The "Completed Architecture" diagram in Phase 4 showed the CLI binary at the
skill root, but every other skill in this repo (and the Agent Skills spec)
places executable scripts in a `scripts/` subdirectory.
Changes:
- Replaced ASCII-art two-layer diagram with concrete directory structure
showing `scripts/servicex-cli` inside the skill directory
- Added Trigger/Execute layer table clarifying the role of each file
- Updated the "Agent opens session" flow to use `scripts/` relative paths
- Added deployment model comparison (scripts/ inside skill vs global PATH)
- Updated the "Installation instructions" entry in What NOT to Put table
Trigger: neopabo on Nous Research Discord
Signed-off-by: Magnus Hedemark <magnus919@pm.me>
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>
Magnus Hedemark