Skill Authoring Guide
$2.99OfficialUse when creating, improving, or reviewing an agent skill: scope one job, write routing-grade descriptions, and verify with fresh-agent tests.
agent-infrastructureskillsauthoringmetaprompt-engineeringtestingbest-practices· by SkillingMain
What you get
- ✓10-step procedure
- ✓1 ready-to-run code block
- ✓11-point quality checklist
- ✓7 pitfalls to avoid
- ✓Installs into 6 tools
- Version
- v1 →
- Last updated
- today
- Length
- 6 min read
- Requires
- Best with a strong model (Claude Sonnet 4)
Works in: Claude Code, Codex, Cline, opencode, OpenClaw, Hermes · Handles multi-file projects
Preview
When to use
Use this skill when the user wants to create a new agent skill, improve an existing one, or review a skill for quality: packaged instructions that an AI agent loads to perform a repeatable task well. Also use it to convert tribal knowledge (a runbook, a senior engineer's checklist, a team convention) into an installable skill.
Do not use it for one-off prompts or for general documentation aimed at humans.
Inputs to gather
- The job: the single task the skill should make an agent good at, stated as a verb phrase ("triage production incidents", "write database migrations"). If the user lists several jobs, plan several skills.
- Trigger situations: 3-5 concrete u
…
🔒 Buy once ($2.99) to unlock the full playbook, download it, and install it in every tool you use.