RAG Architect
Designs retrieval pipelines (chunking, embedding, hybrid search, re-rank, evals).
Preview
What this package looks like once your agent has it.
$ npx super-agent install ai-rag-architect → resolving ai-rag-architect@0.1.0 → runtimes ......... any MCP client → scopes ........... agent:upgrade, registry:read → size ............. — ✓ RAG Architect is available to your agent # or point any MCP client at the gateway: # https://superagentskill.com/api/public/mcp
Previews are rendered from this package's published content (install commands, system prompt, examples) — not marketing screenshots.
Description
Designs retrieval pipelines (chunking, embedding, hybrid search, re-rank, evals).
System prompt
The exact instructions this package installs into your agent.
You are "RAG Architect", a senior specialist skill in ai.
Mission: Design an end-to-end RAG pipeline with measurable retrieval quality and latency budget.
Operating rules:
- Always specify chunking, embedding model, index, retrieval, re-rank, generation, eval.
- Quote latency and cost per query target up front.
- Include eval with golden Q/A and retrieval precision@k.
- Reject naive 'just embed and search' designs for production.
Output discipline: be concrete, quantified and opinionated. Refuse to produce generic advice. When inputs are missing, list the 3 questions you need answered before proceeding.Real-world examples
Internal docs Q&A over 50k pages, p95 < 2s, $0.005/query.
Stats
Adoption, reception and performance for this package.
No published performance metrics yet.
Install instructions
Five ways in — pick the one your client supports.
Open Skills CLI (skills.sh)
Standard SKILL.md install for Claude Code, Cursor, Codex, Copilot, Windsurf, Gemini, Cline, Zed and more. No account needed.
npx skills add criptogus/agent-evolve-network/ai-rag-architectnpx skills updatePrefer a portable package? Download the Agent Plugin (.zip) — conformant with the agent-plugins.org v1.0.0 spec.
Every package is Ed25519-signed for integrity and traceability. Verify with the signature sidecar and our public key.
Agent Plugin endpoints — /plugin.json + /mcp.json
Load this skill as a portable Agent Plugins package. Any conformant client reads the manifest, then the MCP config, then exposes the skill's tools.
https://superagentskill.com/api/public/plugins/ai-rag-architect/plugin.jsonhttps://superagentskill.com/api/public/plugins/ai-rag-architect/mcp.json- Point your agent at
https://superagentskill.com/api/public/plugins/ai-rag-architect/plugin.json. - The agent fetches
/mcp.jsonto discover the MCP server URL. - It loads the skill from
skills/ai-rag-architect/SKILL.md. - Call any listed tool — no account required for read tools.
Prefer the full archive? Download the .zip and verify the signature sidecar.
MCP gateway — always the current graded version
Add this URL as an MCP server in Claude, Hermes, Cursor or ChatGPT. This package is included automatically.
https://superagentskill.com/api/public/mcpSAK CLI
Install a pinned version into the current project.
npx super-agent install ai-rag-architectnpx super-agent install ai-rag-architect@0.1.0Copy / paste
Paste the system prompt above into any assistant that has no MCP support.
Open in playground →Changelog
Every published release, newest first.
Versions
| Version | Status | Released | Notes | |
|---|---|---|---|---|
| 0.1.0 | stable | 3 months ago |
Compatibility
Compatibility is verified through the MCP gateway across major agent runtimes. Partial support means the package works but may need manual schema mapping or feature limitations.
Reviews
Reviews & ratings
Only verified buyers (paid) or users with at least one successful run (free) can rate.