stark AI Developer brings practical workflows for implementation-ready specifications, architecture decisions, structural code analysis, editable diagrams, repository visuals, agent memory, and capability recommendations. Its open-source skills expose their instructions and supporting scripts for review and adaptation.
The package has no shared backend, bundled MCP server, telemetry or analytics. Jev Capability Advisor is an optional Codex workflow: fresh recommendations send your supplied task and public capability descriptions to TypeSafe using your own API key. Offline candidate inspection needs no credential or network. Your host controls discovery, permissions and execution; other tools and services keep their own access requirements.
Install
- 1Add it in ChatGPT
Open Plugins in the ChatGPT sidebar (web or desktop), search for “stark AI Developer” and select +. You'll be asked to sign in to any connected service on first use. Then type @ in a chat to call it.
Skills 7
- Animated README Logo
Creates validated animated README logo pipelines
- Architecture Compass
Governs and reviews ADR-guided architecture changes
- CodeGraph + ast-grep
Set up, update, or diagnose semantic and structural tooling
- Codex Memory Curator
Audits, prunes, and rewrites Codex memory state
- Codex Spec Interviewer
Interviews, verifies, ADR-gates, and saves Codex-ready specs
- Draw.io Diagrams
Verified draw.io diagrams with capability-aware export
- Jev Capability Advisor
Find relevant available skills and tools with Jev
Things to ask
- “Turn this feature idea into an implementation-ready specification.”
- “Review the available code context and recommend an architecture with explicit tradeoffs.”
- “Create an editable draw.io diagram for this system.”
Related
SuperpowersPlan, develop, and debug codeplugin · by Jesse Vincent · 294k stars