#copilot-studio
9skills tagged “copilot-studio”.

Agent Performance Triage
Turn a live agent's analytics and transcripts into a diagnosis and a prioritized improvement backlog.

Agent Red Team
Adversarial assurance review for agents you own: prompt injection, oversharing, leakage and tool misuse, mapped to fixes.

Browser UAT Analyst
Run evidence-driven UAT on any browser-based app — Copilot Studio, Power Platform, Dataverse, Dynamics 365, admin centres, or a custom web app — with Playwright execution, a screenshot evidence ledger, and failure classification that separates product defects from tenant config.

Clipchamp Narrated Demo Video
Produce a polished, narrated demo video of a live web app or Copilot Studio agent — real screen-flow footage under an AI (Ava neural) voiceover — either fully headless (ffmpeg + edge-tts) or assembled in the Clipchamp web UI as an editable project.

Copilot Agent Advisor
Tells you which Microsoft 365 / Copilot Studio agent option fits your scenario — use M365 Copilot as-is, build a standard (declarative) agent, or build a custom (custom engine) agent — and which Copilot Studio harness (GitHub Copilot, standard, or Copilot chat) to build on.

Copilot Studio Agent Test
Test a Copilot Studio agent against your own Q&A set and get a graded pass/fail report — no browser automation.

Copilot Studio Harness Picker
Choose the right Copilot Studio harness and build shape; in Cowork, use GPT-5.6 with High effort for Detailed mode, Claude Opus 5 as fallback, or Auto for Quick mode.

Copilot Studio Knowledge Readiness
Assess whether an uploaded or exported document set is ready to power a Copilot Studio agent. Produces a corpus-based readiness score, prioritized cleanup backlog, chunking and metadata guidance, and a test-prompt suite, while calling out any evidence gaps that require live system review.

Enterprise Agent Design Authority (EADA)
An enterprise design review framework that helps architects build secure, scalable, governable, and production-ready Microsoft Copilot Studio agents.