A virtual data architect for teams without one. Includes:
- 8 reference files covering architecture patterns, cloud platforms,
governance maturity, anti-patterns, compliance, vendor evaluation,
case studies, and discovery frameworks
- Interactive governance maturity assessment script
- ADR template for capturing architecture decisions
- 4 Mermaid decision trees for common architecture choices
- QuickScan and proactive discovery flow for users who don't know
where to start
No personal or identifying information included.
CLI wrapper for the WeatherFlow Tempest API: current conditions,
forecast, historical observations, and real-time UDP broadcasts.
Demonstrates all cli-builder patterns in a working, testable project:
- Non-interactive with --json, --dry-run, --quiet, --verbose
- Lazy auth (--help and --dry-run work without a token)
- Multi-device filtering (auto-skips HB hub, prefers ST > SKY > AIR)
- Dual-output via emit() helper
- Structured logging with log/warn/die
- Stderr hygiene and import-time warning suppression
- Idempotent operations
- Global flags in any position (pre-parsed from argv)
Includes the Python CLI script (scripts/tempest-cli) and full API
field layout reference (references/tempest-api-field-layouts.md).
Signed-off-by: Jasper <magnus@groktop.us>
Adds a new Phase 4 section to the cli-builder skill that teaches how
to wrap a CLI tool in an agentskills.io-compliant SKILL.md wrapper,
creating the two-layer architecture: CLI as execution engine + skill
as trigger surface. Includes a complete worked example (weather-cli)
with frontmatter conventions, essential commands, gotchas, and auth
wiring documentation.
Signed-off-by: Jasper <magnus@groktop.us>
10 universal patterns for building CLI tools that AI agents can use
reliably: non-interactive, --json, --dry-run, idempotent, lazy auth,
progressive help, and more. Includes a bash scaffold template, Python
API client reference, advanced edge-case patterns, MCP-vs-CLI decision
framework, and an improvement cycle for iterating on shipped tools.
Principles grounded in real failures from building 15+ agent-facing
CLIs across multiple API services.
Signed-off-by: Jasper <magnus@groktop.us>
SKILL.md distills the full specification from agentskills.io — directory
structure, frontmatter schema, naming rules, progressive disclosure model,
and best practices for skill creation. Includes all 8 source pages as
reference files for on-demand loading.
Magnus Hedemark
Magnus Hedemark