NVIDIA-NeMo/DataDesigner is a framework for generating synthetic datasets from scratch or from seed data, including text, structured records and images, while controlling field relationships and validating results. Data scientists and developers use it to create and evaluate data-generation workflows that can include models, seed datasets, external tools and custom validators. The catalogue entries provide agent skills, agents, instructions and settings for working with Data Designer.
Borrowing it
Nothing to install: this file belongs to NVIDIA-NeMo/DataDesigner. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/NVIDIA-NeMo/DataDesigner/main/.agents/skills/review-code/SKILL.mdgit clone --depth 1 https://github.com/NVIDIA-NeMo/DataDesignerWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/nvidia-nemo/datadesigner/review-code)<a href="https://agentmods.dev/skills/nvidia-nemo/datadesigner/review-code"><img src="https://agentmods.dev/badge/skills/nvidia-nemo/datadesigner/review-code/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/nvidia-nemo/datadesigner/review-code"><img src="https://agentmods.dev/badge/skills/nvidia-nemo/datadesigner/review-code.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high Tool Misuse · line 50 Tool parameters are crafted to achieve unintended or unsafe behavior. Parameter abuse can bypass intended safety checks (e.g. shell=True, --force, dangerous glob patterns).Fix: Validate all tool parameters against an allowlist. Reject dangerous parameter values (shell=True, --force, -rf /) and use safe defaults.
What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00020 | $0.05757 |
| Opus 5.5 | $0.00008 | $0.02303 |
| Sonnet 5.5 | $0.00004 | $0.01151 |
| Haiku 4.5 | $0.00002 | $0.00576 |
Grade A, and why
review-code scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured today.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 402 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Review Code Changes
Perform a comprehensive code review of either the current branch or a specific GitHub pull request.
Arguments
$ARGUMENTS determines the review mode:
PR mode — first argument is a number:
366— review PR #366366 focus on the API changes— review PR #366 with a focus area
Branch mode — no number, or only instructions:
- (empty) — review current branch against
main compare against develop— review against a different basefocus on the API changes— review current branch with a focus area
Additional instructions work in both modes:
be strict about type annotationsskip style nits
Step 1: Gather Changes
If PR mode (argument starts with a number)
Run these commands in parallel using gh:
- PR details:
gh pr view <number> --json title,body,author,baseRefName,headRefName,state,additions,deletions,changedFiles,commits,url - PR diff:
gh pr diff <number> - PR files:
gh pr diff <number> --name-only - PR commits:
gh pr view <number> --json commits --jq '.commits[].messageHeadline' - Existing inline review comments:
gh api repos/{owner}/{repo}/pulls/<number>/comments --paginate --jq '.[].body'5b. Existing PR-level reviews (top-level review bodies from "Review changes"):gh api repos/{owner}/{repo}/pulls/<number>/reviews --paginate --jq '.[].body' - Repo info:
gh repo view --json nameWithOwner -q '.nameWithOwner'
Then get the PR branch locally for full file access. Prefer a worktree so your current branch and uncommitted work are untouched:
git fetch origin pull/<number>/head:pr-<number> --force
git worktree add /tmp/review-<number> pr-<number>
# Cleanup when done: git worktree remove /tmp/review-<number> && git branch -D pr-<number>
If worktrees aren't suitable, you can use gh pr checkout <number> (this switches your current branch — only if you have no uncommitted work). Run the rest of the review from /tmp/review-<number>.
If checkout isn't possible (e.g., external fork), use gh api to fetch file contents:
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- today Changed · -1 lines 7f937edbbf2a
- 1mo ago Changed · +55 lines bc6cf8ebca75
- 1mo ago First seen · 348 lines · 20 tokens per session scan A fc3d0bb30c38
review-code is a skill published in the GitHub repository NVIDIA-NeMo/DataDesigner (2,366 stars, last pushed today), licensed Apache-2.0. It adds 20 tokens to every session and 5,757 once invoked, about $0.0001 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
control-center-review
Review one captured Control Center build before runtime activation.
review-pr
Review GitHub pull requests. Use when user says "review PR", "review pull request", or "/review-pr".
spawn-reviewers
Spawn and collect the reviewer fleet at stage20spawnreviewers. Consumes spawn.json.spec (the authoritative spawn spec from derive-spawn-spec / derive-static-spec), resolves CODEINTELALLOWED and CODEINTELREQUIREROOTARG, builds per-agent prompts from the per-agent template + role suffixes (Bug Hunter A/B, Unified…
review-this-branch
Run the nohuman review gate (fresh-session adversarial reviewer + tamper guard) over the current branch or a GitHub pull request, with no server, no database, and no onboarding, and relay the pass/fail checklist.
workflow-code-review
Run a worker-backed code review using its bundled review lenses: approach correctness, architecture ownership, correctness, guardrails, validation, compatibility, and security. Use when asked to review a PR, branch, diff, or uncommitted changes with workflow-level rigor.
present-local
Render the operator-facing local-mode code review results at stage29present. Covers BLOCKING/HIGH/MEDIUM section templates, Justified Findings (PLN-721), Dismissed Findings (PLN-722), Verifier Stats footer (PLN-773), operator-flag descriptions, override precedence rule for stage22b, Validation Summary, and final…