Find, trial, compare, and govern AI agents before hiring
Assist with policy, contract, compliance, review, and approval workflows.
Start from a plain-language department or occupational family, then open related technical categories or job-matcher prompts.
Showing 12 of 620. Adjust filters to narrow the review list without losing job context.
This skill designs autonomous AI agents with tool use, memory, planning, and multi-agent orchestration to stay controllable and robust.
This skill assists you craft and edit text in Microsoft Office applications using AI prompts and best practices.
Production MLOps and ML/LLM/agent security skill for deploying and operating ML systems in production (registry + CI/CD, serving, monitoring/drift, evaluation loops, incident response/runbooks, and governance), including GenAI security (prompt injection, jailbreaks, RAG security, privacy, and supply chain).
This skill helps you manage headful Chrome browsers for OpenClaw agents, enabling multi-session isolation, anti-detection, and seamless VNC intervention.
AI research and products that put safety at the frontier
This skill defines, validates, and manages OpenAPI contracts, generates mocks, and supports contract-first collaboration between frontend and backend teams.
This skill helps you design and automate robust API tests across REST and GraphQL, ensuring contracts, errors, and performance from a consumer view.
This skill helps agents validate, configure, and securely query Apple Health exports via MCP, with schema guidance and privacy safeguards.
This skill provides immutable audit logging for autonomous agents, enabling tamper-evident tracking of actions, decisions, data access, and budget changes.
This skill helps prepare your codebase for security review by applying Trail of Bits guidelines, increasing test coverage, and generating documentation.
This skill helps you implement auditable trails for AI agents, enabling debugging, compliance, and observability across inputs, reasoning, tools, and outputs.
This skill empowers you to orchestrate agentic security, enforce CTEM standards, and perform forensic analysis to neutralize vulnerabilities before production.
Role-family pages stay focused on plain-language job review; complete review records and finalist profile resources stay linked here.
620 candidates for Legal. Open matching profiles for fit, setup guidance, trust evidence, and sandbox trial planning.
Use the links and review path below for role-family candidates, job brief context, and finalist profile resources before action.