agentleFS
NVIDIAKnown publisherNVIDIA/elements/.agents/skills/agent-availability-report/SKILL.md

agent-availability-report

Skill115 starsChanged 55 days agoApache-2.0View on GitHub

Generate a production availability report for NVIDIA Elements packages, skill registry, and documentation.

  • Installs packages

The file

We split this skill into the rules it gives an agent

11 rules. About 0 are common, 5 are distinctive, and 6 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈5

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 6

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Verify that the latest NVIDIA Elements packages are available on npm, confirm the Elements skill installs from GitHub, confirm the …

    line 12
  2. Distinctive:

    Read the root AGENTS.md.

    line 16
  3. Very specific:

    Run from the repository root with the pinned toolchain through mise.

    line 17
  4. Distinctive:

    Run the deterministic report script:

    line 22
  5. Very specific:

    Do not repeat those lists or the report format in this skill.

    line 42
  6. Distinctive:

    Run the deterministic script from the repository root.

    line 69
  7. Distinctive:

    If the script exits non-zero after printing a report, still use the printed report and treat the exit code as the failure signal.

    line 71
  8. Distinctive:

    Do not rewrite, summarize, or recompute the generated report.

    line 73
  9. Very specific:

    Use --json to print structured report data.

    line 79
  10. Very specific:

    Use --timestamp <iso-utc> only for deterministic verification.

    line 80
  11. Very specific:

    Stop early only for environment-level problems, such as missing npm.

    line 81

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Agent Availability Report

You are an Elements package availability verification agent.

Goal

Verify that the latest NVIDIA Elements packages are available on npm, confirm the Elements skill installs from GitHub, confirm the documentation site is live, and generate a brief status report.

Prepare the Run

  1. Read the root AGENTS.md.
  2. Run from the repository root with the pinned toolchain through mise.
  3. Preserve the current worktree. The report must not change tracked files.

Deterministic Script

Run the deterministic report script:

mise exec -- node .agents/skills/agent-availability-report/scripts/generate-availability-report.js

The script is the source of truth for:

  • package order through PACKAGES
  • docs URL order through DOCS_URLS
  • npm metadata checks
  • npm install checks
  • Node package resolution checks
  • Elements skill installation through the public skills CLI
  • docs URL checks
  • package version comparison
  • temporary project creation and cleanup
  • status calculation
  • report formatting

Do not repeat those lists or the report format in this skill. Update scripts/generate-availability-report.js instead.

Script Behavior

The CLI prints timestamped phase updates and 30-second heartbeats for long-running commands to standard error. Concurrent checks can finish in any order. It reserves standard output for the formatted or JSON report and exits with code 1 only when the generated report has overallStatus: "FAIL".

The exported API returns both the formatted report and structured data:

const { formattedReport, report } = await generateReport();

Return or surface formattedReport as the generated report.

The script creates temporary projects with:

  • mkdtemp(path.join(os.tmpdir(), 'nvidia-elements-agent-availability-report-'))
  • npm init -y
  • npm install --no-audit --no-fund ...
  • mkdtemp(path.join(os.tmpdir(), 'nvidia-elements-agent-skill-availability-'))
  • npx skills@1.7.0 add https://github.com/nvidia/elements --skill elements
  • verification that .agents/skills/elements/SKILL.md declares the elements skill

It removes the temporary projects before returning the report.

Report Workflow

  1. Run the deterministic script from the repository root.
  2. Return or surface the formatted report produced by the script.
  3. If the script exits non-zero after printing a report, still use the printed report and treat the exit code as the failure signal.

Do not rewrite, summarize, or recompute the generated report.

Report delivery is outside this skill.

Debugging

  • Use --json to print structured report data.
  • Use --timestamp <iso-utc> only for deterministic verification.
  • Stop early only for environment-level problems, such as missing npm.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.