Skip to main content
Agent skill

Multica Cli

Manage Multica resources (issues, agents, autopilots, skills, workspaces) and the local agent runtime daemon via the multica CLI. Use when the user runs multica, mentions Multica issues/agents/autopilots/skills/runtimes/workspaces, or needs to script Multica workflows.

Get started

Get the complete skill folder, including its scripts and reference files.

When to use this skill

Use Multica Cli when an AI agent needs a reusable SKILL.md workflow for this job: Manage Multica resources (issues, agents, autopilots, skills, workspaces) and the local agent runtime daemon via the multica CLI. Use when the user runs multica, mentions Multica issues/agents/autopilots/skills/runtimes/workspaces, or needs to script Multica workflows.

When not to use it

Skip Multica Cli when the task is outside the productivity category, or when a more specific skill in this directory already covers the same workflow with clearer triggers.

How to install

Where will you use it?

Install scope
Claude Code folder setup
mkdir -p ~/.claude/skills/multica-cli
# Save SKILL.md to ~/.claude/skills/multica-cli/SKILL.md
  1. Claude Code personal install: place the skill and its bundled files at ~/.claude/skills/multica-cli/SKILL.md. For a shared project, commit the folder at .claude/skills/multica-cli/ instead.
  2. Current Claude Code detects SKILL.md changes in watched directories during the session. If you just created a top-level skills directory, run /reload-skills. Check that the skill is listed before testing its trigger.
  3. For Claude chat or Cowork in the Desktop app, manage uploaded skills in Customize > Skills; copying files into a local Claude Code folder is not a Desktop install. Other agents may use different install locations.

Full install guide for Claude, Cursor, and Codex →

Try a starter prompt

After installing the skill, paste this starter prompt into your agent to verify it triggers on a small task.

Starter prompt
Use the Multica Cli skill for this task: Use Multica Cli when this documented workflow matches the task. Confirm any required inputs or files before making changes.

What supports this recommendation?

68/100 provisional content score. This measures documentation, practical detail and source signals. It is not a measured task success rate or a security certification.

Documentation
77/100
Practical detail
68/100
Source evidence
52/100
Source signals
70/100
Model compatibility evidence
  • claudeinferred

    The skill text mentions Claude or a closely associated term. This is keyword-derived compatibility; no hands-on model test is recorded.

  • chatgptuntested

    No model-specific signal or recorded compatibility test was found.

  • geminiuntested

    No model-specific signal or recorded compatibility test was found.

  • copilotuntested

    No model-specific signal or recorded compatibility test was found.

  • llamauntested

    No model-specific signal or recorded compatibility test was found.

  • perplexityuntested

    No model-specific signal or recorded compatibility test was found.

  • mistraluntested

    No model-specific signal or recorded compatibility test was found.

  • grokuntested

    No model-specific signal or recorded compatibility test was found.

Inferred compatibility is based on content signals. Check the app, its available tools and setup requirements before running a skill.

What this skill does

# Multica CLI

Command-line interface for [Multica](https://multica.ai). Manage issues, assign agents, control the local daemon, and script everything that the web UI can do.

## Quick start

```bash multica login # first-time auth (opens browser, saves PAT to ~/.multica/config.json) multica auth status # verify login + active workspace multica daemon status # daemon must be online for local-runtime agents ```

For scripting and parsing, always pass `--output json` — the default for `list` commands is `table` (human-readable).

## Common workflows

### Issues

```bash multica issue list --status open --output json multica issue get ABC-123 # accepts issue key or UUID multica issue create --title "..." --description "..." # decodes \n, \r, \t, \\ multica issue assign ABC-123 --to "agent-slug" # triggers a task immediately multica issue status ABC-123 --set done multica issue comment add ABC-123 --body "..." multica issue runs ABC-123 # execution history multica issue run-messages <task-id> --issue ABC-123 # follow an agent run's messages multica issue rerun ABC-123 # re-queue with current assignee ```

For multi-line descriptions or content with literal backslashes, prefer `--description-stdin`:

```bash printf 'line 1\nline 2\n' | multica issue create --title "..." --description-stdin ```

### Agents and skills

```bash multica agent list --output json multica agent create --name "..." --runtime-id <id> --model claude-sonnet-4-6 multica agent skills attach <slug> --skill <skill-slug> multica skill import --url https://github.com/org/repo # also: clawhub.ai, skills.sh ```

Prefer `--model <id>` over passing `--model` inside `--custom-args` — some runtimes (codex app-server, openclaw) reject it there.

For secrets in `--custom-env`, use `--custom-env-stdin` or `--custom-env-file` (suggest mode `0600`). Inline values leak to shell history and `ps`.

### Autopilots (scheduled / triggered automations)

```bash multica autopilot create --title "Daily triage" --agent <slug> --mode create_issue --description "..." multica autopilot trigger-add <id> ... # attach a schedule multica autopilot trigger <id> # run once now multica autopilot runs <id> ```

Only `--mode create_issue` is fully supported end-to-end today; `run_only` is not.

### Daemon (local runtime)

```bash multica daemon start # background; add --foreground to attach multica daemon status multica daemon logs multica daemon stop ```

If an assigned issue isn't being picked up, `multica daemon status` first — local-runtime agents won't run with the daemon offline.

## Global flags and env vars

| Flag | Env var | Purpose | |------|---------|---------| | `--workspace-id <id>` | `MULTICA_WORKSPACE_ID` | Override active workspace | | `--server-url <url>` | `MULTICA_SERVER_URL` | Point at a non-default server (self-hosted) | | `--profile <name>` | — | Isolated config/daemon/workspace set (e.g. `dev`) | | `--output json` | — | Machine-readable output for `get`/`create`/`list` |

## Discover more

Every command supports `--help`:

```bash multica issue create --help multica agent update --help ```

See [REFERENCE.md](REFERENCE.md) for the full command tree, less-common subcommands (workspace admin, repo, attachment, config, runtime activity), and authentication notes.

Intended uses

  • Use Multica Cli when this documented workflow matches the task.

Implementation notes

  • Review the source instructions and adapt inputs before running the workflow.

Try it, then tell us how it went

A copied prompt does not tell us whether the task worked. Report your result after checking the output. We collect your tool and outcome, never your files or prompt.