multica-ai

为代码编写、审查和重构提供指引，通过明确前提、采用最小实现、限定修改范围及测试验证，减少AI常见的实现错误，检查改动是否满足请求。

• 实现前梳理前提和歧义
• 限定缺陷修复的修改范围
• 审查过度复杂的代码

Find where Multica’s issue management guidance has moved and how to replace retired metadata guidance. This redirect points older task briefs to the current skill and explains where different kinds of issue information belong.

中文简介正在准备中。当前显示英语简介。

• Find current guidance from an older task brief
• Check alternatives to retired issue metadata
• Locate rules for linking pull requests to issues

Guide a new Multica member from an initial conversation to a confirmed task running as an issue. Mika shapes a concrete goal, previews the plan, starts approved work, and explains where to follow progress and results.

中文简介正在准备中。当前显示英语简介。

• Start a first delegated task in Multica
• Turn current goals into a project board
• Delegate a small research task

Review web interface code against the latest Web Interface Guidelines to identify issues in design, usability, and accessibility. Specify files or a file pattern, and receive concise findings with file names and line numbers.

中文简介正在准备中。当前显示英语简介。

• Review the code behind a web interface
• Check accessibility against the guidelines
• Request a design or usability review

Use Multica’s platform rules to manage issues, agents, projects, and automated runs. The skill directs agents to relevant references and explains checks needed before changes that update workspace records or start work.

中文简介正在准备中。当前显示英语简介。

• Check issue and pull request handling rules
• Configure agents and squad routing
• Investigate scheduled runs that did not start

Guide production incident handling by establishing impact, start time, and recent changes before proposing action. Document evidence for rollback requests, keep the issue updated, and distinguish service recovery from resolution that explains the incident.

中文简介正在准备中。当前显示英语简介。

• Establish the impact and start time of a production incident
• Check whether deployments align with the incident timeline
• Prepare a rollback request with supporting evidence

Use when a local coding agent (Codex, Claude Code, Cursor, or similar) needs to operate Multica through the authenticated `multica` CLI: reading or updating issues, comments, metadata, labels, custom properties, subscribers, projects, agents, squads, runtimes, repos, skills, autopilots, attachments, or workspace state; searching issues; inspecting or cancelling agent runs; replying to a Multica issue from an external agent; creating or triaging issues; checking linked pull requests; or safely handling Multica mention/status side effects without relying on the Multica hosted agent runtime.

中文简介正在准备中。当前显示原文说明。