by raw vector || `embedding_provider_status` | - | Check provider health |## ConfigurationSet in config file or environment:```toml[embeddings]enabled = trueprovider = "openai" # openai | cohere | ollama | localmodel = "text-embedding-3-small"dimension = 1536api_key_env = "OPENAI_API_KEY"```## Provider Setup### OpenAI```bashexport OPENAI_API_KEY="sk-..."do-memory-cli embedding configdo-memory-cli embedding test```### Ollama (local)```bashollama pull nomic-embed-text# Config: provider = "ollama", model = "nomic-embed-text", dimension = 768```## Troubleshooting1. **Test fails**: Check API key env var is set, provider is reachable2. **Slow search**: Run `benchmark` to identify latency; consider local provider3. **Poor results**: Check dimension matches model; rebuild index after provider change## Known Limitations- `enable`/`disable` commands affect current session only (no persistence)- `--semantic-search` flag on `episode list` is declared but not yet wired- HNSW index `save()` is a no-op when `hnsw` feature is enabled

Frequently asked questions

Embedding Ops