warp-eval agent skill by NVIDIA
Evaluates whether an existing hot path is a credible NVIDIA Warp candidate, such as irregular spatial queries, particle or geometry simulation, or branch-heavy loops.
At a glance
| Publisher | NVIDIA Official |
|---|---|
| Repository | NVIDIA/skills (396 listed skills) |
| Category | Developer Tools and Frameworks |
| License | Apache-2.0 |
| Last commit | October 17, 2026 (repository) |
| SKILL.md | 349 lines, 2,610 words |
| Bundled files | 36 files, including references, scripts, assets or templates |
| Quality score | 85/100 · B Passes all seven graded checks |
| Security scan | Not scanned |
| README badge | Get the badges for this listing |
Before you install
Read from the skill's files at the directory's October 19, 2026 snapshot: what ships with it, what its code reads, and the terms it is published under.
- Bundled scripts: 13 script files (13 Python). Your agent may run them, so read them first.
- License: Apache-2.0, an open-source or open-content license.
Install warp-eval
The skills CLI works with Claude Code, Codex, Cursor and other agents; the other routes copy the folder by hand.
npx skills add https://github.com/NVIDIA/skills/tree/main/skills/warp-evaltmp="$(mktemp -d)"
git clone --depth 1 https://github.com/NVIDIA/skills.git "$tmp/repo"
mkdir -p .claude/skills
cp -R "$tmp/repo/"skills/warp-eval .claude/skills/
rm -rf "$tmp"python3 ~/.codex/skills/.system/skill-installer/scripts/install-skill-from-github.py \
--repo NVIDIA/skills \
--path skills/warp-evalNVIDIA/skills is third-party code. Read SKILL.md and any bundled scripts before you install it.
How the author describes it
Evaluate whether an existing hot path is a credible NVIDIA Warp candidate. Use for irregular or spatial queries, particle or geometry simulation, branch-heavy loops, many small launches, host fallbacks, or large intermediates. CPU-only code and absent GPU dependencies are normal unless NVIDIA is prohibited. Exclude required cross-vendor or CPU-only deployment, vendor-lowered dense or NN layers, general Warp API questions, and already-selected Warp kernels. Contribution policy alone is not exclusion.
From the description field of SKILL.md. Agents read this line to decide when to load the skill.
Compatibility, from SKILL.md
| Compatibility | Screening, static evaluation and reporting need no GPU. Measuring Warp requires an NVIDIA CUDA GPU, the target project's dependencies and a representative workload; without them, abort before… |
|---|
Sections in SKILL.md
- Purpose
- Hard rules
- Requirements
- Limitations
- Output Format
- Examples
- Inputs
- Available scripts
- Troubleshooting
- Instructions
- 1. Read the code, derive the contract, check the gates
- 2. Profile the real application
- 3. Form falsifiable hypotheses
- 4. Write the contract before the prototype
- 5. Improve the baseline first
- 6. Prototype the minimum unit
Files in the skill folder
BENCHMARK.mdSKILL.mdassets/warp-evaluation-report-template.mdconfig/skillspector-baseline.yamlevals/evals.jsonevals/files/gate-a-required-portability/deployment.mdevals/files/gate-a-required-portability/neighbors.pyevals/files/gate-b-unwidenable-host-boundary/architecture.mdevals/files/gate-b-unwidenable-host-boundary/scoring.pyevals/files/gate-c-dense-vendor-lowered/feature_stage.pyevals/files/gate-d-cpu-incumbent-not-cuda/baseline.mdevals/files/gate-d-cpu-incumbent-not-cuda/operation_api.pyevals/files/gate-d-mature-incumbent/baseline.mdevals/files/gate-d-mature-incumbent/contact_api.pyevals/files/gate-e-runtime-obligations-forbidden/candidates.pyevals/files/gate-e-runtime-obligations-forbidden/packaging-policy.mdevals/files/gate-f-immaterial-stage/profile.jsonevals/files/gate-f-immaterial-stage/spatial_filter.pyevals/files/pattern-fused-edge-intermediate/context.mdevals/files/pattern-fused-edge-intermediate/message_passing.pyevals/files/pattern-sequential-recurrence/adaptive_filter.pyevals/files/pattern-sequential-recurrence/context.mdevals/files/proceed-persistent-mesh-query/context.mdevals/files/proceed-persistent-mesh-query/queries.py
Showing 24 of 36 files. Browse the folder on GitHub.
Suede Skill Check: 85/100 · B
Report snapshot · · graded-v2
The rubric totals 100 points; published scores are capped at 99. Security scan: not scanned.
Source revision: 4fc9cf6cec78. Report version 32b4ac13ab7a. Badge URLs follow the latest listing; save the report to keep this version.
Download report · Request a fresh review
What to review next
- Boundary clause: 0 of 4 points. 4 when the description says when not to use the skill (“Not for …”, “Do not use …”, “Use … instead”).
- Example request: 0 of 3 points. 3 when the description quotes an example request (3–60 characters in quotation marks).
- Tool permissions declared: 0 of 2 points. 2 when the frontmatter declares allowed-tools.
Add declarations and bundled files when they describe the skill’s actual needs. Update the source, then request a fresh review with the changed commit or PR.
warp-eval passes the required frontmatter check and all seven graded checks, which cover the SKILL.md format, a declared license and a commit in the last year. Those checks earn 56 of the score’s points; the rest come from description quality, instruction depth, bundled files, maintenance and curated-list citations. How the score works.
See the checks and points
| Check | Result |
|---|---|
| Frontmatter parses and declares a name and a description | Pass |
| Name uses lowercase letters, digits and hyphens, 64 characters or fewer | Pass |
| Name matches the skill's folder name | Pass |
| Description is between 50 and 1,024 characters | Pass |
| Description says when an agent should use the skill | Pass |
| SKILL.md body is 500 lines or fewer | Pass |
| A license is declared in the frontmatter or the repository | Pass |
| Repository has a commit in the last 12 months | Pass |
| Score component | Points |
|---|---|
| Structural checks | 56 of 56 |
| Description length | 5 of 5 |
| Boundary clause | 0 of 4 |
| Example request | 0 of 3 |
| Instruction depth | 7 of 7 |
| Reference files | 3 of 3 |
| Bundled scripts | 2 of 2 |
| Recent maintenance | 9 of 9 |
| Curated-list citations | 1 of 7 |
| Tool permissions declared | 0 of 2 |
| Compatibility declared | 2 of 2 |
Two badges for warp-eval
Choose the numeric badge, the letter badge, or both. Each links to this skill’s Suede listing; either valid linked badge can qualify for the feature offer.
[](https://skills.suedeai.ai/directory/nvidia/skills/warp-eval/)
[](https://skills.suedeai.ai/directory/nvidia/skills/warp-eval/)<a href="https://skills.suedeai.ai/directory/nvidia/skills/warp-eval/"><img src="https://skills.suedeai.ai/directory/nvidia/skills/warp-eval/score.svg" alt="Suede Skill Check: 85/100" width="160" height="175"></a>
<a href="https://skills.suedeai.ai/directory/nvidia/skills/warp-eval/"><img src="https://skills.suedeai.ai/directory/nvidia/skills/warp-eval/badge.svg" alt="Suede Skill Check: Grade B" width="160" height="175"></a>Suede Certified on the shield refers to this published structural quality check. Security scan: not scanned. Read the methodology.
Limited-time feature offer: display either the numeric or letter badge in your repository or skill README (both also qualify), then request badge verification. Eligible skills scoring 80–99 can receive a featured placement after Suede verifies at least one valid badge linked to the skill’s listing. Suede has not announced an end date.
Where this skill is cited
NVIDIA/skills appears in 1 curated list: VoltAgent/awesome-agent-skills.