New: 98,000+ skills indexed from GitHub repos with 100+ stars · every skill safety-checkedBrowse top skillsTop skills
Esc to closeBrowse all skills
Submit a skillBrowse skills
Submit a skillBrowse skills

Agent skill

Deep Researcher Customize Prompts Models

by NVIDIA-AI-Blueprints in NVIDIA-AI-Blueprints/deep-researcher-agent

A skill your agent uses when customizing Deep Researcher Agent behavior through Jinja2 prompt templates or per-agent model selection — editing prompts under src/deepresearcheragent/agents//prompts/…

Apache-2.0Auto-check: notesAI & LLM Engineering

Install Deep Researcher Customize Prompts Models

skills CLI
$ npx skills add NVIDIA-AI-Blueprints/deep-researcher-agent --skill deep-researcher-customize-prompts-models -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install NVIDIA-AI-Blueprints/deep-researcher-agent deep-researcher-customize-prompts-models --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/NVIDIA-AI-Blueprints/deep-researcher-agent.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.agents/skills/deep-researcher-customize-prompts-models .claude/skills/deep-researcher-customize-prompts-models && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
deep-researcher-customize-prompts-models
GitHub stars
886
Token cost
~1.6k tokens
SKILL.md length
664 words
Files
3 (incl. references)
Skills in repo
15
Repo updated
First seen
Licence
Apache-2.0

At a glance

A skill your agent uses when customizing Deep Researcher Agent behavior through Jinja2 prompt templates or per-agent model selection — editing prompts under src/deepresearcheragent/agents//prompts/…

  • Works in 6 steps: Identify the target agent and whether… → For a prompt: edit the relevant… → For a model: add or point an llms: entry… → …
  • Customizing Deep Researcher Agent behavior through Jinja2 prompt templates
  • SKILL.md covers Start Here, Authoritative References, Workflow and Validation, plus 2 more sections
  • Calls uv

What it does

Deep Researcher Customize Prompts Models is an agent skill from NVIDIA-AI-Blueprints/deep-researcher-agent. Use when customizing Deep Researcher Agent behavior through Jinja2 prompt templates or per-agent model selection — editing prompts under src/deepresearcheragent/agents//prompts/, adding template variables, or assigning/swapping LLMs per agent role via config (the llms section plus per-agent fields like orchestratorllm, plannerllm, researcherllm, writerllm, sourcerouterllm).

Its SKILL.md is about 1.6k tokens, which your agent loads only when the skill is triggered. The skill folder holds 3 other files, including reference files (for example `references/model-selection.md` and `references/prompt-templates.md`). Compatibility notes: Claude Code, Codex, Cursor, OpenCode, and Agent Skills-compatible tools.

It sits in AI & LLM Engineering, covering Prompt engineering and Multi-agent orchestration. The repository describes itself as: The NVIDIA Deep Researcher Agent Blueprint is an open reference example for building intelligent AI agents that connect to your enterprise data, reason using state-of-the-art… The licence is Apache-2.0.

When your agent uses it

  • Customizing Deep Researcher Agent behavior through Jinja2 prompt templates
  • Per-agent model selection — editing prompts under src/deepresearcheragent/agents//prompts/
  • Adding template variables
  • Assigning/swapping LLMs per agent role via config (the llms section plus per-agent fields like orchestratorllm

Example prompts

  • “/deep-researcher-customize-prompts-models”

Requirements

  • Python 3
  • Compatibility (from SKILL.md): Claude Code, Codex, Cursor, OpenCode, and Agent Skills-compatible tools.
  • Pre-approved tools (allowed-tools): Read, Bash, Edit

Workflow steps

6 steps, taken from the first numbered list in SKILL.md.

  1. Identify the target agent and whether the change is a prompt or a model.
  2. For a prompt: edit the relevant src/deep_researcher_agent/agents//prompts/*.j2
  3. For a model: add or point an llms: entry in the config and set the agent's
  4. Keep token cost in mind: prefer reordering static instructions before dynamic
  5. Validate (below): lint any changed Python, run the agent's tests, and
  6. Summarize changed files and paste the validation evidence.

What it can do on your machine

Read from SKILL.md and the folder at commit 951a1a1. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves these tools, so the agent can use them without asking each time:

    • Read
    • Bash
    • Edit

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    Shell commands in SKILL.md call:

    • uv

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md. Its commands use uv, which can reach the network depending on how they are called.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

  • Compatibility

    Claude Code, Codex, Cursor, OpenCode, and Agent Skills-compatible tools.

    From compatibility in the SKILL.md frontmatter.

Context cost

Deep Researcher Customize Prompts Models loads about 1.6k tokens when it runs, and up to ~3.2k if it reads all its reference files. Until then it costs about 107 tokens; SKILL.md has 664 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~107
When it runs · the whole SKILL.md, loaded when a task matches
~1.6k
With references · SKILL.md plus every file in references/, read only if the agent opens them
~3.2k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check: notes

The automated check noted patterns worth knowing about, such as sudo or a known installer.

  • NotePre-approves every shell command (allowed-tools: Bash)SKILL.md
    allowed-tools: Read, Bash, Edit

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from NVIDIA-AI-Blueprints/deep-researcher-agent at commit 951a1a1, republished under its Apache-2.0 licence (© NVIDIA-AI-Blueprints). 664 words, ~1,635 tokens.

Download SKILL.mdSave it as .claude/skills/deep-researcher-customize-prompts-models/SKILL.md (or your agent's skills folder). This skill also uses 2 other files; get the full folder from GitHub.
name
deep-researcher-customize-prompts-models
description
Use when customizing Deep Researcher Agent behavior through Jinja2 prompt templates or per-agent model selection — editing prompts under src/deep_researcher_agent/agents/*/prompts/, adding template variables, or assigning/swapping LLMs per agent role via config (the llms section plus per-agent fields like orchestrator_llm, planner_llm, researcher_llm, writer_llm, source_router_llm).
allowed-tools
Read, Bash, Edit
compatibility
Claude Code, Codex, Cursor, OpenCode, and Agent Skills-compatible tools.
license
Apache-2.0
metadata.version
0.1.0
metadata.source-repo
NVIDIA-AI-Blueprints/deep-researcher-agent
metadata.tags
deep-researcher nemo-agent-toolkit prompts models jinja2 customization

Customize Deep Researcher Agent Prompts and Models

Use this skill when a developer wants to change how an Deep Researcher Agent reasons or which model it uses — by editing a Jinja2 prompt template or by assigning a different LLM to an agent role — usually without touching agent code. Deep Researcher Agent behavior is driven by prompts and config, so most tuning is a template or YAML change. The one exception is adding a brand-new template, which needs a one-line load_prompt wiring in the agent (see the prompt-templates reference).

Start Here

  • Confirm the change is prompt or model customization, not new tool/agent logic. For a new retrieval source use deep-researcher-add-data-source; for a new tool use deep-researcher-add-tool.
  • Read the authoritative docs and the existing templates/config below first.
  • Prefer editing an existing template or config field over adding new machinery.
  • Keep the prompt's STRICT citation rules intact, and never hard-code a model name where an llms: ref belongs.
  • Keep templates general-purpose: don't hard-code specific queries, domains, or source/tool names — those come from the user's request and the data_source_registry at runtime.

Authoritative References

  • docs/source/customization/prompts.md: prompt guide — template inventory, load_prompt(path, name), render_prompt_template(template, ...), the documented template variables, the STRICT citation rules, and "Creating a New Template". Note it does not document every template's variables (e.g. source_router.j2, writer.j2, source_registry.j2) — the .j2 files are authoritative for the variables they actually use.
  • docs/source/customization/swapping-models.md: choosing hosted vs. self-hosted NIMs and pointing config at them.
  • docs/source/customization/configuration-reference.md: the llms section and each agent's config fields (deep_research_agent, clarifier_agent, …).
  • src/deep_researcher_agent/common/prompt_utils.py: load_prompt and render_prompt_template.
  • src/deep_researcher_agent/common/llm_provider.py: LLMRole and LLMProvider.configure, which bind a resolved LLM to an agent role (used by the deep research agent).
  • Templates to model on: src/deep_researcher_agent/agents/deep_researcher/prompts/*.j2 (orchestrator, planner, researcher, source_router, writer) and src/deep_researcher_agent/agents/clarifier/prompts/*.j2. Other agents have prompts too (e.g. shallow_researcher, chat_researcher) — check src/deep_researcher_agent/agents/*/prompts/.

Longer procedures live in this bundle:

Workflow

  1. Identify the target agent and whether the change is a prompt or a model.
  2. For a prompt: edit the relevant src/deep_researcher_agent/agents/<agent>/prompts/*.j2 template; keep its variables and citation rules intact (see the references).
  3. For a model: add or point an llms: entry in the config and set the agent's role field (e.g. orchestrator_llm, planner_llm, researcher_llm, writer_llm, source_router_llm) to that ref — do not edit Python to swap a model.
  4. Keep token cost in mind: prefer reordering static instructions before dynamic content (KV-cache reuse) and a cheaper model for low-stakes roles.
  5. Validate (below): lint any changed Python, run the agent's tests, and smoke-run the CLI against the config you changed.
  6. Summarize changed files and paste the validation evidence.
Show full SKILL.md (211 more words)Show less

Validation

Run the narrowest checks first; broaden only if you touched shared code.

bash
uv run ruff check src/deep_researcher_agent                      # only if you changed Python
uv run pytest tests/deep_researcher_agent/agents/<agent>         # the agent's tests (a prompt-only edit may have none)
./scripts/start_cli.sh --config_file <your config>   # smoke against the config you edited

Expected: the agent loads its templates without a Jinja2 error and runs with the configured model. A bare ./scripts/start_cli.sh uses the fixed default (configs/config_cli_default.yml), so pass --config_file to exercise your change. For a prompt-only edit (which often has no dedicated unit test), the smoke run is the real check; a config/prompt-only change needs no Python lint.

Common Mistakes

  • Breaking a template variable or the STRICT citation rules in docs/source/customization/prompts.md, which degrades report grounding.
  • Hard-coding specific queries, domains, or source/tool names into a template, which biases the agent toward one task and breaks generalization. Source/domain selection is data-driven (data_source_registry, source_router.j2); keep prompts task-agnostic.
  • Hard-coding a model name in Python instead of using an llms: ref and the agent's role field, so the model can no longer be swapped from config.
  • Changing an agent's default model when you meant a single sub-role. The deep research agent's default is orchestrator_llm (there is no generic llm field); the clarifier's default is llm. Editing the default shifts every unset role.
  • Introducing a large dynamic prefix that defeats KV-cache reuse and raises cost.
  • Pointing an agent's role at a model whose entry is not defined in llms:.
  • deep-researcher-configure-workflow
  • deep-researcher-add-tool
  • deep-researcher-add-data-source
  • deep-researcher-release-qa
  • deep-researcher-prepare-pr

© NVIDIA-AI-Blueprints, Apache-2.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 2 other files (references) in .agents/skills/deep-researcher-customize-prompts-models of NVIDIA-AI-Blueprints/deep-researcher-agent.

  • SKILL.md
  • references/model-selection.md
  • references/prompt-templates.md

Open the folder on GitHubat commit 951a1a1

Compare with similar skills

Deep Researcher Customize Prompts Models next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Deep Researcher Customize Prompts Models compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Deep Researcher Customize Prompts Models this skillNVIDIA-AI-Blueprints/deep-researcher-agent886—~1.6kAutomated safety check: NotesApache-2.0
Building Agent Systemstelagod/code-abyss244—~691Automated safety check: PassMIT
Agent Orchestration Improve Agentaiskillstore/marketplace4337 repos~2.6kAutomated safety check: PassNone
Agent OrchestrationLeoYeAI/openclaw-master-skills2.2k—~4.4kAutomated safety check: PassMIT
Agent Designeralirezarezvani/claude-skills28k—~1.1kAutomated safety check: PassMIT
Flow SwarmLeoYeAI/openclaw-master-skills2.2k—~5.3kAutomated safety check: PassMIT

Similar skills

  • Building Agent Systems

    telagod/code-abyss

    AI agent and LLM system engineering reference covering single-agent dev (ReAct, tool calling, plan-execute), multi-agent coordination (swarm, role decomposition, file locking), LLM security (prompt…

    244 GitHub stars~691 tokensUpdated 2 mo ago
    AI & LLM EngineeringAuto-check passed

  • Agent Orchestration Improve Agent

    aiskillstore/marketplace

    Systematic improvement of existing agents through performance analysis, prompt engineering, and continuous iteration.

    433 GitHub starsUsed in 7 repos~2.6k tokens
    Agent WorkflowsAuto-check passed

  • Agent Orchestration

    LeoYeAI/openclaw-master-skills

    Multi-agent orchestration patterns for production deployments.

    2.2k GitHub stars~4.4k tokensUpdated 2 mo ago
    Agent WorkflowsAuto-check passed

  • Agent Designer

    alirezarezvani/claude-skills

    A skill your agent uses when the user asks to design a multi-agent system, pick an orchestration pattern (supervisor/swarm/pipeline), generate tool schemas for agents, or evaluate agent execution…

    28k GitHub stars~1.1k tokensUpdated 1 mo ago
    Agent WorkflowsAuto-check passed

  • Flow Swarm

    LeoYeAI/openclaw-master-skills

    Multi-agent swarm orchestration via RuFlo + Claude Code. An agent skill from LeoYeAI/openclaw-master-skills.

    2.2k GitHub stars~5.3k tokensUpdated 2 mo ago
    Agent WorkflowsAuto-check passed

  • Cline SDK Guide

    cline/cline

    Reference for building AI agents with the Cline SDK: the Agent runtime, ClineCore sessions, custom tools, plugins, events, providers, scheduling and multi-agent teams.

    70k GitHub stars~2.2k tokensUpdated today
    AI & LLM EngineeringAuto-check passed

More from NVIDIA-AI-Blueprints/deep-researcher-agent

All 15 skills in this repo

  • Deep Researcher Configure Workflow

    NVIDIA-AI-Blueprints/deep-researcher-agent

    A skill your agent uses when composing, adapting, or validating an Deep Researcher Agent workflow YAML under configs/ — selecting a shipped profile, enabling tools and datasourceregistry sources…

    886 GitHub stars~1.1k tokensUpdated yesterday
    Auto-check: notes

  • Deep Researcher Research

    NVIDIA-AI-Blueprints/deep-researcher-agent

    A skill your agent uses when asked to run deep research or Deep Researcher Agent research through a reachable NVIDIA Deep Researcher Agent Blueprint backend.

    886 GitHub stars~4.4k tokensUpdated yesterday
    Auto-check: notes

  • Deep Researcher Add Data Source

    NVIDIA-AI-Blueprints/deep-researcher-agent

    A skill your agent uses when adding or changing an Deep Researcher Agent data source under sources/, registering it as a NeMo Agent Toolkit function, wiring it into the datasourceregistry for UI…

    886 GitHub stars~1.1k tokensUpdated yesterday
    Auto-check: notes

  • Deep Researcher Add Tool

    NVIDIA-AI-Blueprints/deep-researcher-agent

    A skill your agent uses when adding or changing a general-purpose Deep Researcher Agent tool (a NeMo Agent Toolkit function) under sources/, defining its FunctionBaseConfig schema, registering it…

    886 GitHub stars~1.1k tokensUpdated yesterday
    Auto-check: notes

  • Deep Researcher Deploy

    NVIDIA-AI-Blueprints/deep-researcher-agent

    A skill your agent uses when asked to install, deploy, run, validate, troubleshoot, or stop NVIDIA Deep Researcher Agent Blueprint infrastructure.

    886 GitHub stars~3.5k tokensUpdated yesterday
    Auto-check: notes

  • Deep Researcher Maintain CI

    NVIDIA-AI-Blueprints/deep-researcher-agent

    A skill your agent uses when changing Deep Researcher Agent continuous integration, pre-commit, or contributor governance — editing .github/workflows/ (ci, ui, skills-eval, request-nvskills-ci)…

    886 GitHub stars~1.5k tokensUpdated yesterday
    Auto-check: notes

Categories

Questions about Deep Researcher Customize Prompts Models

What does Deep Researcher Customize Prompts Models do?

A skill your agent uses when customizing Deep Researcher Agent behavior through Jinja2 prompt templates or per-agent model selection — editing prompts under src/deepresearcheragent/agents//prompts/…. Deep Researcher Customize Prompts Models is an agent skill from NVIDIA-AI-Blueprints/deep-researcher-agent. Use when customizing Deep Researcher Agent behavior through Jinja2 prompt templates or per-agent model selection — editing prompts under src/deepresearcheragent/agents//prompts/, adding template variables, or assigning/swapping LLMs per agent role via config (the llms section plus per-agent fields like orchestratorllm, plannerllm, researcherllm, writerllm, sourcerouterllm).

When should I use Deep Researcher Customize Prompts Models?

Deep Researcher Customize Prompts Models fits situations like: customizing Deep Researcher Agent behavior through Jinja2 prompt templates; per-agent model selection — editing prompts under src/deepresearcheragent/agents//prompts/; adding template variables; assigning/swapping LLMs per agent role via config (the llms section plus per-agent fields like orchestratorllm.

How do I install Deep Researcher Customize Prompts Models in Claude Code?

Run `npx skills add NVIDIA-AI-Blueprints/deep-researcher-agent --skill deep-researcher-customize-prompts-models -a claude-code`. Or copy the skill folder (.agents/skills/deep-researcher-customize-prompts-models in NVIDIA-AI-Blueprints/deep-researcher-agent) into .claude/skills/deep-researcher-customize-prompts-models in your project. Claude Code loads it when a task matches its description.

How do I install Deep Researcher Customize Prompts Models in Codex?

Run `npx skills add NVIDIA-AI-Blueprints/deep-researcher-agent --skill deep-researcher-customize-prompts-models -a codex`. Or copy the skill folder (.agents/skills/deep-researcher-customize-prompts-models in NVIDIA-AI-Blueprints/deep-researcher-agent) into .agents/skills/deep-researcher-customize-prompts-models in your project. Codex loads it when a task matches its description.

Can I use Deep Researcher Customize Prompts Models in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add NVIDIA-AI-Blueprints/deep-researcher-agent --skill deep-researcher-customize-prompts-models -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/deep-researcher-customize-prompts-models, .gemini/skills/deep-researcher-customize-prompts-models, .github/skills/deep-researcher-customize-prompts-models and .opencode/skills/deep-researcher-customize-prompts-models in your project.

What does Deep Researcher Customize Prompts Models need to run?

Going by SKILL.md and its folder, Deep Researcher Customize Prompts Models needs the command-line tools its instructions call (uv). Our summary lists: Python 3. Its frontmatter pre-approves these tools: Read, Bash, Edit. Compatibility (from SKILL.md): Claude Code, Codex, Cursor, OpenCode, and Agent Skills-compatible tools..

Does Deep Researcher Customize Prompts Models access the network?

SKILL.md contains no URLs. Its commands use uv, which can reach the network depending on how they are called. This is read from the text; nothing was executed.

Is Deep Researcher Customize Prompts Models safe to install?

Our automated static check of SKILL.md found notes only (pre-approves every shell command (allowed-tools: bash)), nothing it rates as a warning. It is not a guarantee. Review the folder before installing.

What licence does Deep Researcher Customize Prompts Models use?

Deep Researcher Customize Prompts Models is published under the Apache-2.0 licence (declared in SKILL.md). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Deep Researcher Customize Prompts Models use?

About 1.6k tokens (SKILL.md is roughly 6.5k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 1.5k tokens, read only when the agent opens those files.

What are the alternatives to Deep Researcher Customize Prompts Models?

Skills that share tags, products or a category with Deep Researcher Customize Prompts Models: Building Agent Systems (telagod/code-abyss, 244 stars), Agent Orchestration Improve Agent (aiskillstore/marketplace, 433 stars), Agent Orchestration (LeoYeAI/openclaw-master-skills, 2.2k stars) and Agent Designer (alirezarezvani/claude-skills, 28k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Deep Researcher Customize Prompts Models?

NVIDIA-AI-Blueprints (a GitHub organization) maintains it in NVIDIA-AI-Blueprints/deep-researcher-agent, which has 886 GitHub stars. The repository holds 15 skills in this directory. The repository was last updated on October 9, 2026.

Source: NVIDIA-AI-Blueprints/deep-researcher-agent on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.