Çoklu dosya
securityResmi
Resmi Sağlayıcı Skill'iView repo
Grill the user relentlessly about a plan, decision, or idea. Use when the user wants to stress-test their thinking, or uses any 'grill' trigger phrases.
Dosyalar2 dosya
SKILL.md23 satır
Loading editor…
Kurulum
ÖnerilenTek komut — ajanınız otomatik olarak devreye alır.
Kurulum komutunu görmek için yukarıdan bir AI aracı seçin.
veya
Manuel Kurulum
Daha fazla adımArşivi indirin ve dosyaları projenize manuel olarak ekleyin.
Skill detayları
Versiyonv1.0.0
YazarMicrosoft
Kategorisecurity
Skill IDmicrosoft/frontier-ghcp-rvas/.github/skills/grilling
Dosyalar2 dosya
İlgili skill'ler
Ai Slop DetectorUser-invocable audit skill for detecting and surfacing AI-slop in documents and code: content that sounds AI-generated, is useless, generic, overconfident, fake, verbose, mechanically structured, or exists because of common LLM failure modes. Use only when the user explicitly asks to run the ai-slop-detector skill, asks for an AI-slop audit, or asks to list AI-generated slop in documents/code. Do not auto-trigger for normal writing edits, humanizing text, code review, linting, or implementation Ask MattAsk which skill or flow fits your situation. A router over the skills in this repo.Code ReviewReview the changes since a fixed point (commit, branch, tag, or merge-base) along two axes — Standards (does the code follow this repo's documented coding standards?) and Spec (does the code match what the originating issue/spec asked for?). Runs both reviews in parallel sub-agents and reports them side by side. Use when the user wants to review a branch, a PR, work-in-progress changes, or asks to "review since X".Codebase DesignShared vocabulary for designing deep modules. Use when the user wants to design or improve a module's interface, find deepening opportunities, decide where a seam goes, make code more testable or AI-navigable, or when another skill needs the deep-module vocabulary.Content AuditAudit RVAS delivery session content (tracks, challenges, docs, starter code) for correctness, hallucinations, outdated information, pacing, broken links, and convention violations, then fix what it finds. Verifies claims against official Azure and tooling docs on the internet. Use when asked to 'review the content', 'check for errors', 'find hallucinations', 'is this still accurate', 'verify the docs', 'check links', 'audit a track', 'is this challenge doable in time', 'fact-check this', or befoDiagnosing BugsDiagnosis loop for hard bugs and performance regressions. Use when the user says "diagnose"/"debug this", or reports something broken/throwing/failing/slow.