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
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.
- Checking CLI auth, profile, and workspace state (and how to log in)
- Reading issues, comments, metadata, projects, agents, squads, runtimes, repos, skills, autopilots, and attachments
- Writing safe issue comments with
--content-file - Creating or updating issues and high-signal metadata
- Handling mention, status, assignment, rerun, and sub-issue side effects
- Linking pull requests back to Multica issues
The skill lives at skills/multica-cli/. Pick the path for your tool.
/plugin marketplace add multica-ai/multica-cli
/plugin install multica-cli@multica-cli
install-skill-from-github.py --repo multica-ai/multica-cli --path skills/multica-cliRestart Codex after installing new skills.
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.
Copy skills/multica-cli/SKILL.md into wherever
your tool loads skills or instructions from.
- The
multicaCLI is installed locally. - The user has run
multica login(ormultica setup) to authenticate. - The intended workspace/profile is selected, or passed explicitly with
--workspace-idand--profile.
Ask your agent to work with Multica once the skill is installed, for example:
Read MUL-123 with the multica CLI and draft a reply for me to review.
For write operations (comments, status changes, mentions, new issues), the agent should ask before making state changes unless you have already clearly authorized that exact action. See EXAMPLES.md for more.