AI & Agents Agent Skills for Cursor

Orchestrates multi-agent AI teams with persistent file-based planning and role-based collaboration for complex projects.

Manages workflow transitions and completion reports in 2-Agent workflow.

Apply Chain-of-Verification (CoVe) prompting to improve response accuracy through self-verification.

Chain patterns for multi-phase pipelines: MCP detection, handoff files, checkpoint-resume, worktree agents, CronCreate monitoring.

Format prompts for different LLM providers with chat templates and HNSW-powered context retrieval

Use this skill when creating, improving, or optimizing prompts for Claude.

Split a file into overlapping chunks suitable for parallel fanout processing and emit a manifest describing each chunk

Score any MCP server, API, or CLI for agent-readiness using Clarvia AEO (Agent Experience Optimization).

Deep specialist in Claude Code - Anthropic's CLI.

Use when orchestrating multi-agent code analysis with claudemem.

CRITICAL - Guide for using Claudish CLI ONLY through sub-agents to run Claude Code with OpenRouter models (Grok, GPT-5, Gemini, MiniMax).

Manage persistent coding sessions across Claude Code, Codex, Antigravity (agy), Grok Build, and OpenCode engines.

Use when specs are mature enough to split work into parallel ClawdStrike lanes with explicit ownership, dependency graphs, verification…

Build enterprise agents for Microsoft 365, Teams, and Copilot Studio using the Microsoft Agents SDK with aiohttp hosting, AgentApplication…

Orchestrates long-running multi-stage tasks through structured planning, executor-evaluator subagent loops, and rigorous acceptance…

Automate Composio tasks via Rube MCP (Composio).

Guide for creating effective skills. This skill should be used when users want to create a new skill (or update an existing skill) that…

Install Codex skills into $CODEX_HOME/skills from a curated list or a GitHub repo path.

Configure which review agents run for your project.

Build AI agents that interact with computers like humans do -

Multi-protocol consensus for agent swarms supporting Raft leader election, Byzantine fault tolerance, Gossip state propagation, and CRDT…