Skip to main content

preflight

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.

Source facts

Repository
NVIDIA/kumo-engine
Last source activity
October 9, 2026 at 00:32
Detected SKILL.md language
English
Stars
38
Forks
8

Install options

The review-first prompt is selected by default. You can switch to a direct command or download a local copy.

Review the source files

Read SKILL.md and any companion files shown by SkillsMP before deciding whether to install.

File Explorer
2 files

Showing SKILL.md

SKILL.md
Source instructions · Read-only preview
name
preflight
description
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.
# 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. ```bash 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](references/codex-mcp.md) 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: ```bash command -v kubectl kubectl version --client kubectl config get-contexts "{context}" ``` Use [check-logs](../check-logs/SKILL.md) for authorized log collection. A supplied log file does not require `kubectl` or a Kubernetes login. --- ## Step 4: Docker (when needed) ```bash 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.
View on GitHub