Ready to supercharge your AI agents?

Install any skill in seconds. Free to start, no credit card required.

Get Started Free →

Embedding Strategies · wshobson | DecimalAI

ai mlby wshobson

Embedding Strategies

wshobson/embedding-strategies

Source wshobson/agents ↗License MIT

Select and optimize embedding models for semantic search and RAG applications.

SkillScore96Maintained

Automatic

AI Engineer pack

Last verified 8/7/2026

What it changes

Passed 22 of 23 test cases with the skill, and 20 of 23 without it.

Without skill87%

With skill96%

Checks it passed that the model alone missed

Recommends voyage-3-large for high-accuracy Claude applications
Recommends multilingual-e5-large for multi-language vector search

2 fixed20 passed either way1 still failing0 broke

Pass-rate lift: +9 pp
Tokens: +16%
Agent turns: 0%
Response time: -19%

Model gemini-3.6-flashMeasured 8/7/2026v122 of 23 cases passed with skill

Tokens, turns and time describe resource use, not a dollar price.

Use this skill

Save it into your project's skills folder. Claude Code picks it up in its next session.

curl -fsSL --create-dirs -o .claude/skills/wshobson-embedding-strategies/SKILL.md https://app.decimal.ai/s/wshobson-embedding-strategies/SKILL.md

Want it pinned and updatable? pip install "decimalai>=0.15", then decimalai skills add wshobson-embedding-strategies, and start Claude Code with claude --plugin-dir "$(git rev-parse --show-toplevel)/.agents"

1 · One-time — install the CLI (docs ↗)

pip install "decimalai>=0.15"

2 · Get the skill — writes .agents/skills/wshobson-embedding-strategies/ and pins it in .decimal/skills.lock

decimalai skills add wshobson-embedding-strategies

No CLI? Get the same file — curl · raw file

curl -fsSL --create-dirs -o .claude/skills/wshobson-embedding-strategies/SKILL.md https://app.decimal.ai/s/wshobson-embedding-strategies/SKILL.md

Raw file: /s/wshobson-embedding-strategies/SKILL.md ↗ · machine-readable summary at /s/wshobson-embedding-strategies.json ↗

Safety checks: 3 of 3 passed

Code scan CleanIntent PassedContent Clean

See it in action

One of 2 test cases the skill fixed. Same model, same prompt, with and without the skill.

1 of 2

Prompt

We are building an enterprise search platform powered by Anthropic's Claude 3.5 Sonnet. The team wants to default to OpenAI's text-embedding-3-large due to its 3072 dimensions. Which embedding model family and specific model is recommended for Claude-based applications, and what are its dimensions and token context limits?

What was checked, without and with the skill
Checked	Without skill	With skill
Recommends voyage-3-large for high-accuracy Claude applications	Missed	Passed
Identifies Voyage AI as the recommended embedding provider for Claude applications	Passed	Passed

case-03 · gemini-3.6-flash · 8/7/2026 · answers are capped and redacted

What's inside

The instructions your model reads when the skill loads.

SKILL.md60 lines2 files

Embedding Strategies

Guide to selecting and optimizing embedding models for vector search applications.

When to Use This Skill

Choosing embedding models for RAG
Optimizing chunking strategies
Fine-tuning embeddings for domains
Comparing embedding model performance
Reducing embedding dimensions
Handling multilingual content

Core Concepts

1. Embedding Model Comparison (2026)

Model	Dimensions	Max Tokens	Best For
voyage-3-large	1024	32000	Claude apps (Anthropic recommended)
voyage-3	1024	32000	Claude apps, cost-effective
voyage-code-3	1024	32000	Code search
voyage-finance-2	1024	32000	Financial documents
voyage-law-2	1024	32000	Legal documents
text-embedding-3-large	3072	8191	OpenAI apps, high accuracy
text-embedding-3-small	1536	8191	OpenAI apps, cost-effective
bge-large-en-v1.5	1024	512	Open source, local deployment
all-MiniLM-L6-v2	384	256	Fast, lightweight
multilingual-e5-large	1024	512	Multi-language

2. Embedding Pipeline

Document → Chunking → Preprocessing → Embedding Model → Vector
                ↓
        [Overlap, Size]  [Clean, Normalize]  [API/Local]

Templates and detailed worked examples

Track record

Benchmark

22 / 23

test cases passed, vs 20 / 23 without

Adoption

Users: 0
Times used: 0

Safety and source details

SkillSafety

✓ 3 of 3 passed

Code scan15 of 15 checks clean

0 critical · 0 warning · 0 info — scanner v4 — 8/3/2026

View 15 scanner checks

live_secretremote_code_executionreverse_shelldata_exfiltrationssrf_metadataagent_snoopinganti_refusaldestructive_commandsobfuscated_unicodeunicode_homoglyphopaque_blobsuspicious_urltool_overreachtrigger_abuseprompt_injection_phrasing

IntentSafe

LLM judge · does the skill do what it claims

ContentClean

LLM judge · policy & harmful-content review

Source

Imported

wshobson / agents

plugins/llm-application-dev/skills/embedding-strategies/SKILL.md

View on GitHub ↗

License MITImported 8/3/2026Version v1Bundled 1 file

Other skills for the same job

Published skills whose descriptions closely match this one, with their headline benchmark lift.

More skills from the same source and nearby in the registry, with their headline benchmark lift.

Ready to supercharge your AI agents?

See it in action

What's inside

Embedding Strategies

When to Use This Skill

Core Concepts

1. Embedding Model Comparison (2026)

2. Embedding Pipeline

Templates and detailed worked examples

Track record

Benchmark

Adoption

SkillSafety

Source

Other skills for the same job

Related skills