“subagents”的搜索结果

Coordinates a named team of Codex workers with concrete responsibilities and shared progress records. It selects available collaboration tools, manages communication and separate working copies when needed, and handles integration, team archival, and cleanup after the work ends.

中文简介正在准备中。当前显示英语简介。

• Splitting related implementation work across cooperating agents
• Investigating several aspects of a clearly defined problem
• Inspecting team progress and member responsibilities

Coordinate a task from a verifiable goal through completion. Handle work directly or split independent tasks across separate agent sessions, track progress, verify results, and arrange pull request merging when included in the goal.

中文简介正在准备中。当前显示英语简介。

• Split independent tasks across agents
• Check progress across ongoing tasks
• Resume a previously started project

Set up and customize Pi, a terminal coding agent framework. This skill guides model configuration, extension development, terminal interfaces, and integration with other applications through its SDK, a software development kit, or process messaging.

中文简介正在准备中。当前显示英语简介。

• Install Pi and configure model access
• Create custom tools and terminal interfaces
• Embed Pi in another application

Analyze a project’s code and existing settings to recommend useful Claude Code automations. Receive tailored suggestions for event-triggered actions, specialist agents, skills, plugins, and external tool connections, with reasons and setup locations.

中文简介正在准备中。当前显示英语简介。

• Choosing Claude Code features for a new project
• Finding ways to automate formatting and checks
• Selecting external tool connections for the project

Create a dedicated AI subagent for recurring work, with a defined role, working process, output format, and constraints. Package its files in a plugin and optionally draft a companion skill that routes suitable tasks to it.

中文简介正在准备中。当前显示英语简介。

• Creating a dedicated code review agent
• Turning repeated instructions into an agent persona
• Adding related agents to an existing plugin

Build Claude Code plugin hooks: automated checks triggered by tool use or session events. Get guidance on prompt and command hooks for validating actions, checking task completion, loading context, and testing configurations.

中文简介正在准备中。当前显示英语简介。

• Checking dangerous commands before execution
• Verifying completion before the agent stops
• Loading project context when a session starts

Analyze a project's code and configuration to recommend useful Claude Code automations. Get tailored suggestions for event-triggered actions, specialist agents, reusable skills, plugins, and external tool connections, with reasons for each recommendation.

中文简介正在准备中。当前显示英语简介。

• Set up Claude Code for a new project
• Find useful formatting and testing automations
• Choose external tool connections for a project's stack

Manage shell commands and AI agent tasks through a shared gbrain job queue. Track progress, steer agents, pause or resume work, and coordinate parallel tasks, with guidance for long operations, completion reporting, and reusable stage checkpoints.

中文简介正在准备中。当前显示英语简介。

• Run scripts as monitored background jobs
• Coordinate parallel research by AI agents
• Redirect, pause, or resume an agent task

Build, edit, or debug backend AI agents with eve, a framework that represents agents as directories of files. Work on instructions, tools, connections, schedules, and related components using documentation bundled with the installed version.

中文简介正在准备中。当前显示英语简介。

• Create a backend AI agent with eve
• Update agent instructions, tools, and connections
• Debug schedules and subagent configurations

Write clear briefs for subagents and conversation forks, agents that inherit conversation history. Specify purpose, known findings, scope, and expected output while respecting each agent's existing role and separating research requests from implementation.

中文简介正在准备中。当前显示英语简介。

• Writing a focused research brief for a subagent
• Specifying files and constraints for implementation
• Defining scope for an agent inheriting conversation history

Guide new Kortix users from a vague idea to a concrete task and a finished deliverable. Introduce relevant connections, memory, parallel agents, or scheduled follow-ups as useful next steps after completing the first result.

中文简介正在准备中。当前显示英语简介。

• Help new users choose their first Kortix task
• Turn a vague request into a concrete deliverable
• Guide users through completing their first result

Guide a Trae agent through recurring failures with diagnosis, alternative approaches, and relevant checks. The skill defines when to intervene, requires evidence for completion, and separates the agent’s self-review from external validation.

中文简介正在准备中。当前显示英语简介。

• Change approaches after repeated failures
• Check evidence behind a completion claim
• Review risks and validation gaps before delivery

Use cmux on macOS to organize visible teams of AI agents, send prompts, inspect terminal output, and monitor completion. Set up role-based teams or have several agents investigate the same problem; live operation remains unproven in the supplied material.

中文简介正在准备中。当前显示英语简介。

• Launch a team to investigate an intermittent test failure
• Have multiple agents investigate the same bug
• Send follow-up prompts to a running agent

Review medium to large code changes using checks selected for the actual patch. Analyze the change and surrounding code, assign focused reviews by function, file, or feature, and combine findings with locations, confidence levels, and supporting evidence.

中文简介正在准备中。当前显示英语简介。

• Reviewing patches of roughly 50 to 1,000 lines
• Checking risks specific to a changed feature
• Reviewing changes alongside callers and related implementations

Analyze bug-fix commits in a Git repository to uncover recurring failure patterns. Produce individual bug analyses and a reusable pattern guide that removes project-specific details, helping inform future code reviews.

中文简介正在准备中。当前显示英语简介。

• Extract recurring bug patterns from past fixes
• Build a reusable guide for code reviews
• Analyze fixes within a chosen date range or path

Review how an AI agent loads, retains, summarizes, and shares working information. This historical guide helps examine forgotten constraints, repeated actions, tool selection, and handoffs using context engineering practices published in 2024–2025.

中文简介正在准备中。当前显示英语简介。

• Reviewing information loaded at startup versus on demand
• Investigating repeated actions or forgotten constraints
• Planning summaries and persistent task notes

Helps decide whether to handle a task directly, create a subagent, or route it to an agent already familiar with the work. The choice depends on required background knowledge and whether plausible but incorrect results can be checked.

中文简介正在准备中。当前显示英语简介。

• Choosing who should handle a task
• Delegating self-contained research with verifiable sources
• Routing context-heavy reviews to an informed agent

Organize open GitHub issues and pull requests using the gh CLI, GitHub's command-line tool. Identifies resolved issues and pending fixes, estimates priorities and change sizes locally, and proposes closures, links, reviews, or merges for approval.

中文简介正在准备中。当前显示英语简介。

• Clean up resolved issues left open
• Link issues to pull requests with pending fixes
• Estimate priorities and change sizes for outstanding work

Review source code without running it to identify potential security vulnerabilities. Findings include severity, confidence, attack scenarios, and suggested fixes, delivered as JSON for further triage and Markdown for human review.

中文简介正在准备中。当前显示英语简介。

• Review source code for potential vulnerabilities
• Focus a scan using a threat model
• Prepare findings for further triage

Turn broad life sciences questions into focused research plans. Resolve names and identifiers for genes, diseases, or compounds, select relevant research skills, and combine evidence into a concise answer that explains uncertainty and useful follow-up analyses.

中文简介正在准备中。当前显示英语简介。

• Reviewing evidence linking a gene to a disease
• Combining evidence about a variant and its associated traits
• Researching protein structure, function, and drug interactions

Turn a recurring workflow into a new agent skill through guided discussion. Define use cases, activation conditions, file structure, and instructions, then create and validate SKILL.md and supporting files, including workflows using external tools through MCP.

中文简介正在准备中。当前显示英语简介。

• Turning recurring work into a reusable skill
• Standardizing report or document creation steps
• Designing workflows that use external services through MCP

Organize substantial tasks into a cycle of creation, independent review, and revision while preserving the original request. Turn broad quality goals into observable checks, collect evidence, and finish with verified results or a clearly identified blocker.

中文简介正在准备中。当前显示英语简介。

• Turning vague quality goals into observable completion checks
• Coordinating independent workstreams and reviewers
• Comparing anonymous candidates against a shared benchmark

Audit custom subagents, the specialized assistants used by Claude Code and Codex. Check whether definitions load, identify overlapping roles, review model choices and tool access, and receive scores with prioritized fixes and optional confirmed edits.

中文简介正在准备中。当前显示英语简介。

• Checking agents when joining a project
• Reviewing newly added or imported agents
• Investigating delegation to the wrong agent

Build Claude Code plugin hooks: automated checks triggered by tool use or session events. Get guidance on prompt and command hooks for validating actions, checking task completion, loading context, and testing configurations.

中文简介正在准备中。当前显示英语简介。

• Checking dangerous commands before execution
• Verifying completion before the agent stops
• Loading project context when a session starts