mirror of
https://github.com/magnus919/agent-skills.git
synced 2026-09-11 19:47:12 +03:00
Magnus Hedemark
738ec715e7
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.
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
--helpoutput becomes a contract the agent parses to understand your tool - Every command supports
--jsonfor machine-readable output the agent consumes - Every operation is idempotent —
--dry-runpreviews 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.