Skill v1.0.0
currentTrusted Publisher100/100version: "1.0.0" name: aiq-research description: | Use when asked to run deep research or AI-Q research through a reachable NVIDIA AI-Q Blueprint backend. license: Apache-2.0 permissions: env:
- AIQ_SERVER_URL
network:
- http://localhost:8000
compatibility: | Designed for Claude Code, OpenCode, Codex, and Agent Skills-compatible tools. Requires Python 3.11+ and network access to a running local AI-Q Blueprint server at http://localhost:8000 by default. Non-local backends must be explicitly trusted by the user and granted by the host tool outside this public skill. metadata: version: "2.1.0" author: "NVIDIA AI-Q Blueprint Team <aiq-blueprint@nvidia.com>" github-url: "https://github.com/NVIDIA-AI-Blueprints/aiq" tags:
- nvidia
- aiq
- blueprint
- deep-research
- research-agents
- agent-skills
languages:
- python
- bash
domain: "research-agents" allowed-tools: Read Bash
AIQ Research Skill
Purpose
Use this skill to call a locally running NVIDIA AI-Q Blueprint server through the helper script at scripts/aiq.py.
Use this skill for research-shaped requests, including:
- "deep research on ..."
- "AIQ research ..."
- "research ..."
- "use AI-Q to answer ..."
- "ask AI-Q about ..."
Do not use this skill for install, deploy, start, stop, UI, CLI, Docker, Helm, or troubleshooting requests. Those belong to aiq-deploy.
Prerequisites
Users need:
- Python 3.11+ available as
python3. - A reachable local or self-hosted AI-Q Blueprint backend.
AIQ_SERVER_URLset when the backend is not running athttp://localhost:8000; non-local values must be trusted by
the user before any query is sent.
- A backend configured with authentication disabled for this public helper, or a separate authenticated AI-Q skill for
authenticated environments.
- Network access from the local machine to the AI-Q backend URL.
- Credentials configured in the backend environment, not in this skill. This public helper does not collect or manage
API keys.
The helper script has no third-party Python package dependencies; it uses Python standard-library HTTP modules.
Instructions
- Resolve the target backend URL.
- Run
healthbefore sending research requests. - If no backend is reachable, ask for a backend URL or hand off to
aiq-deploy. - Before sending any user query, state the exact AI-Q backend URL that will receive it. For non-local URLs, continue
only if the user has explicitly confirmed that URL is trusted in the current conversation.
- Poll asynchronous deep research jobs when AI-Q returns a job ID.
- Present returned reports with citations and source URLs intact.
- Stop on failed jobs and show the returned error; do not retry automatically.
Step 1 - Resolve the backend
Use AIQ_SERVER_URL when set. Otherwise try the default local backend:
python3 $SKILL_DIR/scripts/aiq.py health
Expected output: JSON from a reachable AI-Q health endpoint.
If health fails and no explicit AIQ_SERVER_URL was set, ask:
I do not see a reachable local AI-Q backend. Do you already have an AI-Q backend URL you want to use, or should I deploy a local Skill backend?
- If the user provides a URL, set
AIQ_SERVER_URLfor subsequent helper calls and rerunhealth. - If the user wants local deployment, hand off to
aiq-deployand preserve the original research request. - If a reachable backend returns
401or403, stop and explain that this public skill does not manage
authentication. Ask the user to use an authenticated AI-Q skill or configure authentication for their environment.
- If
healthsucceeds but/chator/v1/jobs/async/agentsfails, report that the backend is reachable but not
compatible with this public research flow, then offer to run aiq-deploy validation.
Step 2 - Send the routed research request
Before sending the request, state the resolved endpoint:
I will send this query to <AIQ_SERVER_URL>. Make sure this endpoint is trusted before sending sensitive information.
Do not send credentials, cookies, bearer tokens, or secret values through the query text.
Run:
python3 $SKILL_DIR/scripts/aiq.py chat "<USER_QUESTION>"
Expected output:
- A normal JSON response for shallow or direct answers.
- Or structured JSON containing
{"status": "deep_research_running", "job_id": "<JOB_ID>"}for asynchronous deep
research.
If the response is normal JSON, present the result immediately. Do not force polling when there is no job_id.
Step 3 - Poll asynchronous jobs
If the response includes deep_research_running, extract the job_id and poll with the same absolute script path:
python3 $SKILL_DIR/scripts/aiq.py research_poll <JOB_ID>
Expected output: the final report JSON when the job completes successfully.
Use the runtime's non-blocking or background execution mechanism when available. If the chosen execution method requires escalated permissions, request explicit user approval first and explain why. Tell the user that deep research is running in the background.
Step 4 - Resume after interruptions
If polling is interrupted, the job continues server-side. Resume with:
python3 $SKILL_DIR/scripts/aiq.py status <JOB_ID>python3 $SKILL_DIR/scripts/aiq.py report <JOB_ID>python3 $SKILL_DIR/scripts/aiq.py research_poll <JOB_ID>
Use status to inspect job status and saved artifacts. Use report when the job has already finished and you only need the final output. Use research_poll to keep waiting for completion.
Step 5 - Present the report
When research_poll completes successfully, fetch and present the full report. Keep citations and source URLs intact. If the job status is failed, failure, or cancelled, show the error from the status response and ask whether the user wants to retry with a narrower query or different approach.
Version Compatibility
IMPORTANT: This skill is designed for NVIDIA AI-Q Blueprint version 2.1.0.
Semantic Versioning Compatibility Rules:
Skill version: X.Y.ZBlueprint or endpoint version: A.B.CCompatible IF:1. A == X (Major versions MUST match)2. B >= Y (Minor version must be equal or greater)3. C can be anything (Patch version does not affect compatibility)
Examples:
- Skill version 2.1.0 is compatible with Blueprint version 2.1.0.
- Skill version 2.1.0 is compatible with Blueprint version 2.2.0.
- Skill version 2.1.0 is compatible with Blueprint version 2.1.5.
- Skill version 2.1.0 is not compatible with Blueprint version 3.0.0.
- Skill version 2.1.0 is not compatible with Blueprint version 2.0.0.
If your Blueprint version is not compatible:
- Check for an updated skill version matching your Blueprint version.
- Use a Blueprint version compatible with this skill.
- Proceed with caution only when the user accepts the compatibility risk; API routes or response shapes may have
changed.
Available Scripts
| Script | Purpose | Arguments | |
|---|---|---|---|
scripts/aiq.py health | Check whether the configured server responds | none | |
scripts/aiq.py chat | POST /chat; may return inline output or a deep-research job ID | <query> | |
scripts/aiq.py agents | List available async agent types | none | |
scripts/aiq.py submit | Submit an explicit async job | <query> [agent_type] | |
scripts/aiq.py research | Submit an async job, poll, and print the final report JSON | <query> [agent_type] | |
scripts/aiq.py research_poll | Resume polling an existing async job | <job_id> | |
scripts/aiq.py status | Fetch job status plus /state artifacts | <job_id> | |
scripts/aiq.py state | Fetch event-store artifacts only | <job_id> | |
scripts/aiq.py report | Fetch the final report for a completed job | <job_id> | |
scripts/aiq.py stream | Stream SSE events from a job | <job_id> | |
scripts/aiq.py cancel | Cancel a running job | <job_id> |
When the host supports a run_script() helper, call it with scripts/aiq.py and the arguments above. Otherwise, run the equivalent shell command, such as python3 $SKILL_DIR/scripts/aiq.py health.
Environment Variables
| Variable | Required | Default | Description | |
|---|---|---|---|---|
AIQ_SERVER_URL | No | http://localhost:8000 | Local or self-hosted AI-Q server base URL |
Security Best Practices
- Do not put API keys, bearer tokens, cookies, or basic-auth credentials in
AIQ_SERVER_URL. - Store backend credentials in the AI-Q deployment environment, not in this skill or command examples.
- User query text is transmitted to the configured
AIQ_SERVER_URL. Confirm the endpoint is trusted before sending
sensitive or confidential information.
- Treat returned reports as potentially sensitive if the backend uses private data sources.
- Do not truncate citations or source URLs from returned reports.
Limitations
- This skill requires a running AI-Q backend; it does not deploy one.
- The public helper does not manage authentication tokens or cookies.
- Remote
AIQ_SERVER_URLendpoints may log prompts, responses, and metadata. - If the backend returns HTTP 500 or lacks async agents, report the failure instead of fabricating a research answer.
Examples
Example 1: Run a routed chat or research request
python3 $SKILL_DIR/scripts/aiq.py healthpython3 $SKILL_DIR/scripts/aiq.py chat "Compare local AIQ deep research with a standard web search workflow"
Expected output:
<health JSON from AI-Q><JSON chat response or {"status": "deep_research_running", "job_id": "<JOB_ID>"}>
If AI-Q returns a job ID, continue with research_poll.
Example 2: Resume an existing job
python3 $SKILL_DIR/scripts/aiq.py status <JOB_ID>python3 $SKILL_DIR/scripts/aiq.py research_poll <JOB_ID>
Replace <JOB_ID> with the UUID returned by AI-Q. Expected output: status JSON followed by the report JSON when the job completes. If the job failed, show the returned status and do not retry automatically.
References
| Topic | Documentation | |
|---|---|---|
| Helper script | scripts/aiq.py | |
| Deployment and backend validation | ../aiq-deploy/SKILL.md |
Common Issues
Issue: No backend is reachable
Symptoms:
healthfails with connection refused.- The default
http://localhost:8000URL does not respond.
Causes:
- AI-Q is not running.
- AI-Q is running on a different host or port.
- A local firewall or network setting blocks the connection.
Solutions:
- Ask whether the user has an existing AI-Q backend URL.
- If they provide one, set it and rerun health:
``bash export AIQ_SERVER_URL="http://localhost:<PORT>" python3 $SKILL_DIR/scripts/aiq.py health ``
- If they want a local backend, hand off to
aiq-deployand preserve the original research request.
Issue: Backend requires authentication
Symptoms:
- Requests fail with HTTP 401 or HTTP 403.
- The backend is reachable but rejects
/chator async job calls.
Causes:
- The backend was deployed with authentication enabled.
- The public helper does not attach user tokens or cookies.
Solutions:
- Stop and explain that this public skill does not manage authentication.
- Ask the user to use an authenticated AI-Q skill or configure their backend for this public local workflow.
- Rerun
healthand the original query only after the authentication boundary is resolved.
Issue: Health succeeds but research routes fail
Symptoms:
healthreturns successfully./chat,/v1/jobs/async/agents, or polling commands fail.
Causes:
- The backend is not using an API-enabled AI-Q config.
- The async job registry is not available in the selected backend.
- The backend version is incompatible with this skill.
Solutions:
- Run:
``bash python3 $SKILL_DIR/scripts/aiq.py agents ``
- If agents are unavailable, report the compatibility failure and offer to run
aiq-deployvalidation. - Confirm the deployed Blueprint version is compatible with skill version 2.1.0.
Issue: Job is interrupted or appears stuck
Symptoms:
- Local polling is interrupted.
- The job keeps showing
running. - Poll output shows
running, but a report is returned or cancel says the job is alreadysuccess.
Causes:
- Deep research is asynchronous and continues server-side.
- Local polling output can lag behind terminal server state.
Solutions:
- Check current state:
``bash python3 $SKILL_DIR/scripts/aiq.py status <JOB_ID> ``
- If
has_report: trueorjob_status.status: success, fetch the report:
``bash python3 $SKILL_DIR/scripts/aiq.py report <JOB_ID> ``
- If the job is still running, continue polling:
``bash python3 $SKILL_DIR/scripts/aiq.py research_poll <JOB_ID> ``