Agent skills for Gemini CLI

Collect and synthesize opinions from multiple AI agents.

Mint a tamper-evident, post-quantum-signed receipt for a consequential agent action (deploy, delete, pay, grant-access, model decision) so…

Agent Designer - Multi-Agent System Architecture

A scoring scale for evaluating how well a CLI is designed for AI agents, based on the "Rewrite Your CLI for AI Agents" principles.

Head-to-head comparison of coding agents (Claude Code, Aider, Codex, etc.) on custom tasks with pass rate, cost, time, and consistency…

Use for runtime policy enforcement and governance of AI agents with Microsoft's Agent Governance Toolkit (AGT).

Use when an agent workflow needs deterministic recovery evidence for sandbox, MCP/tool, worker, checkpoint, memory, or orchestration…

只读统计 Claude/Codex 的 Skill 使用证据并检查 agent 配置健康。仅用于明确的健康检查、配置诊断、使用排行或低使用候选请求；会识别 enabled 插件并单列批量审计读取。不要用于规范源、触发、全局/项目/profile/冷存储、投影或退役治理，改用…

Structured self-debugging workflow for AI agent failures using capture, diagnosis, contained recovery, and introspection reports.

Use when a user wants to build, launch, grade, or schedule a Claude Managed Agent (CMA) in their own Anthropic account — "build me an…

Build applications where agents are first-class citizens.

Agent Nurture Framework: a systematic methodology for training AI agents from novice to expert through conversational knowledge…

Use when auditing an AI agent system against the OWASP Agentic Security Initiative Top 10 — checks tool access, prompt boundaries, memory…

Add x402 payment execution to AI agents with per-task budgets, spending controls, and non-custodial wallets.

Interview the user and produce an Agent PRD — the planning document that must exist before any agent code is written.

Transforms vague problems into structured, agent-solvable problem briefs and evaluates their automation feasibility.

Compile a narrative persona, style guide, or best-practices document into a compact, imperative rule set suitable for an agent's system…

Triage failed Agent QA runs with MCP evidence, artifacts, logs, fixed failure categories, confidence, and actionable next steps.

Agent skill for queen-coordinator - invoke with $agent-queen-coordinator

Give your AI agent eyes to see the entire internet. 17 platforms via CLI, MCP, curl, and Python scripts.

Create LangChain agents with create_agent, define tools, and use middleware for human-in-the-loop and error handling.