rag-pipelines SKILL.md skillA
rag-pipelines from jnpiyush/agentx is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.
mdr add jnpiyush/agentx/rag-pipelines@v1.0.0Pins v1.0.0 in mdr.lock. Pin the fingerprint instead.
- Audit grade
- A, 17 of 17 checks passed
- Kind
- SKILL.md skill
- Repository
- jnpiyush/agentx
- Path
.github/skills/ai-systems/rag-pipelines/SKILL.md- Versions recorded
- 5
- Latest version
- v1.0.0, committed Sep 15, 2026
- First version recorded
- Mar 1, 2026
- Size
- 11,694 bytes
- Repository stars
- 19
- License
- Apache-2.0
Design and build production RAG (Retrieval-Augmented Generation) pipelines. Use when implementing document ingestion, chunking strategies, embedding selection, vector search, hybrid retrieval, reranking, or generation with grounding.
Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file the same grade.
What the file says
# RAG Pipelines > **Purpose**: Build production-grade Retrieval-Augmented Generation systems that ground LLM responses in authoritative knowledge. --- ## When to Use This Skill - Building document Q&A systems grounded in enterprise knowledge - Implementing semantic search over unstructured documents - Designing chunking strategies for different document types - Selecting and configuring vector databases for retrieval - Implementing hybrid search (keyword + semantic) and reranking - Optimizing retrieval quality (precision, recall, faithfulness) ## Prerequisites - Document corpus to index - Embedding model access (OpenAI, Azure OpenAI, or open-source) - Vector store or search service - LLM for generation ## Decision Tree ``` Building a RAG system? +- What type of documents? | +- Short, structured (FAQ, KB articles)? | -> Small chunks (256-512 tokens), simple splitting | +- Long, unstructured (reports, papers)? | -> Semantic chunking, hierarchical retrieval | +- Code repositories? | -> AST-aware chunking, function-level | +- Multi-modal (PDFs with tables/images)? | -> Document intelligence + specialized parsers +- What query patterns? …
Read the whole file at its exact version.
How to install
mdr add jnpiyush/agentx/rag-pipelines@sha256:c1d080a58f61077eThe line at the top of this page pins the label v1.0.0, which is what most people want. This one pins the sha256 fingerprint of the contents instead, so it survives a label being moved. Either way the exact version is written to mdr.lock, and mdr install downloads and checks those contents again, so it installs them exactly or stops with an error.
[](https://markdownregistry.com/a/art_njm43dryh4uf7dsh)
4 badge image fetches in 30 days. What the badge shows.
Versions
The registry has recorded 5 versions of this file, between Mar 1, 2026 and Sep 15, 2026, about one every 49 days.
| version | committed | commit | size | audit | |
|---|---|---|---|---|---|
| v1.0.0 latest | 2026-09-15 | f17c505 | 11,694 B | A | view · diff |
| v1.0.0 | 2026-04-22 | 7f3a017 | 11,692 B | A | view · diff |
| v1.0.0 | 2026-03-04 | 848caee | 11,679 B | A | view · diff |
| v1.0.0 | 2026-03-01 | 969f335 | 11,674 B | A | view · diff |
| v1.0.0 | 2026-03-01 | bb11a09 | 10,650 B | A | view |
Audit of the latest version
- pass: Frontmatter block present
- pass: Frontmatter declares a name
- pass: Frontmatter declares a description
- pass: Size between 200 bytes and 200 KB (11694 bytes)
- pass: No zero-width or bidi control characters
- pass: No instruction hidden inside an HTML comment
- pass: No link to an exfiltration or paste host
- pass: No credential-shaped string
- pass: No instruction to send local credentials anywhere
- pass: No text hidden with inline styles
- pass: No prompt-injection phrasing
- pass: No curl or wget piped into a shell
- pass: No recursive delete of root, home or parent
- pass: No instruction to read or print local credentials
- pass: No base64 blob over 200 characters
- pass: No link to a raw IP address
- pass: No script tag
Source
jnpiyush/agentx · 19 stars · license Apache-2.0 · pushed 2026-11-04 · branch master
API
GET https://markdownregistry.com/api/v1/artifacts/art_njm43dryh4uf7dsh GET https://markdownregistry.com/api/v1/resolve?ref=jnpiyush/agentx/rag-pipelines GET https://markdownregistry.com/api/v1/blob/c1d080a58f61077ec7a2054e83a09b068197f65e46ab20bdeab9a627b2724eeb
Your AI assistant does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.
Guides: the SKILL.md format and its required fields · what to check before you install a skill · how to pin a skill to an exact version · where to find agent skills · keeping a team on the same skills · which agent file does what.