Borrowing it
Nothing to install: this file belongs to sagar-shirwalkar/collibra-atlas. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/sagar-shirwalkar/collibra-atlas/main/.agents/skills/embedding-strategies/SKILL.mdgit clone --depth 1 https://github.com/sagar-shirwalkar/collibra-atlasWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/sagar-shirwalkar/collibra-atlas/embedding-strategies)<a href="https://agentmods.dev/skills/sagar-shirwalkar/collibra-atlas/embedding-strategies"><img src="https://agentmods.dev/badge/skills/sagar-shirwalkar/collibra-atlas/embedding-strategies/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/sagar-shirwalkar/collibra-atlas/embedding-strategies"><img src="https://agentmods.dev/badge/skills/sagar-shirwalkar/collibra-atlas/embedding-strategies.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00067 | $0.00616 |
| Opus 5 | $0.00034 | $0.00308 |
| Sonnet 5 | $0.00013 | $0.00123 |
| Haiku 4.5 | $0.00007 | $0.00062 |
Grade A, and why
embedding-strategies scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 11d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 51 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Guide to selecting, comparing, and optimizing embedding models for vector search and RAG.
Leading words
- Compare — Evaluate embedding candidates against the project's retrieval criteria (latency, dimension, domain fit). Not every model suits every workload.
- Chunk — Split documents into embeddable pieces while preserving semantic boundaries. The chunking strategy is as important as the model.
- Optimize — Tune the pipeline: normalize embeddings, batch requests, cache results, reduce dimensions when possible.
Phases
PHASE 1: Scout
Completion criterion: a shortlist of 2-3 embedding models that match the project's constraints (language domain, latency budget, local vs API, dimension limits).
- Identify the project's constraints: language, deployment environment (local/API), latency requirements, and cost budget.
- Compare candidate models using the comparison table in
references/details.md. - For local deployments, check ONNX/MLX compatibility and model size. For API deployments, check rate limits and pricing.
- If the project uses Claude, consider Voyage AI models (Anthropic recommended).
PHASE 2: Chunk
Completion criterion: a chunking strategy documented and implemented — chunk size, overlap, boundary detection, and preprocessing steps.
- Choose a chunk size based on your embedding model's token limit (e.g., 512 tokens for
bge-base-en-v1.5, 8191 fortext-embedding-3-large). - Pick a boundary strategy:
- Semantic boundaries (headings, paragraphs) — preserves meaning, uneven sizes.
- Fixed-size with overlap — uniform chunks, may split mid-sentence.
- Add metadata to each chunk (source, heading, position) for downstream filtering.
- Preprocess text before embedding: normalize whitespace, strip boilerplate.
PHASE 3: Optimize
Completion criterion: embedding pipeline integrated into the project's bundle build, with batch processing and optional caching.
- Normalize all embeddings to unit length (required for cosine similarity).
- Batch embed requests (e.g., 32-64 texts per batch) for throughput.
- Cache embeddings for static content to avoid recomputing on rebuild.
- If dimension reduction is needed (e.g., 3072 → 768 via PCA), evaluate the recall tradeoff before committing.
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 11d ago First seen · 51 lines · 67 tokens per session scan A 450aec80d114
embedding-strategies is a skill published in the GitHub repository sagar-shirwalkar/collibra-atlas (0 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 67 tokens to every session and 616 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
embeddings
Vector embeddings with HNSW indexing, sql.js persistence, and hyperbolic support. 75x faster with agentic-flow integration. Use when: semantic search, pattern matching, similarity queries, knowledge retrieval. Skip when: exact text matching, simple lookups, no semantic understanding needed.
agent-platform-rag-engine-management
Manage and query Agent Platform RAG Engine Corpora and retrieve grounded contexts using the Google GenAI SDK. Use when listing RAG corpora or files, inspecting a corpus, retrieving contexts, or generating content grounded in a RAG corpus. Do not use for standard database queries (use SQL/Spanner skills), Google…
llm-app-patterns
Production-ready patterns for building LLM applications. Covers RAG pipelines, agent architectures, prompt IDEs, and LLMOps monitoring. Use when designing AI applications, implementing RAG, building agents, or setting up LLM observability.
9router-embeddings
Generate vector embeddings via 9Router /v1/embeddings using OpenAI / Gemini / Mistral / Voyage / Nvidia / GitHub embedding models for RAG, semantic search, similarity. Use when the user wants embeddings, vectors, RAG, semantic search, or to embed text.
azure-search-documents-dotnet
Azure AI Search SDK for .NET (Azure.Search.Documents). Use for building search applications with full-text, vector, semantic, and hybrid search. Covers SearchClient (queries, document CRUD), SearchIndexClient (index management), and SearchIndexerClient (indexers, skillsets). Triggers: "Azure Search .NET"…
browserwing-admin
Manage and operate BrowserWing — an intelligent browser automation platform. Install dependencies, configure LLM, create/manage/execute automation scripts, use AI-driven exploration to generate scripts, browse the script marketplace, and troubleshoot issues.