corezoid

Creates and manages Corezoid API Gateway (APIGW) endpoints — generates OpenAPI specs, builds wrapper processes, configures authentication, sets HTTP paths and methods, and deploys via convctl make-api-wrapper. Activate whenever a user asks to expose a process as an HTTP API, create an API Gateway endpoint, set up a REST endpoint for a Corezoid process, configure external access to a process, create a webhook, or asks about APIGW, API paths, or making a process callable from the outside. This skill covers the full workflow from zero to a live HTTP endpoint.

Creates an HTTP API wrapper for an existing Corezoid process — generates an OpenAPI 3.0.0 specification and a wrapper process JSON, then deploys both via the convctl make-api-wrapper command. Activate whenever a user asks to make a process callable via HTTP, create an API wrapper, expose a process as a REST endpoint, generate an OpenAPI spec for a process, or mentions "make-api-wrapper". This is the correct skill for turning any Corezoid process into an externally-callable HTTP API with proper authentication and API Gateway integration.

Designs multi-process Corezoid systems — chooses the right patterns (connector vs logic vs async fan-out), plans process decomposition and composition, reviews architectural decisions, and produces architecture documents with process maps. Activate whenever a user asks to design a system, choose between patterns, plan a multi-process flow, review an architecture, decompose a business problem into Corezoid processes, or asks "how should I structure this in Corezoid?" or "what processes do I need for X?". Also activate when the user describes a business capability (payments, onboarding, notifications, etc.) and wants to implement it in Corezoid — even if they don't use the word "architecture".

Creates and manages Corezoid dashboards — adds charts (column, pie, funnel, table), binds metrics to process nodes, configures real-time mode, and sets up drill-down linking between dashboards. Activate whenever a user asks to create a dashboard, add a chart, visualize process metrics, set up reporting for a Corezoid process, configure real-time monitoring, or asks what dashboards or charts exist. Also activate when the user wants to show task counts, completion rates, error rates, or any other process statistics visually in Corezoid.

Builds Corezoid process JSON from scratch or from a template — both connectors (wrapping an external API) and logic processes (orchestrating other processes via RPC calls). Activate whenever a user asks to create a connector, build a process, make a process that calls an API, implement business logic in Corezoid, or provides credentials alongside a process description. This skill knows all mandatory node fields and the exact JSON structure needed — use it before generating any process JSON to avoid structural errors that block deployment.

Systematically reviews a Corezoid process JSON and produces a structured Markdown checklist of issues — covering hardcoded values, repeated logic, cycle detection, node naming, JavaScript/Erlang code quality, and error handling completeness. Activate whenever a user asks to review, check, audit, or validate a Corezoid process or connector, or pastes a process JSON and asks if it looks correct. Also activate before any deployment to catch issues early. Output is a ready-to-act checklist the user can work through directly.

Documents a Corezoid process — produces a human-readable Markdown file AND enriches the process JSON with descriptions on every node and parameter. Output is designed for team wikis, internal portals, and potential future product integration. Activate whenever a user asks to document a process, write docs for a connector, add descriptions to a process, create documentation for a logic, describe what a process does, or any similar phrasing. Also activate when the user shares a process JSON and asks to explain it or make it self-documenting. Always produce BOTH outputs (Markdown file + enriched JSON) — never just one.

Modifies existing Corezoid processes and fixes broken connectors — covers exporting, editing process JSON, managing environment variables, and diagnosing failed tasks. Activate whenever a user asks to update a process, fix a connector, add a node, change how a process works, debug a failed task, or provides ResultNodeObjID and ResultTaskData showing where execution stopped. Also activate when the user says "add a call to process X", "the task failed with error Y", or "modify the logic". This skill knows the correct export→edit→variable→test workflow and error taxonomy.