create-skill

Creating Skills in ClerkBox

This skill guides you through creating effective Agent Skills for ClerkBox. Skills are markdown files that teach the agent how to perform specific tasks: reviewing PRs using team standards, generating commit messages in a preferred format, querying database schemas, or any specialized workflow.

How ClerkBox Uses Skills (read this first)

ClerkBox uses progressive loading: the system prompt only contains a lightweight skill index (slug, name, description, trigger_keywords, path). The agent reads a skill's SKILL.md via read_file only when it matches the current task. Therefore:

1. description + trigger_keywords are the routing signal — they decide whether your skill ever gets read. Make them specific.
2. The user can also activate a skill explicitly by typing /<skill-slug> at the start of a message.
3. chains_to can chain a skill to successor skills (advisory) — after the main action completes, the agent may load a listed successor whose description matches the new state.

Before You Begin: Gather Requirements

Before creating a skill, gather essential information from the user (ask conversationally, one short round):

1. Purpose and scope: What specific task or workflow should this skill help with?
2. Trigger scenarios: When should the agent automatically apply this skill?
3. Key domain knowledge: What specialized information does the agent need that it wouldn't already know?
4. Output format preferences: Are there specific templates, formats, or styles required?
5. Existing patterns: Are there existing examples or conventions to follow?

Inferring from Context

If you have previous conversation context, infer the skill from what was discussed. You can create skills based on workflows, patterns, or domain knowledge that emerged in the conversation.

---

Skill File Structure

Directory Layout

Skills are stored as directories containing a SKILL.md file:

skill-name/
├── SKILL.md              # Required - main instructions
├── reference.md          # Optional - detailed documentation
├── examples.md           # Optional - usage examples
└── scripts/              # Optional - utility scripts
    ├── validate.py
    └── helper.sh