WYRE-AI [Skill Title]
Overview
One short paragraph: what this domain is and what an MSP does with it.
Anti-triggers
Where this skill gets loaded by mistake, and what to load instead. One bullet per case, each naming the correct destination skill:
- [Neighbouring concern] — use
[vendor]-[other-skill]instead. - [Adjacent vendor with overlapping vocabulary] — this skill only speaks the [Vendor] API.
Include this section only when a real routing mistake exists: a
sibling skill in the same plugin covering an adjacent entity, or another
vendor sharing this one's vocabulary. Two skills whose names alone
disambiguate them do not need it. A bullet that just negates the
when_to_use ("do not use for non-[Vendor] questions") is filler —
cut it.
Key Concepts
The entities, relationships, and terminology Claude needs before touching the API. Prefer a compact table for enums and status codes. If the full field reference is long, summarize the important fields here and link the complete table:
See references/fields.md for the complete field reference.
Common Workflows
Workflow name
- Step one
- Step two
Include decision points and the non-obvious ordering constraints. Skip workflows that are just "call the endpoint."
API Patterns
The request shapes that aren't guessable — auth quirks, pagination
casing, filter syntax. Link references/api.md for the exhaustive
endpoint catalog if it's long.
Gotchas
The section that earns the skill its tokens: rate-limit behavior, case-sensitive parameters, fields that silently drop, errors whose messages mislead. Each entry: what happens, why, what to do instead.
Related Skills
Only if the links genuinely route the reader somewhere (e.g., a shared auth skill). Omit otherwise.