Files
magnus919_agent-skills/cli-builder/README.md
T
Magnus Hedemark 738ec715e7 Add human-focused README.md to every skill and bundle directory
Each README is written for a human audience, explaining:
- What the skill does (not what format it follows)
- What benefit the user gets from installing it
- Quick setup and usage patterns
- When to load/trigger the skill
- What scripts, references, and templates it ships

data-scientist already had a README — left unchanged.

48 READMEs added across all skill and bundle directories.
2026-07-09 22:30:12 -04:00

30 lines
1.4 KiB
Markdown

# CLI Builder — Design Agent-Friendly CLI Tools
A comprehensive design guide and scaffold for building CLI tools that **AI agents can actually use**. 10 universal design patterns grounded in real failures from building 15+ agent-facing CLIs.
## Why Install This Skill
When your agent loads this skill, it can **design, build, and refactor CLI tools** that agents can discover and use without human help. That means:
- **Every `--help` output becomes a contract** the agent parses to understand your tool
- **Every command supports `--json`** for machine-readable output the agent consumes
- **Every operation is idempotent** — `--dry-run` previews changes before they happen
- **Authentication is lazy** — help and dry-run work without credentials
- **Errors are structured** — different exit codes for different failure modes
## What You Get
| Directory | Purpose |
|-----------|---------|
| `SKILL.md` | 500+ line reference: 10 design patterns, 3-phase build workflow, agent-compatibility test suite |
| `templates/` | Python API client scaffold and bash CLI scaffold |
| `references/` | Agent-compatibility test suite, Python API client pattern |
## Triggers
Load this when building a new CLI tool, refactoring an existing tool that causes agent friction, or debugging why your agent keeps failing to use a CLI properly.
## Requirements
Bash, Python 3.8+, jq, and a standard Unix CLI environment.