Creates new workflows (slash commands) following the Antigravity format with phases, agent coordination, and verification checkpoints. [EXPLICIT]
From jm-adknpx claudepluginhub javimontano/jm-adk-alfaThis skill uses the workspace's default tool permissions.
agents/guardian.mdagents/lead.mdagents/specialist.mdagents/support.mdevals/evals.jsonknowledge/body-of-knowledge.mdknowledge/knowledge-graph.mdprompts/meta.mdprompts/primary.mdprompts/variations/deep.mdprompts/variations/quick.mdreferences/domain-knowledge.mdtemplates/output.docx.mdtemplates/output.html"A workflow is a choreography. Every agent knows its entrance, its solo, and its exit."
Factory for creating new workflows (slash commands) in the kit. Produces workflow .md files that coordinate agents through phases with verification checkpoints. [EXPLICIT]
When to use:
/jm:{command})| Input | Type | Required | Description |
|---|---|---|---|
| Workflow Name | Text | Yes | Kebab-case command name |
| Description | Text | Yes | One-line purpose |
| Agents | List | Yes | Agent names involved |
| Skills | List | Yes | Skills loaded during execution |
| Output | Type | Description |
|---|---|---|
workflows/{name}.md | File | Workflow definition |
full-lifecycle) must declare mode transitions.[!WARNING] IF workflow has no verification phase THEN STOP. Add a quality gate as the final phase.
[!WARNING] IF workflow references non-existent agents or skills THEN STOP. Cross-reference against the agent/skill catalog.
Example invocations:
| Scenario | Handling |
|---|---|
| Empty or minimal input | Request clarification before proceeding |
| Conflicting requirements | Flag conflicts explicitly, propose resolution |
| Out-of-scope request | Redirect to appropriate skill or escalate |
Searches, retrieves, and installs Agent Skills from prompts.chat registry using MCP tools like search_skills and get_skill. Activates for finding skills, browsing catalogs, or extending Claude.