Results for “agent-to-agent”

Coordinates multiple AI agents working on a shared task list using Claude Code's native team tools, with task decomposition, staged execution, and verification.

Automatically detects project state and runs an 8-phase pipeline to plan, build, test, lint, fix bugs, and document code across multiple AI coding agents.

Guides project-level decisions for LLM-powered systems: task-model fit, pipeline architecture, token and cost estimation, and agent-assisted iteration.

Analyze codebase with parallel mapper agents to produce .planning/codebase/ documents

Coordinates a 13-agent team for rigorous academic research on any topic, supporting eight modes from quick briefs to systematic reviews with meta-analysis.

Analyzes past agent sessions to identify recurring failures and skill gaps, then automatically creates or patches skills and runs self-evolution to fix them, tracking improvement over time.

Run an AI Startup division meeting with the seven AI Startup agents (no AI Lab agents). Use when the user requests to "start a startup meeting", "convene the startup team", or "run a sprint review for the product".

Engage with a social platform for AI agents: post text, photos, quotes, links, and chat logs; reblog with commentary; tag content; follow agents; send and answer asks; and manage your profile via a CLI tool.

Resolves legacy references to the legal-counsel capability by routing to the current runtime agent or skill.

Architecture-first workflow for delegating complex projects to AI coding agents. Ensures code fits the system before it's written.

Resolves legacy references to finops-manager by routing to the current runtime capability, agent, or plugin skill.

Convenes a multi-persona council of historical thinkers to deliberate on complex problems and synthesize a verdict.

Migrate Claude Code configuration, skills, agents, and MCP servers to Codex project and global files.

Recommends the best skill, agent, or command for a given task by classifying intent and scanning available tools.

Coordinates four reasoning skills and an agent for structured thinking, problem solving, creative ideation, and learning.

Build and query AI-powered knowledge bases from claude-mem observations, enabling focused conversational sessions on specific topics.

Analyzes recent conversation messages to identify a supporter personality type and generate a shareable identity card with tool recommendations.

Curated collections of agent skills organized by role and expertise level, from essentials to security, web development, AI, and game development.

Enforces evidence-based debugging, safety gates, and anti-slack detection to keep AI agents thorough and honest during code changes.

Writes or updates a HANDOFF.md file in the project root to capture goal, progress, and next steps for a fresh agent to continue in-progress work.

Spawns a researcher agent to investigate how to implement a project phase, gathering context on architecture patterns, standard libraries, and common pitfalls.

Audits Claude Code context window consumption across agents, skills, MCP servers, and rules. Identifies bloat, redundant components, and produces prioritized token-savings recommendations.

Ensures skills are invoked before any response, including clarifying questions, and establishes how to find and use skills.

Maintain durable session memory across agent disconnects by writing structured checkpoints to the repo's session directory, enabling context recovery.

Automate Zoho Desk operations including tickets, contacts, agents, departments, and help desk workflows via Composio's toolkit and Rube MCP.

Optimizes long-running agent sessions with structured context compression, summarization, and durable handoff summaries that preserve decisions, files, risks, and next actions.

Operates as an autonomous system that loads context from index files, follows goal-driven principles, and uses available agents and skills to execute decisions.

Keeps AI coding agents tightly scoped to only change what the user explicitly requested, using the simplest viable solution and asking before expanding scope.

Runs a structured clarifying interview for new project requests before building, then outputs a fully specified prompt.md for a fresh agent session to execute.

Provides jurisdiction-specific legal context and contract scaffolding for the US, EU, and Canada, grounding agents in verified government references to reduce legal hallucinations.

Delegates a bounded repository task to an allowlisted external coding CLI through a guarded runner, with provider selection, timeout handling, and independent local review.

Use when multi-company coordination, cross-team communication, or inter-company workflow execution is needed. This skill defines protocols for agents from different companies to cooperate on shared projects and tasks.

Forces AI agents to investigate before editing or running destructive commands, improving code quality by requiring concrete facts like importers, data schemas, and user instructions.

Provides a structured process for creating or updating skills that extend an AI agent's capabilities with specialized knowledge, workflows, and tool integrations.

Publishes agent skills to GitHub with automatic validation of SKILL.md, README quality checks, repository creation or updates, and real installation verification via npx skills.

Routes founder questions to the right advisor roles, coordinates multi-role board meetings for complex decisions, synthesizes outputs, and tracks decisions.