build-rag-pipeline SKILL.md skillA

This file is byte-identical to the first copy the registry indexed, one of 4 indexed copies. Same content hash, so the same checks give both the same grade.

build-rag-pipeline from velimirmueller/ai-development-skills is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.

Install it, pinned
mdr add velimirmueller/ai-development-skills/build-rag-pipeline@git:20261009.b6d037a

Pins git:20261009.b6d037a in mdr.lock. Pin the fingerprint instead.

Audit grade
A, 17 of 17 checks passed
Kind
SKILL.md skill
Repository
velimirmueller/ai-development-skills
Path
skills/ai/build-rag-pipeline/SKILL.md
Versions recorded
1
Latest version
git:20261009.b6d037a, committed Oct 9, 2026
Size
7,103 bytes
Repository stars
6
License
MIT

Use when building retrieval-augmented answers over your own documents — structure-aware chunking, pinned embeddings in pgvector, hybrid vector plus full-text search with RRF, tenant isolation in the query, citations, an "I don't know" path, retrieval evals before prompt tuning.

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

# Build a RAG Pipeline

Ingest, normalize, chunk, embed, store, retrieve, answer with citations. The order of work matters: build retrieval and measure it (recall@k, MRR) **before** touching the answer prompt. Most bad RAG answers are retrieval failures that a prompt cannot fix. Store default: `ai.rag_store: pgvector` in the profile.

## 1. Audit current state

Read `.claude/stack-profile.md` (`database`, `ai.rag_store`, `ai.provider`, `languages`, `backend.track`). If absent, detect per [stack-profile.md](../../core/_shared/stack-profile.md). Change nothing yet:

```bash
grep -rln "pgvector\|halfvec\|vector(" migrations drizzle alembic src 2>/dev/null           # existing vector schema
grep -rniE "embed|chunk|similarity|cosine|<=>" src --include=*.ts --include=*.py | head       # ad hoc retrieval code
ls src/platform/llm src/rag evals/datasets 2>/dev/null                                        # seam, RAG module, golden sets
grep -rn "tenant_id\|row level security\|enable row level" migrations drizzle alembic 2>/dev/null | head
psql "$DATABASE_URL" -c "select extname, extversion from pg_extension where extname='vector'"  # expect 0.8.3 or later
```
…

Read the whole file at its exact version.

How to install

The exact contents, by fingerprint
mdr add velimirmueller/ai-development-skills/build-rag-pipeline@sha256:5af20c203fb3a8f7

The line at the top of this page pins the label git:20261009.b6d037a, 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.

Badge

mdr badge

[![mdr](https://markdownregistry.com/badge/art_skhm7lsqgkv6ipvd.svg)](https://markdownregistry.com/a/art_skhm7lsqgkv6ipvd)

0 badge image fetches in 30 days. What the badge shows.

Versions

The registry has recorded 1 version of this file, committed on Oct 9, 2026.

versioncommittedcommitsizeaudit
git:20261009.b6d037a latest2026-10-09 b6d037a 7,103 BA view

Audit of the latest version

A  17 of 17 checks passed. Fixed automatic checks with no AI involved, so the same checks give the same answer every run.
  • pass: Frontmatter block present
  • pass: Frontmatter declares a name
  • pass: Frontmatter declares a description
  • pass: Size between 200 bytes and 200 KB (7103 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

GitHub

velimirmueller/ai-development-skills · 6 stars · license MIT · pushed 2026-10-23 · branch main

API

GET https://markdownregistry.com/api/v1/artifacts/art_skhm7lsqgkv6ipvd
GET https://markdownregistry.com/api/v1/resolve?ref=velimirmueller/ai-development-skills/build-rag-pipeline
GET https://markdownregistry.com/api/v1/blob/5af20c203fb3a8f790009ab8ad16b93b2a7c893c9bd8ae0d63603c2eef6ea168

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.

More from velimirmueller/ai-development-skills

build-llm-seam SKILL.md skill
velimirmueller/ai-development-skills · skills/ai/build-llm-seam/SKILL.md · Use when adding the first LLM call to a service, or when model calls are scattered through it — one module owns every…
git:20261009.d042141 · audit A · 6 stars
build-mcp-server SKILL.md skill
velimirmueller/ai-development-skills · skills/ai/build-mcp-server/SKILL.md · Use when exposing a service or dataset to AI clients through the Model Context Protocol — few task-shaped tools with…
git:20261009.d042141 · audit B · 6 stars
secure-llm-features SKILL.md skill
velimirmueller/ai-development-skills · skills/ai/secure-llm-features/SKILL.md · Use when shipping or reviewing an LLM feature that reads untrusted text or has tools — prompt-injection threat model…
git:20261009.b6d037a · audit B · 6 stars
set-up-llm-evals SKILL.md skill
velimirmueller/ai-development-skills · skills/ai/set-up-llm-evals/SKILL.md · Use when an LLM feature ships on vibes — golden datasets in the repo, deterministic checks first, an LLM judge with a…
git:20261009.d58ee01 · audit A · 6 stars
build-nextjs-backend SKILL.md skill
velimirmueller/ai-development-skills · skills/backend/build-nextjs-backend/SKILL.md · Use when building or reviewing the server side of a Next.js 16 App Router app — a server-only data access layer that…
git:20261009.d042141 · audit B · 6 stars
build-supabase-edge-function SKILL.md skill
velimirmueller/ai-development-skills · skills/backend/build-supabase-edge-function/SKILL.md · Use when logic must run server-side next to Supabase — a webhook, a cron or database-triggered job, a third-party call…
git:20261009.d58ee01 · audit B · 6 stars
configure-backend-tests SKILL.md skill
velimirmueller/ai-development-skills · skills/backend/configure-backend-tests/SKILL.md · Use when a backend service needs a test setup or its tests mock the database. Builds the pyramid - pure unit tests…
git:20261009.24f5e39 · audit A · 6 stars
design-http-api SKILL.md skill
velimirmueller/ai-development-skills · skills/backend/design-http-api/SKILL.md · Use when adding or changing HTTP endpoints, or when the frontend needs typed calls — sets the OpenAPI 3.1 contract, RFC…
git:20261009.d042141 · audit A · 6 stars
harden-backend SKILL.md skill
velimirmueller/ai-development-skills · skills/backend/harden-backend/SKILL.md · Use when a backend service is about to take untrusted traffic or fails a security review. Adds edge validation, rate…
git:20261009.d042141 · audit A · 6 stars
scaffold-fastapi-service SKILL.md skill
velimirmueller/ai-development-skills · skills/backend/scaffold-fastapi-service/SKILL.md · Use when starting a Python HTTP API or adding a service to a repo with no FastAPI app yet — scaffolds a uv src-layout…
git:20261009.24f5e39 · audit A · 6 stars
scaffold-go-service SKILL.md skill
velimirmueller/ai-development-skills · skills/backend/scaffold-go-service/SKILL.md · Use when starting a Go HTTP service or adding one to a repo with no Go module yet — scaffolds stdlib net/http (1.22+…
git:20261009.e2b6168 · audit B · 6 stars
scaffold-hono-service SKILL.md skill
velimirmueller/ai-development-skills · skills/backend/scaffold-hono-service/SKILL.md · Use when starting a TypeScript HTTP API or adding a service to a repo with no Hono app yet — scaffolds a strict-TS Hono…
git:20261009.e2b6168 · audit A · 6 stars

Every file in velimirmueller/ai-development-skills

Other files named build-rag-pipeline

build-rag-pipeline SKILL.md skill
velimirmueller/claude-development-skills · skills/ai/build-rag-pipeline/SKILL.md · Use when building retrieval-augmented answers over your own documents — structure-aware chunking, pinned embeddings in…
git:20261009.b6d037a · audit A · 6 stars
build-rag-pipeline SKILL.md skill
velimirmueller/lab-claude-skills · skills/ai/build-rag-pipeline/SKILL.md · Use when building retrieval-augmented answers over your own documents — structure-aware chunking, pinned embeddings in…
git:20261009.b6d037a · audit A · 5 stars
build-rag-pipeline SKILL.md skill
velimirmueller/claude-skills · skills/ai/build-rag-pipeline/SKILL.md · Use when building retrieval-augmented answers over your own documents — structure-aware chunking, pinned embeddings in…
git:20261009.b6d037a · audit A · 6 stars

Browse by kind, by grade A, or by owner.