create-skill

/create-skill — Skill Factory

Create a new Claude Code skill with correct structure, robust bash, and built-in quality gates. This skill encodes lessons from 250+ Greptile review comments to prevent the most common skill authoring mistakes.

Arguments

• $ARGUMENTS must contain the skill name in kebab-case (e.g. deploy-check)
• If $ARGUMENTS is empty, ask the user for a skill name before proceeding

Set SKILL_NAME to the provided name. Validate it is kebab-case (^[a-z][a-z0-9]*(-[a-z0-9]+)*$). Reject otherwise.

---

Phase 0 — Discovery & Pre-flight

Pre-flight: Verify required tools and environment:

for tool in git mktemp; do
  # > /dev/null 2>&1: suppress command path on success and shell's "not found" on failure — the || clause provides the error message
  command -v "$tool" > /dev/null 2>&1 || { echo "ERROR: required tool '$tool' not found"; exit 1; }
done
# > /dev/null 2>&1: suppress git's own "fatal: not a git repository" — our || message is more actionable
git rev-parse --show-toplevel > /dev/null 2>&1 || { echo "ERROR: not in a git repository — run /create-skill from the repo root"; exit 1; }

Parse $ARGUMENTS per the Arguments section above. If validation fails, abort with a clear error.

Discovery: Before writing anything, gather requirements interactively. Ask the user these questions (all at once, not one-by-one):

1. Purpose — What does this skill do? (one paragraph)
2. Arguments — What CLI arguments should it accept? (e.g. --fix, --dry-run, <path>)
3. Phases — What are the major steps? (bullet list of 3-8 phases)
4. Tools needed — Which tools does it need? (Bash, Read, Write, Edit, Glob, Grep, Agent)
5. Artifacts — Does it produce output files? If so, where and what format?
6. Dangerous operations — Does it modify code, push to git, call external APIs, or delete files?
7. Resume/skip support — Should it support --start-from or --skip-* flags for long-running pipelines?

Wait for the user's answers before proceeding. Do not guess or assume.