LLM Torch Profiler Analysis
sgl-project/sglang
Unified LLM torch-profiler triage skill for sglang, vllm, TensorRT-LLM, and TokenSpeed.
Use only to generate or update a governance skill card for a specified existing agent skill directory.
OfficialApache-2.0Auto-check: notes
Install Skill Card Generator
$ npx skills add NVIDIA/skills --skill skill-card-generator -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install NVIDIA/skills skill-card-generator --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/NVIDIA/skills.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/skill-card-generator .claude/skills/skill-card-generator && rm -rf skills-srcUse ~/.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/
Install the "skill-card-generator" agent skill from https://github.com/NVIDIA/skills/tree/main/skills/skill-card-generator into .claude/skills/skill-card-generator/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "skill-card-generator", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/NVIDIA/skills/tree/main/skills/skill-card-generatorType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add NVIDIA/skills --skill skill-card-generator -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install NVIDIA/skills skill-card-generator --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/NVIDIA/skills.git skills-src && mkdir -p .agents/skills && cp -r skills-src/skills/skill-card-generator .agents/skills/skill-card-generator && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "skill-card-generator" agent skill from https://github.com/NVIDIA/skills/tree/main/skills/skill-card-generator into .agents/skills/skill-card-generator/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "skill-card-generator", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add NVIDIA/skills --skill skill-card-generator -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install NVIDIA/skills skill-card-generator --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/NVIDIA/skills.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/skills/skill-card-generator .cursor/skills/skill-card-generator && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "skill-card-generator" agent skill from https://github.com/NVIDIA/skills/tree/main/skills/skill-card-generator into .cursor/skills/skill-card-generator/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "skill-card-generator", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/NVIDIA/skills.git --path skills/skill-card-generator--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add NVIDIA/skills --skill skill-card-generator -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install NVIDIA/skills skill-card-generator --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/NVIDIA/skills.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/skills/skill-card-generator .gemini/skills/skill-card-generator && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "skill-card-generator" agent skill from https://github.com/NVIDIA/skills/tree/main/skills/skill-card-generator into .gemini/skills/skill-card-generator/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "skill-card-generator", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install NVIDIA/skills skill-card-generatorInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add NVIDIA/skills --skill skill-card-generator -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/NVIDIA/skills.git skills-src && mkdir -p .github/skills && cp -r skills-src/skills/skill-card-generator .github/skills/skill-card-generator && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "skill-card-generator" agent skill from https://github.com/NVIDIA/skills/tree/main/skills/skill-card-generator into .github/skills/skill-card-generator/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "skill-card-generator", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add NVIDIA/skills --skill skill-card-generator -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install NVIDIA/skills skill-card-generator --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/NVIDIA/skills.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/skills/skill-card-generator .opencode/skills/skill-card-generator && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "skill-card-generator" agent skill from https://github.com/NVIDIA/skills/tree/main/skills/skill-card-generator into .opencode/skills/skill-card-generator/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "skill-card-generator", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
Facts
- Skill name
skill-card-generator- GitHub stars
- 3.5k
- Token cost
- ~1.6k tokens
- SKILL.md length
- 645 words
- Files
- 14 (incl. scripts, references)
- Skills in repo
- 380
- Repo updated
- First seen
- Licence
- Apache-2.0
At a glance
Use only to generate or update a governance skill card for a specified existing agent skill directory.
- Works in 10 steps: First, read this SKILL.md completely… → Resolve the target skill directory from… → Stay within the declared permission… → …
- Discussing skill capabilities
- SKILL.md covers Purpose, Prerequisites, Instructions and Available Scripts, plus 4 more sections
- Runs Python scripts from its folder
What it does
Skill Card Generator is an agent skill from NVIDIA/skills, published by the product's own GitHub organization. Use only to generate or update a governance skill card for a specified existing agent skill directory. Do not use for explaining, listing, comparing, or discussing skill capabilities.
Its SKILL.md is about 1.6k tokens, which your agent loads only when the skill is triggered. The skill folder holds 17 other files, including scripts and reference files (for example `BENCHMARK.md`, `evals/evals.json` and `references/catalog/limitations.json`). Compatibility notes: Any agent that can run Python scripts and write files
It works with NVIDIA AI Platform. The repository describes itself as: Agent Skills for NVIDIA products — install into Claude Code, Codex, and other coding agents to run Physical AI, robotics, simulation, CUDA, and RAG workflows end to end. The licence is Apache-2.0.
When your agent uses it
- Discussing skill capabilities
Example prompts
- “/skill-card-generator”
Requirements
- Python 3
- Compatibility (from SKILL.md): Any agent that can run Python scripts and write files
Workflow steps
10 steps, taken from the first numbered list in SKILL.md.
- First, read this SKILL.md completely before running any script.
- Resolve the target skill directory from $ARGUMENTS; if omitted, use the current working directory.
- Stay within the declared permission scope. Do not read .env, credential files, hidden auth folders, or unrelated repo files; do not write…
- Run scripts/discover_assets.py against the target. Use the structured signal summary first; if output is truncated, read only targeted…
- Build a context JSON file from the structured signal summary first, then from extracted file contents only when needed.
- Populate credential_requirements with only two fields: requires_api_key_or_credential and credential_types. Ground the classification in…
- Follow references/style-guide.md for every context field. Use HUMAN-REQUIRED only when no source supports a truthful value.
- Render the card with scripts/render_card.py and fix any schema errors before proceeding.
- Review the card manually, remove resolved VERIFY and SELECT markers, then run scripts/validate_submission.py.
- Before finishing, confirm the rendered card has no unrendered {{ ... }} or {% ... %} template fragments.
What it can do on your machine
Read from SKILL.md and the folder at commit 0e0d506. It shows what the files ask for, not the result of running them.
Tool permissions
Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.
From allowed-tools in the SKILL.md frontmatter.
Runs code
Ships 3 files in scripts/ (Python), which the agent can run.
From the folder's file list and the shell code blocks in SKILL.md.
Network
No URLs in SKILL.md.
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
Any agent that can run Python scripts and write files
From compatibility in the SKILL.md frontmatter.
Context cost
Skill Card Generator loads about 1.6k tokens when it runs, and up to ~9.1k if it reads all its reference files. Until then it costs about 51 tokens; SKILL.md has 645 words of instructions outside code blocks.
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.
- NoteMentions a .env fileSKILL.md:61
declared permission scope. Do not read `.env`, credential files, hidden auth folders, or unrelated repo files; do not w
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); the scripts in this folder are not scanned.
SKILL.md
The full file from NVIDIA/skills at commit 0e0d506, republished under its Apache-2.0 licence (© NVIDIA). 645 words, ~1,607 tokens.
Download SKILL.mdSave it as
.claude/skills/skill-card-generator/SKILL.md (or your agent's skills folder). This skill also uses 13 other files; get the full folder from GitHub.- name
- skill-card-generator
- description
- Use only to generate or update a governance skill card for a specified existing agent skill directory. Do not use for explaining, listing, comparing, or discussing skill capabilities.
- compatibility
- Any agent that can run Python scripts and write files
- license
- CC-BY-4.0 AND Apache-2.0
- metadata.author
- Trustworthy AI Projects <trustworthyaiprojects@nvidia.com>
- metadata.tags
- skill-card, governance, documentation, trustworthy-ai
- metadata.domain
- documentation
- permissions.file_read
- target_skill_directory, references/, scripts/
- permissions.file_write
- target_skill_directory, /tmp/
Generate Skill Card
Skill directory to analyze: $ARGUMENTS
Purpose
Create a draft NVIDIA governance skill card for an existing agent skill. The skill gathers source signals, guides the agent to build a grounded JSON context, renders a deterministic markdown card, and checks that human-review markers were removed before submission.
Use this when:
- A skill directory already exists and needs a new governance card.
- A changed skill needs its existing card refreshed.
- A skill owner is preparing legal/safety review material.
Do NOT use for:
- Explaining, listing, comparing, or discussing skills or skill capabilities.
- Creating or rewriting the source skill itself.
- Generating cards for non-skill assets such as models, datasets, containers, or full systems.
- Signing, publishing, or approving a skill card.
- Replacing required human legal, safety, or owner review.
Prerequisites
- Python 3 is available.
jinja2is installed before runningrender_card.py.- The target path is a skill directory containing
SKILL.mdorskill.md. - The agent can write a temporary context JSON file and the rendered card output.
- Runtime permissions allow reads from
target_skill_directoryplus this skill'sreferences/andscripts/, writes only to the target skill directory or/tmp/, and shell execution only for the three scripts listed below.
Instructions
- First, read this
SKILL.mdcompletely before running any script. - Resolve the target skill directory from
$ARGUMENTS; if omitted, use the current working directory. - Stay within the declared permission scope. Do not read
.env, credential files, hidden auth folders, or unrelated repo files; do not write outside the target skill directory or/tmp/. - Run
scripts/discover_assets.pyagainst the target. Use the structured signal summary first; if output is truncated, read only targeted files or small excerpts. - Build a context JSON file from the structured signal summary first, then from extracted file contents only when needed.
- Populate
credential_requirementswith only two fields:requires_api_key_or_credentialandcredential_types. Ground the classification in SKILL.md prose documentation — not script inspection alone. Forcredential_types, use the controlled vocabulary inreferences/style-guide.md. Never include credential values, assignments, or raw environment variable names. - Follow
references/style-guide.mdfor every context field. UseHUMAN-REQUIREDonly when no source supports a truthful value. - Render the card with
scripts/render_card.pyand fix any schema errors before proceeding. - Review the card manually, remove resolved VERIFY and SELECT markers, then run
scripts/validate_submission.py. - Before finishing, confirm the rendered card has no unrendered
{{ ... }}or{% ... %}template fragments.
Show full SKILL.md (256 more words)Show less
Available Scripts
| Script | Purpose | Arguments |
|---|---|---|
scripts/discover_assets.py | Extracts skill files, repo signals, style guide, and template into one discovery report. | <skill_directory> |
scripts/render_card.py | Validates context JSON and renders the skill card from the Jinja template. | --context <context.json> --template <skill-card.md.j2> --out <output.md> |
scripts/validate_submission.py | Fails if the rendered card still contains VERIFY or SELECT review markers. | <rendered-card.md> |
Examples
Discover signals for a target skill:
run_script("scripts/discover_assets.py", args=["/path/to/target-skill"])Render a card from the completed context:
run_script(
"scripts/render_card.py",
args=[
"--context", "/tmp/target-skill-context.json",
"--template", "references/skill-card.md.j2",
"--out", "/path/to/target-skill/target-skill-card.md"
]
)Validate the reviewed card before submission:
run_script("scripts/validate_submission.py", args=["/path/to/target-skill/target-skill-card.md"])Limitations
- The generated card is a draft and must be reviewed by a human owner.
- Discovery is limited to local files and repo metadata visible from the target path.
- The renderer validates required context shape, not the legal or safety correctness of field values.
- Canned limitation and risk catalogs are starting points; remove entries that do not apply.
Troubleshooting
| Error | Cause | Solution |
|---|---|---|
directory not found | The target path is wrong or not mounted in the workspace. | Re-run discovery with the absolute path to the skill directory. |
jinja2 not installed | The renderer dependency is missing. | Install jinja2, then re-run render_card.py. |
Context validation failed | Required fields are missing or typed incorrectly. | Fix the context JSON using references/style-guide.md. |
| Unresolved marker failure | VERIFY or SELECT markers remain after review. | Confirm each marked field, prune catalog entries, then re-run validate_submission.py. |
Files in this skill
SKILL.md- this file (orchestration)references/style-guide.md- per-context-field guidancereferences/skill-card.md.j2- exact card layoutreferences/Skill Card Generator License.txt- license text for this skill packagereferences/catalog/limitations.json- canned technical-limitations catalogreferences/catalog/risks.json- canned risk-management catalogscripts/discover_assets.py- discovery and signal extractionscripts/render_card.py- Jinja renderer with context validationscripts/validate_submission.py- pre-submission marker validator
© NVIDIA, 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 13 other files (scripts, references) in skills/skill-card-generator of NVIDIA/skills.
- SKILL.md
- BENCHMARK.md
- Skill Card Generator Card
- Skill Card Generator License
- evals/evals.json
- references/catalog/limitations.json
- references/catalog/risks.json
- references/skill-card.md.j2
- references/style-guide.md
- scripts/discover_assets.py
- scripts/render_card.py
- scripts/validate_submission.py
- skill-card.md
- skill.oms.sig
Open the folder on GitHubat commit 0e0d506
Compare with similar skills
Skill Card Generator 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.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Skill Card Generator this skillNVIDIA/skills | 3.5k | — | ~1.6k | Automated safety check: Notes | Apache-2.0 | |
| LLM Torch Profiler Analysissgl-project/sglang | 37k | 2 repos | ~6.4k | Automated safety check: Pass | Apache-2.0 | |
| Skill InspectorNVIDIA/SkillSpector | 20k | — | ~1.8k | Automated safety check: Pass | Apache-2.0 | |
| Embeddings via 9Routerdecolua/9router | 30k | — | ~604 | Automated safety check: Pass | MIT | |
| NEAR AI Cloud Private Inferenceinternet-court/internet-court-skill | 6.4k | 2 repos | ~1.3k | Automated safety check: Pass | Custom licence | |
| Nemoclaw Maintainer Normalize Title TagsNVIDIA/NemoClaw | 23k | — | ~693 | Automated safety check: Pass | Apache-2.0 |
Similar skills
- Official
Skill Inspector
NVIDIA/SkillSpector
Decides whether an agent skill is safe to install by combining a SkillSpector static scan with the agent's own source review, ending in APPROVE, CAUTION or REJECT.
Embeddings via 9Router
decolua/9router
Generates vector embeddings through the 9Router /v1/embeddings endpoint, using models from providers such as OpenAI, Gemini, Mistral and Voyage for RAG and semantic search.
NEAR AI Cloud Private Inference
internet-court/internet-court-skill
Shows how to call NEAR AI Cloud through an OpenAI-compatible API and verify that inference ran in a TEE, using attestation checks and signed chat responses.
- Official
Nemoclaw Maintainer Normalize Title Tags
NVIDIA/NemoClaw
Remove bracketed NemoClaw tags from GitHub issue and PR titles.
- Official
Megatron-LM Container and Dependency Setup
NVIDIA/Megatron-LM
Walks an agent through working inside the Megatron-LM CI container and changing dependencies with uv, so lock files resolve the same locally and in CI.
More from NVIDIA/skills
All 380 skills in this repo- Official
Vss Deploy Detection Tracking 2D
NVIDIA/skills
A skill your agent uses when the user wants to deploy, run, debug, tear down, or call the REST API of the RTVI-CV 2D detection / tracking microservice.
- Official
HSB IP Def File Tool
NVIDIA/skills
Generates, validates, compares and explains HOLOLINK_def.svh macro files for the HSB IP, using bundled Python scripts and asking before it writes anything.
- Official
Isaac Sim Mission Control Showcase
NVIDIA/skills
Runs and validates an end-to-end Mission Control demo in a locally installed Isaac Sim, with a Nova Carter robot driven through a Python server.
- Official
Defect Image Generation with Cosmos AnomalyGen
NVIDIA/skills
Orchestrates defect image generation for PCBA, metal surface and glass inspection with NVIDIA Cosmos AnomalyGen on OSMO, from cold-start Day 0 to real-photo Day 1 labeling.
- Official
Physical AI Video Augmentation on OSMO
NVIDIA/skills
Orchestrates video data augmentation and auto-labeling workflows on OSMO, from flow selection and preflight checks to submission, monitoring and output download.
- Official
TAO Detection KPI Analysis
NVIDIA/skills
Runs NVIDIA TAO Data Services KPI analysis on object detection results, comparing predictions to ground truth and writing per-class precision, recall and AP to a CSV.
Related
Works with
Questions about Skill Card Generator
What does Skill Card Generator do?
Use only to generate or update a governance skill card for a specified existing agent skill directory. Skill Card Generator is an agent skill from NVIDIA/skills, published by the product's own GitHub organization. Use only to generate or update a governance skill card for a specified existing agent skill directory.
When should I use Skill Card Generator?
Skill Card Generator fits situations like: discussing skill capabilities.
How do I install Skill Card Generator in Claude Code?
Run `npx skills add NVIDIA/skills --skill skill-card-generator -a claude-code`. Or copy the skill folder (skills/skill-card-generator in NVIDIA/skills) into .claude/skills/skill-card-generator in your project. Claude Code loads it when a task matches its description.
How do I install Skill Card Generator in Codex?
Run `npx skills add NVIDIA/skills --skill skill-card-generator -a codex`. Or copy the skill folder (skills/skill-card-generator in NVIDIA/skills) into .agents/skills/skill-card-generator in your project. Codex loads it when a task matches its description.
Can I use Skill Card Generator 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/skills --skill skill-card-generator -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/skill-card-generator, .gemini/skills/skill-card-generator, .github/skills/skill-card-generator and .opencode/skills/skill-card-generator in your project.
What does Skill Card Generator need to run?
Going by SKILL.md and its folder, Skill Card Generator needs Python for the scripts in its folder. Our summary lists: Python 3. Compatibility (from SKILL.md): Any agent that can run Python scripts and write files.
Does Skill Card Generator access the network?
SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.
Is Skill Card Generator safe to install?
Our automated static check of SKILL.md found notes only (mentions a .env file), nothing it rates as a warning. It is not a guarantee. The check reads SKILL.md only: the scripts in the folder are not scanned, so read them before running anything.
What licence does Skill Card Generator use?
Skill Card Generator 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 Skill Card Generator use?
About 1.6k tokens (SKILL.md is roughly 6.4k 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 7.5k tokens, read only when the agent opens those files.
What are the alternatives to Skill Card Generator?
Skills that share tags, products or a category with Skill Card Generator: LLM Torch Profiler Analysis (sgl-project/sglang, 37k stars), Skill Inspector (NVIDIA/SkillSpector, 20k stars), Embeddings via 9Router (decolua/9router, 30k stars) and NEAR AI Cloud Private Inference (internet-court/internet-court-skill, 6.4k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Skill Card Generator?
NVIDIA (a GitHub organization, an official publisher) maintains it in NVIDIA/skills, which has 3,534 GitHub stars. The repository holds 380 skills in this directory. The repository was last updated on October 7, 2026.
Source: NVIDIA/skills on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.