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/commit/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/commit)<a href="https://agentmods.dev/skills/nvidia-nemo/datadesigner/commit"><img src="https://agentmods.dev/badge/skills/nvidia-nemo/datadesigner/commit/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/commit"><img src="https://agentmods.dev/badge/skills/nvidia-nemo/datadesigner/commit.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00011 | $0.00787 |
| Opus 5.5 | $0.00004 | $0.00315 |
| Sonnet 5.5 | $0.00002 | $0.00157 |
| Haiku 4.5 | $0.00001 | $0.00079 |
Grade A, and why
commit 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 1mo ago.
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 — 113 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Commit Changes
Commit the current staged/unstaged changes with a well-crafted commit message.
Arguments
$ARGUMENTS can be used for special instructions, such as:
- Guiding the message: "emphasize the breaking change"
- Adding context: "this fixes issue #123"
- Requesting amend: "amend the previous commit"
Step 1: Gather Information
Run these commands in parallel to understand the changes:
- Git status:
git status --porcelain(check for staged/unstaged changes) - Staged diff:
git diff --cached(what will be committed if there are staged changes) - Unstaged diff:
git diff(what's modified but not staged) - Recent commits:
git log -5 --oneline(to match existing commit style)
Important checks:
- If no changes exist (nothing staged or unstaged), inform the user there's nothing to commit
- If there are unstaged changes but nothing staged, stage all changes with
git add -A(or ask user if they want to selectively stage) - If there are both staged and unstaged changes, ask user if they want to include unstaged changes
Step 2: Analyze Changes
Review the diff to understand:
- What changed (files, functions, features)
- Why it changed (bug fix, new feature, refactor, etc.)
- Impact (breaking changes, dependencies, configuration)
Step 3: Generate Commit Message
Message Guidelines
-
Subject line:
- Use imperative mood ("add feature" not "added feature")
- Keep under 50 characters (hard limit: 72)
- Don't end with a period
- Use lowercase for the first letter
-
Body (if needed for complex changes):
- Separate from subject with blank line
- Wrap at 72 characters
- Explain what and why, not how
- Use bullet points for multiple items
-
Footer (if needed):
- Reference issues:
Fixes #123,Closes #456
- Reference issues:
Examples
Simple change:
add user authentication endpoint
Change with body:
add rate limiting to public endpoints
- Implement token bucket algorithm
- Add configurable limits per endpoint
- Include rate limit headers in responses
Closes #234
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.
- 1mo ago First seen · 113 lines · 11 tokens per session scan A f4d88974c7d8
commit is a skill published in the GitHub repository NVIDIA-NeMo/DataDesigner (2,366 stars, last pushed today), licensed Apache-2.0. It adds 11 tokens to every session and 787 once invoked, about $0.0000 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
commit
Create git commits with good messages. Use when user says "commit", "create commit", or asks to commit changes.
cross-repo-cache
Check if cross-repo coordinator results can be reused, avoiding redundant Sonnet agent launches. Compares peer repo git hashes against stored hashes from last coordinator run. Triggers on: entering Phase 1.4.1, checking cross-repo cache, before discovering peers. Returns CROSSREPOCACHEHIT with cached status or…
experiment-loop
Autonomous benchmark-driven experiment loop: propose a change, measure the metric, keep what improves it, revert what doesn't, repeat. Git is the ledger — every kept improvement is a commit. Every discarded attempt is a clean revert.
sup-coding
Coding workflow recipe (brainstorm → design → spec → plan → implement → review → verify → finish).
caveman-commit
Ultra-compressed commit message generator. Cuts noise from commit messages while preserving intent and reasoning. Conventional Commits format. Subject ≤50 chars, body only when "why" isn't obvious. Use when user says "write a commit", "commit message", "generate commit", "/commit", or invokes /caveman-commit.…
tldr-commit
Ultra-compressed commit message generator. Cuts noise from commit messages while preserving intent and reasoning. Conventional Commits format. Subject ≤50 chars, body only when "why" isn't obvious. Use when user says "write a commit", "commit message", "generate commit", "/commit", or invokes /tldr-commit.…