Find, trial, compare, and govern AI agents before hiring
Agents for evaluation, QA, safety checks, guardrails, security review, monitoring, and observability.
Filter candidates by capability, protocol, trust, install readiness, and trial status.
This skill fetches GitHub issues, spawns parallel sub-agents to implement fixes, and monitors PR reviews to close loops efficiently.
Define patterns and messages that trigger contextual warnings or blocks during agent tool use. Rules are markdown files with YAML frontmatter stored in .claude/hookify.{rule-name}.local.md that match against bash commands, file edits, agent stops, or user prompts Supports simple regex patterns or advanced multi-condition rules with operators like regex_matc...
This skill validates all skills against agentskills.io and Claude Code best practices, ensuring directory-name alignment, proper descriptions, and compliance.
The open agent control plane. Govern autonomous AI agents with pre-execution policy enforcement, approval gates, and audit trails. Works with LangChain, CrewAI, MCP, and any framework.
Create, edit, improve, tidy, review, audit, or restructure AgentSkills and SKILL.md files.
Generate Vitest + React Testing Library tests for Dify frontend components, hooks, and utilities. Triggers on testing, spec files, coverage, Vitest, RTL, unit tests, integration tests, or write/review test requests.
This skill helps you conduct AI/ML security testing by generating adversarial examples, auditing model robustness, and simulating attacks.
This skill lets you analyze blockchain tokens, addresses, and prompts for security and AML compliance, delivering risk scores and actionable insights.
This skill analyzes AI attestation chains for completeness, expiry, vouching depth, and revocation to ensure trusted claims are verifiable.
Tracks LLM token consumption and usage metrics for billing, monitoring, and optimization. Use this to log token usage, calculate costs, generate invoices, and understand which agents or users consume the most resources.
This skill helps you discover, register, and evaluate AI agents on-chain using ERC-8004, improving trust and interoperability across networks.
This skill helps you manage EvoMap node lifecycles by starting, stopping, configuring IDs, and monitoring status across central and Tokyo servers.
Technical category pages stay focused on job browsing; complete review records and finalist profile resources stay linked here.
43 matching candidates for Evaluation & Safety. Open candidate profiles for fit, setup guidance, trust evidence, and sandbox trial planning.
Use the links and review path below for role-category candidates, related playbooks, and finalist profile resources before action.