agentleFS
Sign inStart free
NVIDIAKnown publisherNVIDIA/kumo-engine/.agents/skills/preflight/SKILL.md

preflight

Skill34 starsChanged 23 days agoApache-2.0View on GitHub

Use before a debugging workflow, when asked to check the environment, or when the local CLI tools needed for the requested task are not working.

We split this skill into the rules it gives an agent

8 rules. 0 are common, 7 are distinctive, and 1 is very specific to this project.

  • 0

    Common

    Most of the 39 edited versions we read keep these.

  • 7

    Distinctive

    This author's own choices. Worth a look.

  • 1

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Use this skill when the user:

    line 10
  2. Distinctive:

    Before starting a debugging workflow

    line 12
  3. Distinctive:

    When local CLI tools aren't working

    line 13
  4. Distinctive:

    Run only checks needed for the requested task.

    line 17
  5. Distinctive:

    Check this only when the user wants a second opinion.

    line 42
  6. Distinctive:

    Check local prerequisites only after the user selects Kubernetes logs for this task.

    line 52
  7. Very specific:

    Use check-logs for authorized log collection.

    line 62
  8. Distinctive:

    If any required checks fail, provide specific remediation steps.

    line 106

“Common” is measured: kept by at least 6 in 10 of the 39 edited versions of this file we could read. “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

Preflight Checks

When to Use

Use this skill when the user:

  • Asks to "check environment", "preflight", or "validate setup"
  • Before starting a debugging workflow
  • When local CLI tools aren't working

Run only checks needed for the requested task. Do not install system packages, change global configuration, or contact private services automatically.

Step 1: GitHub CLI (skippable)

Note: User can skip this step if they don't need GitHub issue integration or will provide issue details manually.

echo "=== GitHub CLI ==="
if command -v gh &> /dev/null; then
    echo "✓ Installed: $(gh --version | head -1)"
    if gh auth status 2>&1 | grep -q "Logged in"; then
        echo "✓ Authenticated"
    else
        echo "✗ Not authenticated - run: gh auth login"
    fi
else
    echo "✗ Not installed - https://cli.github.com/"
fi

Step 2: Optional Codex Consultation

Check this only when the user wants a second opinion. Identify the available Codex session or configured integration; do not start a model call as a generic preflight probe. See the consultation reference for the handoff prompt and optional Codex MCP configuration. Missing integration does not block debugging or an already requested fix.

Step 3: Kubernetes (when collecting live logs)

Check local prerequisites only after the user selects Kubernetes logs for this task. Record the supplied context, namespace, and workload; ask only for missing target details. These checks do not contact the cluster:

command -v kubectl
kubectl version --client
kubectl config get-contexts "{context}"

Use check-logs for authorized log collection. A supplied log file does not require kubectl or a Kubernetes login.

Step 4: Docker (when needed)

echo "=== Docker ==="
if command -v docker &> /dev/null; then
    echo "✓ Installed: $(docker --version)"
    if docker info &> /dev/null 2>&1; then
        echo "✓ Daemon running"
    else
        echo "✗ Daemon not accessible"
    fi
else
    echo "✗ Not installed"
fi

Summary Format

━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
           PRE-FLIGHT CHECK SUMMARY
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━

Required (skippable if not using GitHub issues):
  gh CLI:              {✓/✗}
  gh authenticated:    {✓/✗}

Task-dependent:
  Docker:              {✓/✗/not needed}
  kubectl / context:   {✓/✗/not needed}

Optional:
  Codex consultation:  {available/unavailable/not requested}

━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━

If any required checks fail, provide specific remediation steps.

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.

Reviews can't be read right now.

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.

Check your setup, free