'Recover from broken agent state including crash recovery, context overflow, merge conflicts, and corrupted worktrees.'

Manage Claude Code sessions with naming, checkpointing, and resume strategies.

>-

Autonomous goal execution — give a goal, get a plan, confirm, execute, report. You steer, Claude drives.

This agent runs in a short‑lived environment. Any uncommitted or unpushed work will be permanently

Use Orchestration Mode. Parse plan files and delegate tasks to parallel subagents.

Faithful implementation of the Outline Agent from PaperOrchestra

Faithful implementation of the Section Writing Agent from PaperOrchestra

Niche agent for callback receiver safety: access control on implemented callback handlers, permissionless state inflation via callbacks, and selective revert exploitation

Trigger 15 events detected in recon event_definitions.md (optional skill) - Used By breadth agents (assigned to core state or dedicated agent)

Trigger Pattern SHARE_ALLOCATION flag detected in pattern scan - Inject Into Breadth agents, depth-edge-case

Final pre-commit sweep: did we learn anything in this session that the next person (or agent) working in this repo will regret not having written down?

Deep research before planning. Launches parallel agents to search docs, web, and codebase, then synthesizes findings into actionable context.

../../../src/sdk/claude-plugin/skills/appmesh-remote/SKILL.md

Find and answer unanswered GitHub discussions. Activate when user wants to contribute to open source discussions, help answer GitHub questions, or find discussions to answer. Delegates all work to subagents.

--- name: create-book

whisper-transcribe

Read agent interaction logs across packs and detect operational patterns. Emits state-transition FeedbackEvents for degradation/recovery.

На втором этапе **необходимо** **добиться систематичности в**

Данная практика не особо сложная, поэтому попробуйте составить

На втором этапе в части теории необходимо уделить внимание проработке

На втором этапе необходимо осознанно практиковаться в мышлении

На втором этапе необходимо уделить внимание проработке принципов и работ

На втором этапе необходимо научиться осознанно управлять общим планом

指导用户如何自定义 Trae Skills 的配置，包括覆盖角色设定、调整技术偏好和定义全局规则。

Implement the Agent-to-Agent (A2A) protocol for standardized inter-agent communication, enabling agents to discover, delegate, and collaborate with other agents.

Полное удаление аккаунта и всех связанных данных из конфигурации.

Install and set up the Acorn theorem prover CLI. Use when the environment doesn't have Acorn installed or when the user needs to set up Acorn for the first time.

Active Interleave Skill

Add new documentation sources to .claude/doc-sources.toml for Context7 access

>

Claim and work on beads safely with proper coordination. Use when starting work, finishing work, or finding the next task. Covers the full bead lifecycle: discover → verify → claim → work → close.

Agency is a command-line AI agent orchestrator that runs coding agents in isolated Git worktrees with tmux-managed sessions.

Interactive element picker that opens a browser window with a DevTools-like selection overlay. Users hover to highlight elements and click to select. Returns detailed element info including selector,

Use the agent-exec CLI to run Codex/Claude/Cursor and manage skills for this repo.

Enable communication between AI coding agents using AI Maestro's dual-channel messaging system. Agents are identified by their agent ID or alias from the agent registry. Supports both SENDING and RECE

Bidirectional sync between agent-ops issues and GitHub Issues

Install AgentOps into a new or existing project. Handles .agent/ setup and .github/ merging.

agent-orchestration

Agent Provisioner Skill

Programmatic agent definitions for the Claude Agent SDK in TypeScript and Python. Use when creating agents for SDK-based applications rather than filesystem-based Claude Code.

Quantum-resistant, self-learning version control for AI agents with ReasoningBank intelligence and multi-agent coordination

agentic-vision

Inter-agent communication for tmux sessions. Send and receive messages between AI agents.

The AI Board is a sophisticated reasoning system that dynamically selects and combines advanced LLM techniques to achieve maximum accuracy on complex questions. It uses multi-agent debate, adversarial

AI Collaboration Standards

> **语言**: [English](../../../../../skills/claude-code/ai-collaboration-standards/SKILL.md) | 简体中文

Manage AI agents through the AI Maestro CLI. This skill provides commands for creating, updating, deleting, hibernating, and waking agents. It also handles plugin management and agent import/export.

ai-task-runner

Collaborative planning with all mounted CLIs (Claude, Codex, Gemini, OpenCode) for comprehensive solution design.