Data & Analysis ✓ NVIDIA · Official deep-researchai-q-blueprintresearch-agentspythonbashasync-jobslocal-backend

NVIDIA AI-Q Deep Research

Run deep research through a reachable local or self-hosted AI-Q Blueprint backend.

FollowSkills review · FSRS-2.0
Not recommended
55/ 100 5-point scale 2.8 / 5
Trust18 / 25 · 3.6/5

The evidence shows a single declared environment variable, Read/Bash as allowed tools, localhost as the default network target, and explicit disclosure and confirmation before sending queries to non-local endpoints. The script rejects embedded credentials, restricts remote HTTP, and warns that queries, reports, and metadata may be logged. Points are deducted because the public helper requires an unauthenticated backend and sensitive-data consent, retention controls, and recovery remain largely dependent on the host and backend.

Reliability8 / 20 · 2.0/5

The documentation and script cover health checks, requests, asynchronous polling, stop-on-failure behavior, resume guidance, identifier validation, and diagnostic errors, with no third-party Python dependencies. Points are deducted because this review is static and did not execute key paths; compatibility depends on an external AI-Q Blueprint version and available routes, so end-to-end stability is unverified.

Adaptability9 / 15 · 3.0/5

Trigger phrases, research use cases, explicit non-fit deployment/troubleshooting cases, and the input/output flow are reasonably clear, with support for local or self-hosted backends. Points are deducted because a running AI-Q service is mandatory, Chinese-language behavior is not specified, and reachability and mainland-China network fit lack evidence.

Convention10 / 15 · 3.3/5

SKILL.md provides progressive sections, prerequisites, command tables, version-compatibility rules, security guidance, limitations, examples, and troubleshooting. It identifies Apache-2.0, version 2.1.0, an author, and an upstream repository; repository material also supplies a benchmark report and sync-based maintenance context. Points are deducted for no skill-specific changelog, no clearly assigned maintenance owner or formal update procedure, and NOASSERTION license metadata.

Effectiveness6 / 15 · 2.0/5

The core outcome is clear: route research queries to the AI-Q backend, handle synchronous or asynchronous results, and preserve citations, source URLs, and downloadable artifacts; repository benchmark material reports limited correctness and effectiveness results. Points are deducted because no independently reproducible output is available in this static review, result quality depends on the external backend, and reports still require human verification.

Verifiability4 / 10 · 2.0/5

The source code, command interface, error branches, evaluation tasks, and benchmark report provide auditable material. Points are deducted because the benchmark is an in-repository report rather than independently verifiable CI or test evidence, this review did not execute the skill, and there is no corroborating third-party evidence.

Evidence confidence:Low Reviewed Jul 20, 2026 Reviewed revision 55f18499943e
The upstream repository has new commits since this review. The score still applies to the reviewed revision shown and may not cover the latest changes.
Before you use it
  • Confirm AIQ_SERVER_URL before sending queries; remote endpoints may log prompts, responses, and metadata, so do not send confidential information.
  • The public helper relies on a backend with authentication disabled and is not suitable by default for identity-protected or strongly isolated data sources.
  • Verify the deployed AI-Q Blueprint version against the 2.1.0 compatibility rules and review returned reports and citations manually.
  • Chinese-language support and mainland-China network reachability are not established by the source files.
Review evidence [1][2][3][4][5][6][7][8][9]
See the full review method →

What does this skill do, and when should you use it?

AI-Q Research is one skill in NVIDIA’s skills catalog for research-shaped requests. It uses scripts/aiq.py to call a reachable NVIDIA AI-Q Blueprint backend and supports both inline responses and asynchronous research jobs. The workflow checks backend health, sends the query, polls jobs when needed, and presents reports with citations and source URLs intact. It is intended for users who already operate an AI-Q backend; it does not deploy the backend or manage authentication credentials.

Resolves AIQ_SERVER_URL, defaulting to http://localhost:8000; runs a health check; sends research queries through /chat; extracts and polls asynchronous job IDs; retrieves job status, reports, and durable artifacts; can export a portable report.md with local artifacts; and preserves citations and source URLs in returned reports.

  1. A researcher with a running NVIDIA AI-Q Blueprint backend wants to run a deep-research request.
  2. A developer wants to ask AI-Q a research question or compare approaches through a local service.
  3. A user needs to resume an interrupted asynchronous research job and retrieve its final report.
  4. A user wants to export a research report and associated charts or CSV artifacts for local sharing.

What are this skill's strengths and limitations?

Pros
  • Supports both inline answers and asynchronous deep-research jobs.
  • Includes health, status, report, and artifact-management commands for recovery and retrieval.
  • Has no third-party Python package dependencies because it uses Python standard-library HTTP modules.
  • Designed for Claude Code, OpenCode, Codex, and Agent Skills-compatible tools.
Limitations
  • Requires a running and reachable AI-Q Blueprint backend.
  • The public helper does not manage API keys, bearer tokens, cookies, or other authentication.
  • Authenticated backends require a separate authenticated AI-Q skill or an environment configured for this public flow.
  • Remote AIQ_SERVER_URL endpoints may log prompts, responses, and metadata; backend deployment is outside this skill’s scope.

How do you install this skill?

Use the repository README’s supported command: npx skills add nvidia/skills --skill aiq-research --yes. To target Codex, use npx skills add nvidia/skills --skill aiq-research --agent codex --yes. The README does not document a manual destination path for copying this skill alone.

How do you use this skill?

Provide Python 3.11+ as python3 and run a reachable AI-Q Blueprint backend. Without AIQ_SERVER_URL, the skill uses http://localhost:8000; remote URLs require explicit user trust confirmation. Run python3 $SKILL_DIR/scripts/aiq.py health first, then python3 $SKILL_DIR/scripts/aiq.py chat "deep research on ...". If the response contains a job ID, run python3 $SKILL_DIR/scripts/aiq.py research_poll <JOB_ID>; after completion, use report <JOB_ID> to retrieve the report.

FAQ

Does this skill deploy an AI-Q backend?
No. It requires an existing reachable local or self-hosted AI-Q Blueprint backend; deployment is outside this skill’s scope.
Where are queries sent?
They are sent to the backend specified by AIQ_SERVER_URL, defaulting to http://localhost:8000. The endpoint should be trusted before sending sensitive information.
What if the backend requires authentication?
The public helper does not attach tokens or cookies. For HTTP 401 or 403 responses, use an authenticated AI-Q skill or configure the backend for this workflow.
Does it retry failed research jobs automatically?
No. It reports the returned error and asks whether to retry with a narrower query or a different approach.

More skills from this repository

All from NVIDIA/skills

Dev & Engineering ✓ NVIDIA · Official

Earth2Studio Data Source Builder

Connect remote weather data to Earth2Studio with tested source wrappers.

Dev & Engineering ✓ NVIDIA · Official

NeMo Relay Installation Guide

Choose and verify the right NeMo Relay path for CLIs, language packages, and maintained frameworks.

Dev & Engineering ✓ NVIDIA · Official

NeMo Relay Quick Start

Helps first-time NeMo Relay users prove observable execution value through the smallest suitable trial.

Data & Analysis ✓ NVIDIA · Official

DICOM Series Preflight

Header-only validation for one DICOM series before conversion or inference.

Dev & Engineering ✓ NVIDIA · Official

Jetson BSP Info Check

Verify Jetson BSP version, board configs, and rootfs state before flashing.

Dev & Engineering ✓ NVIDIA · Official

DALI Dynamic Mode Assistant

Helps agents write, review, and migrate NVIDIA DALI imperative dynamic-mode code.

Automation & Ops ✓ NVIDIA · Official

Jetson Device Info Snapshot

Capture a concise software, kernel, OS, and power-mode baseline from a running Jetson target.

Dev & Engineering ✓ NVIDIA · Official

NeMo Relay Migration Assistant

Safely migrate NeMo Flow projects to NeMo Relay.

Dev & Engineering ✓ NVIDIA · Official

Earth2Studio Diagnostic Builder

Build Earth2Studio wrappers for single-step diagnostic data transformations.

Data & Analysis ✓ NVIDIA · Official

Earth2Studio Weather Data Fetch

Fetch validated weather and climate variables from Earth2Studio sources by time and data type.

Automation & Ops ✓ NVIDIA · Official

Jetson Health Snapshot

Read-only diagnostics that consolidate a live Jetson’s hardware, resource, and service state.

Dev & Engineering ✓ NVIDIA · Official

AMC Sample Dataset Calibration

Verify a running NVIDIA AutoMagicCalib service end to end with its bundled sample dataset.

Dev & Engineering ✓ NVIDIA · Official

Holoscan SDK Setup Guide

Inspects a Linux host and selects the most suitable Holoscan SDK installation path.

Automation & Ops ✓ NVIDIA · Official

Jetson Headless Memory Optimizer

Reclaim memory on GUI-free Jetson devices through safe, reversible system-service changes.

Dev & Engineering ✓ NVIDIA · Official

NeMo Relay Typed Wrappers & Codecs

Add typed boundaries to NeMo Relay integrations while preserving predictable JSON middleware semantics and caller-visible behavior.

Dev & Engineering ✓ NVIDIA · Official

Omniverse Realtime Viewer

Routes USD viewer requests to the right architecture and guides rendering, interaction, UI, and validation.

Dev & Engineering ✓ NVIDIA · Official

CUDA-Q Quantum Onboarding

Guides developers from CUDA-Q installation to quantum kernels, GPU simulation, and real QPU execution.

Dev & Engineering ✓ NVIDIA · Official

Clinical ASR Flywheel: Environment Setup

Validate that a clinical ASR evaluation environment can complete a TTS-to-ASR round trip through NVIDIA-hosted speech services.

Data & Analysis ✓ NVIDIA · Official

TAO DAFT Dataset Converter

Guides AI agents through tao-daft conversion between supported NVIDIA TAO DAFT dataset formats.

Dev & Engineering ✓ NVIDIA · Official

AutoMagicCalib Video Calibration

Turn local multi-camera MP4 recordings into AutoMagicCalib calibration results through a REST API.

Related skills