Multica 내장 - 재사용 가능한 기술로 코딩 에이전트를 실행 및 관리하기위한 오픈 소스 플랫폼.

로컬 코딩 에이전트를 가르치는 휴대용 기술 - Claude Code, Codex, Cursor, 그리고 다른 사람 — Multica를 운영하는 방법 multica CLI : 읽기 및 삼기 문제, 회신 metadata를 안전하게 관리하고, 언급/status 부작용을 처리하십시오.

한국어 |

그것은하지 않는 것

이 저장소는 **** Grant Multica가 자체에 접근할 수 없습니다. 제출은 사용자의 로컬 CLI 로그인, 선택된 프로필, Active Workspace 및 모든 명령에 대한 명시적 승인은 에이전트가 실행됩니다. 기술이 가르치는 how Multica를 안전하게 구동하십시오; 작업 공간 권한 또는 상점 비밀을 우회하지 마십시오.

어떤 커버

• CLI auth, 프로파일 및 작업 공간 상태 확인 (그리고 로그인 방법)
• 읽기 문제, 의견, 메타데이터, 라벨, 사용자 정의 속성, 가입자, 프로젝트, 에이전트, 스쿼드, 런타임, 리포지, 기술, autopilots 및 첨부 파일
• 제목, 설명 및 댓글 본문에 대한 검색 문제
• 읽는 의견 역사는 싸게 — 실 검사, --compact, 및 해결된 보행 접히는

Multica CLI Skill

Built for Multica — an open-source platform for running and managing coding agents with reusable skills.

A portable skill that teaches any local coding agent — Claude Code, Codex, Cursor, and others — how to operate Multica through the authenticated multica CLI: read and triage issues, reply to comments safely, manage metadata, and handle mention/status side effects.

English | 简体中文

What it does not do

This repository does not grant Multica access by itself. Permissions come only from the user’s local CLI login, selected profile, active workspace, and explicit approval for any commands the agent runs. The skill teaches how to drive Multica safely; it never bypasses workspace permissions or stores secrets.

What it covers

• Checking CLI auth, profile, and workspace state (and how to log in)
• Reading issues, comments, metadata, labels, custom properties, subscribers, projects, agents, squads, runtimes, repos, skills, autopilots, and attachments
• Searching issues across titles, descriptions, and comment bodies
• Reading comment history cheaply — thread scans, --compact, and resolved-thread folding
• Writing safe issue comments with --content-file, including the working-directory restriction on file arguments
• Creating or updating issues and high-signal metadata
• Handling mention, status, assignment, rerun, and sub-issue side effects, and suppressing unwanted agent runs with --no-start
• Inspecting run history and token usage; cancelling a run when asked
• Linking pull requests back to Multica issues
• Saying so plainly when the CLI cannot do something, instead of faking it

Install

The skill lives at skills/multica-cli/. Pick the path for your tool.

Claude Code (plugin marketplace)

/plugin marketplace add multica-ai/multica-cli
/plugin install multica-cli@multica-cli

Codex (skill installer)

install-skill-from-github.py --repo multica-ai/multica-cli --path skills/multica-cli

Restart Codex after installing new skills.

Cursor

Copy the skill into your personal Cursor skills directory:

mkdir -p ~/.cursor/skills/multica-cli
cp -R skills/multica-cli/* ~/.cursor/skills/multica-cli/

Or drop the project rule .cursor/rules/multica-cli.mdc into a project’s .cursor/rules/ directory. See CURSOR.md for details.

Any other agent

Copy skills/multica-cli/SKILL.md into wherever your tool loads skills or instructions from.

Requirements

• The multica CLI is installed locally, at v0.4.26 or newer. Earlier versions lack commands the skill relies on (notably --no-start), and will reject them. Check with multica version.
• The user has run multica login (or multica setup) to authenticate.