Security & Testing Agent Skills for Microsoft Copilot

Take over Active Directory user and computer accounts by writing alternate certificate keys to msDS-KeyCredentialLink (Shadow Credentials)…

Evaluate learning materials and technology for WCAG, Section 508, and accessibility compliance with remediation recommendations

Use when users need to debug, modify, or extend the code-forge application's CLI commands, argument parsing, or CLI behavior.

Add a new or companion test across identifiers, limits, implementation, datalogging, bins, and active flow.

Add Clerk authentication to any project by following the official quickstart

Printing Press CLI for Adguard Home. AdGuard Home REST-ish API. Our admin web interface is built on top of this REST-ish API.

Every Admin By Request portal action, plus a local SQLite mirror of audit, events, inventory and requests for ad-hoc...

Use when iterating on a fix after an adversarial code review (Codex, human reviewer) surfaces design-level findings — not typos, lint, or…

Roleplay a hostile user to find and triage UX pain points.

Dispatch subagents to refute each finding listed earlier in this session, then report which survive.

Orchestrate an Aegis runtime-reliability investigation from repository analysis through sandbox reproduction, diagnosis, repair…

Full-stack diagnostic for agent and LLM applications.

This skill should be used when the user wants to "run an evaluation", "evaluate my ADK agent", "write an eval dataset", "analyze eval…

Designs and runs agent evaluation frameworks to measure and improve performance.

Check any AI agent codebase against the OWASP Agentic Security Initiative (ASI) Top 10 risks.

Verify AI agent patterns including loop safety, retry limits, tool consistency, context size, and graph cycle analysis.

Create, edit, validate, and run Agent QA tests, suites, and hooks through MCP or CLI while preserving canonical IDs and schema contracts.

Debug, patch, and verify failed Agent QA runs from MCP evidence, artifacts, logs, and local code without hiding product or infrastructure…

Use this skill when an agent is about to follow, publish, or delegate a runbook and needs a local readiness check first.

Use this skill before an agent asks for approval to send, publish, delete, write to an external system, or otherwise create side effects.

Audits and validates AI agent skills against strict structural and pre-release packaging checklists.