RAG Production Engineering
v1.0.0Build, optimize, and operate production-ready Retrieval-Augmented Generation systems with best practices in architecture, chunking, embedding, retrieval, eva...
⭐ 0· 96·0 current·0 all-time
MIT-0
Download zip
LicenseMIT-0 · Free to use, modify, and redistribute. No attribution required.
Security Scan
OpenClaw
Benign
high confidencePurpose & Capability
The name/description (RAG production methodology) matches the content: architecture, chunking, embeddings, retrieval, evaluation, and operations. The skill requests no binaries, env vars, or installs — appropriate for a documentation/methodology skill. Minor naming inconsistency: README examples refer to 'afrexai-rag-engineering' while registry slug is 'afrexai-rag-production' and there are external paid 'context packs' links; these are plausible but worth noting.
Instruction Scope
SKILL.md is a step-by-step playbook; it contains guidance, decision trees, and checklists only. It does not instruct the agent to read arbitrary host files, access environment variables, or send data to third-party endpoints. It does reference external tooling names and libraries as recommendations (e.g., PyMuPDF, Tesseract) but does not invoke them itself.
Install Mechanism
No install spec and no code files are present, so nothing will be written to disk or fetched during install. This is the lowest-risk install model for a skill that is documentation-only.
Credentials
The skill declares no required environment variables, credentials, or config paths. The SKILL.md does not ask for secrets. This is proportionate for a methodology/guide skill.
Persistence & Privilege
The skill is not always-included (always:false) and is user-invocable; model invocation is permitted (default) which is normal. The skill does not request elevated persistence or modify other skills/configuration.
Assessment
This skill is a documentation-style, instruction-only playbook for building production RAG systems and appears coherent with that purpose. Before installing or using it, consider: 1) Verify the publisher (source is unknown) and confirm the external links (afrexai-cto.github.io) are trustworthy. 2) Be cautious with real or sensitive data — this guide recommends tooling for domains like healthcare/finance but does not itself enforce compliance; do not feed PHI/PCI data to agents or systems unless you have appropriate controls. 3) Note the README mentions paid 'context packs' and a different package name in an example (minor inconsistency); treat those as marketing rather than functionality. 4) Because the skill can be invoked by the agent, test it first in a sandbox with non-sensitive inputs and review any suggested commands or integration steps before applying them in production. If you need stronger assurance, ask the publisher for a canonical homepage and confirm the package slug/name and ownership.Like a lobster shell, security has layers — review code before you run it.
aivk970zgqjht2fchatn5swc4tf2s83gd16chunkingvk970zgqjht2fchatn5swc4tf2s83gd16embeddingsvk970zgqjht2fchatn5swc4tf2s83gd16evaluationvk970zgqjht2fchatn5swc4tf2s83gd16latestvk970zgqjht2fchatn5swc4tf2s83gd16llmvk970zgqjht2fchatn5swc4tf2s83gd16productionvk970zgqjht2fchatn5swc4tf2s83gd16ragvk970zgqjht2fchatn5swc4tf2s83gd16retrievalvk970zgqjht2fchatn5swc4tf2s83gd16vectorvk970zgqjht2fchatn5swc4tf2s83gd16
License
MIT-0
Free to use, modify, and redistribute. No attribution required.
