Builder.io

Review a configured queue of pull requests, checking code changes, linked issues, tests, and review discussions. Report actionable findings and supporting evidence, then assess approval or merge separately against the permissions and conditions configured for each action.

中文简介正在准备中。当前显示英语简介。

• Triage a filtered pull request queue manually or on a schedule
• Report actionable findings with locations and concrete fixes
• Assess approval and merge against separate policies

Look across feedback, operational data, errors, and delivery failures over a defined period to find recurring problems. Trace patterns to shared causes, examine earlier fixes, and recommend systemic changes, implementing and verifying them only when configured policies allow.

中文简介正在准备中。当前显示英语简介。

• Review recurring problems across feedback and operational records
• Investigate symptoms that returned after an earlier fix
• Find shared causes across related features and callers

Open a running local app in Design to compare routes and screen sizes, collaborate on visual changes, and hand those changes to a coding agent for application to the source.

中文简介正在准备中。当前显示英语简介。

• Compare desktop and mobile versions of the same app screen
• Review a sequence of onboarding or checkout screens
• Collaborate on visual changes through shared previews

Collect unresolved work that needs human judgment from configured pull requests, issues, feedback, errors, and delivery signals. Group related problems into a decision queue with source links, supporting evidence, and visible gaps in coverage.

中文简介正在准备中。当前显示英语简介。

• Reviewing work that still needs a human decision
• Grouping recurring errors and user concerns
• Checking pull requests awaiting review or approval

Guide public skill additions and updates through file placement, catalog documentation, installation discovery, integration settings, and validation. Distinguish ordinary skills from instruction-based, app-backed, and generated skills so each receives the appropriate checks.

中文简介正在准备中。当前显示英语简介。

• Adding a public skill and its catalog page
• Checking whether a skill can be discovered for installation
• Adding optional managed AGENTS.md or CLAUDE.md instructions

Monitor another AI agent’s work and independently investigate the same task. Compare the original request with actual changes and test evidence, report gaps and concrete follow-up steps, and make limited fixes when authorized.

中文简介正在准备中。当前显示英语简介。

• Monitor an agent session until completion or a blocker
• Audit a pull request against the original request
• Compare findings from multiple agents

Organize large coding tasks with Claude Fable directing lower-cost subagents. Delegate bounded research, edits, and tests, then have Fable verify evidence, resolve conflicting findings, integrate changes, and review the final result.

中文简介正在准备中。当前显示英语简介。

• Split a large codebase investigation across subagents
• Delegate independent, narrowly scoped code edits
• Distribute targeted tests and log summaries

Configure a software delivery workflow that turns selected feedback and maintenance signals into verified, reviewed changes. Define information sources, schedules, working directories, and separate permissions for actions such as implementation, merging, deployment, and notifications.

中文简介正在准备中。当前显示英语简介。

• Choose connected sources for feedback and maintenance signals
• Set separate permissions for implementation, merging, and deployment
• Configure supported schedules, worktrees, and notifications

An experimental workflow for finding and resuming coding runs interrupted by a host restart or automation failure. It checks original instructions, worktree ownership, and external state, then reports which runs were resumed, skipped, or held.

中文简介正在准备中。当前显示英语简介。

• Resuming coding work after an agent host restart
• Finding unfinished work after automation stops
• Checking external state before retrying an uncertain action

Open Agent-Native apps beside the conversation through Dispatch MCP, a connection for app tools. Create or edit content using the current screen and selection, then read saved results back to confirm the changes.

中文简介正在准备中。当前显示英语简介。

• Opening Slides beside the conversation
• Creating a presentation through natural-language requests
• Making focused edits to selected elements

Organize work so an expensive AI model handles planning, judgment, and final review while cheaper helper agents perform bounded research, coding, and testing. Define ownership and verification requirements, then inspect the evidence and integrate their results centrally.

中文简介正在准备中。当前显示英语简介。

• Delegate broad codebase research to cheaper agents
• Split coding tasks with clear file ownership
• Distribute test runs and log analysis

Monitor one explicitly authorized pull or merge request, inspect current reviews and checks, and fix actionable findings within scope. Apply separate permission and verification conditions before publishing fixes, replying, approving, or merging.

中文简介正在准备中。当前显示英语简介。

• Following one authorized pull request through review
• Fixing actionable review findings within an agreed scope
• Rechecking reviews and checks after a branch update

Collect product feedback, usage data, runtime errors, and issue reports from configured sources. Classify and group findings with supporting evidence, then apply separate project rules for implementing fixes, requesting clarification, or closing reports.

中文简介正在准备中。当前显示英语简介。

• Triage feedback from multiple sources
• Group related error reports
• Check collection coverage and unavailable sources

An experimental workflow for delivering software changes through configured checks, pull requests, review updates, and merge verification. It follows project permissions and release conditions, and reports missing evidence or checks before treating delivery as complete.

中文简介正在准备中。当前显示英语简介。

• Publishing verified changes through a pull request
• Updating code after review feedback
• Checking merge conditions before release

Monitor explicitly authorized software delivery tasks, verify which work has stopped, and send reminders only when a concrete next step is due and the configured notification policy allows it.

中文简介正在准备中。当前显示英语简介。

• Find stalled delivery tasks during scheduled checks
• Verify the current state of a task's pull request or worktree
• Send permitted reminders without repeating unchanged notices

Compare competing plans from AI agents against the actual task and available evidence. Choose one, combine useful parts, or request revisions, then produce a single execution handoff with ordered steps, verification checks, and reasons for rejected alternatives.

中文简介正在准备中。当前显示英语简介。

• Compare plans from Codex and Claude Code
• Combine complementary implementation proposals
• Check migration and validation gaps before implementation

Keep implementation work moving by turning routine uncertainty into explicit assumptions. The agent follows existing project patterns, makes small reversible changes, validates results, and reports its decisions, completed changes, checks, and remaining risks.

中文简介正在准备中。当前显示英语简介。

• Continue implementation while away
• Reduce routine clarification stops
• Review autonomous decisions and validation results

Add a short status line to the end of agent responses so readers can see whether work is finished, a specific follow-up remains, or progress depends on their input.

中文简介正在准备中。当前显示英语简介。

• Check whether an agent has finished the requested work
• Identify specific follow-up tasks at the end of a response
• Standardize status reporting through project instructions

Guide implementation, upgrades, and debugging by checking official documentation and local specifications first. Identify the relevant version, confirm supported behavior, and use those findings to produce an implementation or answer with appropriate validation.

中文简介正在准备中。当前显示英语简介。

• Integrate an external API using official documentation
• Check breaking changes before upgrading a library
• Investigate errors caused by API changes

Recover recent work context from local Clips Rewind recordings. Search by words, app, or time range, then inspect relevant text and screen frames to clarify what the user recently saw or said.

中文简介正在准备中。当前显示英语简介。

• Recall something you recently said
• Find a screen you viewed moments ago
• Recover context from recent work

Manage long-running or parallel agent work around five-hour and weekly usage limits. Check consumption between batches, pause new work at 95 percent, preserve a clear handoff, and check actual usage again before resuming.

中文简介正在准备中。当前显示英语简介。

• Manage usage during long-running agent tasks
• Check remaining capacity between parallel work batches
• Resume paused work after checking usage limits

Turns a repeatable workflow from a conversation, skill, spreadsheet, or Claude/ChatGPT project into an Agent-Native app. It creates populated screens with controls that hand tasks to an in-app agent and return results to the relevant objects.

中文简介正在准备中。当前显示英语简介。

• Turning a repeatable chat workflow into an app
• Giving an existing skill a visual interface
• Building a workbench from a spreadsheet

Turn a text development plan into a visual document with diagrams, file maps, annotated code, and open questions. For interface work, add wireframes or an interactive prototype so reviewers can examine screens and behavior before implementation.

中文简介正在准备中。当前显示英语简介。

• Turn an existing text plan into a visual review document
• Compare interface states and user flows before coding
• Explain architecture and data flow with inline diagrams

Turn a pull request, branch, commit, or git diff into an interactive review overview. Show interface changes, affected files, API behavior, data structures, and annotated code differences so reviewers can understand the overall change before inspecting individual lines.

中文简介正在准备中。当前显示英语简介。

• Review a large pull request
• Compare interface states before and after changes
• Understand API and data structure changes