From migma
Use when integrating Migma from app code through the REST API, TypeScript SDK, CLI, or MCP server. Helps choose the right surface, wire authentication, create or fetch generated emails, send tests, schedule campaigns, validate emails, and avoid stale internal contracts.
How this skill is triggered — by the user, by Claude, or both
Slash command
/migma:public-apiThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
Use this skill when a user wants to build with Migma from code or automation. Do not treat this file as an endpoint reference. Verify details against the official docs and OpenAPI before writing code.
Use this skill when a user wants to build with Migma from code or automation. Do not treat this file as an endpoint reference. Verify details against the official docs and OpenAPI before writing code.
Official sources:
@migma/mcp.setup.migma.Authorization: Bearer $MIGMA_API_KEY.POST /v1/projects/emails/generate, then poll generation status.result.emails[] as the source of truth for generated emails.emailId for one generated email, especially series slots.conversationId only for whole-generation status or single-email fallback where explicitly supported.When integrating Migma into an app:
emailId, subject, from email, and from name in server-side constants or config.emailId without sending.Leave the user with:
emailId values and matching product eventsnpx claudepluginhub migmaai/migma-skills --plugin migmaProvides behavioral guidelines to reduce common LLM coding mistakes, focusing on simplicity, surgical changes, assumption surfacing, and verifiable success criteria.
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.
Creates, edits, and optimizes skills for Claude Code, including drafting, evaluating with test prompts, iterating on performance, and improving skill descriptions for better triggering accuracy.