From armor
Audits a live API against its OpenAPI/Swagger spec by spawning subagents to verify requests, responses, and error handling. Use when QA'ing an API implementation.
How this skill is triggered — by the user, by Claude, or both
Slash command
/armor:become-rest-client <spec> <server> <details><spec> <server> <details>specserverdetailsThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
Audit `$server` against spec `$spec` using only the spec as your map. `$details` may narrow scope.
Audit $server against spec $spec using only the spec as your map. $details may narrow scope.
Pick a kebab-case $NAME from the spec's info.title, then:
./scripts/ensure-restish.sh
./scripts/init-api.sh --name "$NAME" --spec "$spec" --base "$server"
# init refuses if "$NAME" already exists; switch to update-api.sh if so
restish $NAME --help now lists every operation grouped by tag.
Group operations by tag. In one message, spawn a parallel Agent per tag. Each subagent gets the API name, its operation list, auth (existing profile or a bearer via -H authorization:...), and this checklist:
restish <name> <op> --help — required flags match the spec?<op> — expected — actual — severity. Structured, ~300 words max.Group findings as spec lies (server contradicts spec), spec gaps (server returns undocumented things), server bugs (violates own spec), ambiguities (spec silent). Link each to the operation. The user files tickets from this.
npx claudepluginhub markacianfrani/armor --plugin armorGuides creation, editing, and verification of skills for AI coding agents using test-driven development with subagent scenarios. Use when authoring or debugging skills.