About

Imported from practicalswan/agent-skills (nemo-retriever/SKILL.md). Install upstream with npx skills add practicalswan/agent-skills --skill nemo-retriever. Copyright stays with the author (CC-BY-4.0 AND Apache-2.0).

nemo-retriever

Name: nemo-retriever
Author: practicalswan

The retriever CLI indexes a folder of PDFs into LanceDB (retriever ingest) and serves vector search over it (retriever query). For any task about searching/answering questions across a folder of PDFs, use this CLI — do not write a custom RAG.

Beyond PDFs and beyond semantic search. retriever ingest also handles images, Office, HTML, TXT, audio, and video — see references/setup.md for the per-format recipe and references/install.md for the install extras ([multimedia], libreoffice, ffmpeg). For non-semantic operations — page filter, verbatim quote with citation, corpus-level aggregate, chart/image caption hits — see references/query.md. Don't fall back to native Read/Grep/Python on non-PDF inputs.

Install (if `retriever` is missing)

If command -v retriever returns nothing, follow references/install.md to install the NeMo Retriever Library before proceeding. It prints RETRIEVER_VENV=<path>; substitute that path for <RETRIEVER_VENV> in every example in this skill (setup, query, troubleshooting, and the CLI references).

Workflow — read the reference for the current phase, then execute

Turn type	Read this once	Then execute
Setup turn (first turn — `./lancedb/nv-ingest.lance` doesn't exist)	`references/setup.md`	Build the index
Query turn (every subsequent turn — user asks a question)	`references/query.md`	One `retriever query` call
Anything errored or returned empty	`references/troubleshooting.md`	Apply the named recovery; do not improvise

For the full retriever ingest / retriever query CLI specs, see references/cli/ingest.md and references/cli/query.md. You do not need these for routine turns — <RETRIEVER_VENV>/bin/retriever <subcommand> --help is faster.

Before ingesting a mixed folder, inventory extensions (find <dir> -name '*.*' | sed 's/.*\.//' | sort -u) — --input-type=auto silently drops anything outside the supported set. See references/troubleshooting.md "Unsupported file types".

Hard limits (apply to every turn)

Setup turn: build the index in one shell command (see references/setup.md). STOP after the index lands.
Query turn: at most 2 Bash calls — 1 retriever query, +1 optional targeted text-extract per references/query.md. Reply and then STOP.
No narration between tool calls. Tokens you emit between calls become input + cached input for every later turn — quadratic cost. Go straight from reading the summary to writing the JSON file.
Banned: TodoWrite, Glob, Grep, Read of whole PDFs, re-running setup, spawning subagents, speculative "confirmation" calls.

Long query turns (5+ tool calls, 1M+ cache-read tokens) cost ~5× a disciplined turn and almost always still produce the wrong answer. Answering partially beats timing out.

Anti-Patterns

Indexing content before clarifying corpus boundaries, freshness, or ownership: Retrieval quality collapses when the source of truth is unstable.
Treating embedding, chunking, and backend choices as invisible defaults: They change recall, latency, and storage cost in user-visible ways.
Claiming grounded answers without checking the retrieved passages that supported them.

Verification Protocol

Before claiming "skill applied successfully":

Pass/fail: The workflow names the corpus, index or backend choice, and the query path before answering deployment or QA questions.
Pass/fail: Retrieval checks include at least one real query and inspection of the supporting passages or scores.
Pass/fail: Ingestion or indexing advice keeps corpus freshness and reindex cost visible instead of implicit.
Pressure-test scenario: Apply the workflow to a retriever that answers quickly but returns stale passages after a corpus update.
Success metric: The user gets a reproducible retriever setup or debugging path with live retrieval evidence.

Cross-Client Portability

This skill is written to stay usable across GitHub Copilot, Claude Code, and Codex.

GitHub Copilot: keep the folder in a Copilot-visible skill path or wrap the workflow in project instructions when folder discovery is unavailable.
Claude Code: keep the folder in a local skills directory or a compatible plugin source.
Codex: install or sync the folder into $CODEX_HOME/skills/nemo-retriever and restart Codex after major changes.

MCP Availability And Fallback

Preferred MCP Server: None required

Fallback prompt: "Use the nemo-retriever skill without MCP. Rely on the local SKILL.md, bundled references or scripts, and manual verification. Show the exact commands, evidence, and final checks you used before concluding."
If the current host does not expose a matching server, use the bundled references, scripts, native toolchain, and manual workflow already described in this skill.
Treat direct local verification, rendered output, logs, tests, or screenshots as the fallback evidence path before completion.

Related Skills

notebooklm-management: Use it when retrieval-backed research needs a notebook-style grounding workflow.
development-workflow: Use it when the retriever work also needs scoped implementation and validation checkpoints.
cloud-design-patterns: Use it when the retriever deployment choice also needs storage, scaling, or service-boundary analysis.

Use it

Copy one of these into your project. Installing also returns the manifest and these snippets.

yaml

targets:
  - https://api.opensmartroute.ai/api/v1/registry/practicalswan-agent-skills-nemo-retriever/manifest   # or paste the manifest below

Manifest

An Open Capability Manifest: the router reads it to know what this does, what it costs and when to pick it.

practicalswan-agent-skills-nemo-retriever.ocm.jsonjson

{
  "ocm": "1",
  "id": "practicalswan-agent-skills-nemo-retriever",
  "kind": "skill",
  "name": "nemo-retriever",
  "description": "NVIDIA NeMo Retriever deployment and usage guidance for local retrieval services, corpus ingestion, and grounded question-answering workflows.",
  "publisher": "practicalswan",
  "version": "1.0.0",
  "capabilities": {
    "domains": [
      "general"
    ],
    "tags": [
      "skill-md",
      "nvidia",
      "nemo",
      "retriever",
      "rag",
      "indexing",
      "qa",
      "skills-sh"
    ],
    "languages": [
      "en"
    ]
  },
  "quality_prior": 0.6,
  "examples": [
    "NVIDIA NeMo Retriever deployment and usage guidance for local retrieval services, corpus ingestion, and grounded question-answering workflows."
  ],
  "primary": false,
  "metadata": {
    "source": {
      "provider": "skills.sh",
      "repository": "https://github.com/practicalswan/agent-skills",
      "path": "nemo-retriever/SKILL.md",
      "ref": "HEAD",
      "url": "https://github.com/practicalswan/agent-skills/blob/HEAD/nemo-retriever/SKILL.md",
      "key": "practicalswan/agent-skills/nemo-retriever/SKILL.md"
    },
    "compatibility": "Guidance imported from the NVIDIA NeMo Retriever skill for local retriever deployment and corpus-backed QA workflows.",
    "license": "CC-BY-4.0 AND Apache-2.0"
  },
  "instructions": "# nemo-retriever\n\nThe `retriever` CLI indexes a folder of PDFs into LanceDB (`retriever ingest`) and serves vector search over it (`retriever query`). For any task about searching/answering questions across a folder of PDFs, use this CLI — do not write a custom RAG.\n\n**Beyond PDFs and beyond semantic search.** `retriever ingest` also handles images, Office, HTML, TXT, audio, and video — see `references/setup.md` for the per-format recipe and `references/install.md` for the install extras (`[multimedia]`, libreoffice, ffmpeg). For non-semantic operations — page filter, verbatim quote with citat",
  "cost": {
    "context_tokens": 1395
  }
}

Fetch it by URL: GET /api/v1/registry/practicalswan-agent-skills-nemo-retriever/manifest?version=1.0.0

Reviews

Star ratings from people who tried it. One review per account; edit yours any time.

No reviews yet. Install it, try it, and be the first to rate it.