# Invocation Doctor

> Test and improve whether an agent invokes a skill on the right requests and avoids invoking it on near-miss requests. Use when a skill works explicitly but is under-triggered, over-triggered, or has a weak description.

- Skill: `getedgehq/invocation-doctor` (Agent Skill, multi-file: 9 files)
- Install (CLI): `npx skillmds@latest add getedgehq/invocation-doctor`
- Raw SKILL.md: https://api.skillmd.com/api/skills/getedgehq/invocation-doctor/raw
- Safety review: pending
- Works with: Claude Code, Claude.ai, OpenAI Codex
- Category: AI & ML
- Author: getedgehq (https://skillmd.com/u/getedgehq)
- Updated: 2026-09-22
- Page: https://skillmd.com/skills/getedgehq/invocation-doctor

---


# Invocation Doctor

1. Create positive, near-miss negative, and ambiguous trigger cases.
2. Split cases before optimizing; do not tune on every example.
3. Use Waza when available to run the actual trigger suite.
4. Rewrite only the skill description first; avoid bloating the body to solve discovery.
5. Compare held-out precision/recall before vs after.
6. Publish both regressions and improvements.