Fire the adversarial-sprint runner via the per-pilot overlay. Triggered when the operator asks for an adversarial sprint, a review-driven build, or a multi-chunk change with cross-family gates. Single-purpose: get the operator from "fire the runner" to a run command, without re-teaching them the framework CLI. For durable principles (digest + index + rehydration), see skills/adversarial-sprint/SKILL.md.
claude-skill
platform-diagnostics
ANo problem foundTeslemetry/hass-teslemetry
Platform exists as homeassistant/components/<domain>/diagnostics.py.
platform-diagnostics got grade A on our automated scan on 2026-10-26.
Before you install
- Read any scripts this skill ships.
- Note every URL it fetches.
- Check allowed-tools and hooks.
Embed this grade
Add this badge to your README. It shows the current grade from CheckSkills.
Report this skill if the grade looks wrong, or if something slipped through.
Related
Use when a consumer repo needs proposal-first backlog, Registry, and Atlas drafts from new project intent before source exists.
The report notes that src/resolver/strategies/openapi-3-2-apidom/resolve.js uses apidom-reference's openapi-3-1 resolve strategy instead of openapi-3-2.
interface: displayname: "Run Tests" shortdescription: "The user wants to run XCUITests, parse test results, view test failures, or export test attachments."
const { testComponent } = require('./implementation')