---
title: "stark-ai-developer"
description: "stark AI Developer brings practical workflows for implementation-ready specifications, architecture decisions, structural code analysis, editable diagrams, repository visuals, agent memory, and capability recommendations"
canonical: https://agentpluginsdirectory.com/plugins/stark-ai-developer
last-updated: 2026-09-28
---

# stark-ai-developer
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.
- Slug: stark-ai-developer
- Publisher: servrox solutions UG
- Repository: https://github.com/stark-ai-de/agent-skills
- Manifest: plugins/stark-ai-developer/plugin.json
- Version: 1.7.1
- License: Apache-2.0
- Category (editorial): other
- Skills: 7 (animated-readme-logo, architecture-compass, codegraph-ast-grep, codex-memory-curator, codex-spec-interviewer, drawio-diagrams, jev-capability-advisor)
- MCP servers: 0
- Stars: 5
- Repository created: 2026-05-19
- Repository last pushed: 2026-09-28
- Publisher type: Organization
- Listing: https://agentpluginsdirectory.com/plugins/stark-ai-developer
- Schema: https://agent-plugins.org/schemas/1.0.0/plugin.schema.json

## What stark-ai-developer does, in the publisher's words

portable Agent Plugin generated from the explicit plugins/stark-ai-developer.source.json allowlist.

This harness-first package contains 7 developer workflows and has no shared backend, bundled MCP server, telemetry or analytics. Jev Capability Advisor optionally sends supplied task text and public capability cards to TypeSafe using your own API key; offline candidate inspection needs no network or credentials. Canonical skill content remains maintained under skills/ / /; this portable copy is generated and must not be edited as a source.

Use plugins/stark-ai-developer/ only with a client that supports the portable Agent Plugins contract. Standalone skill installation remains available from the repository through npx skills@latest.

From the project README, punctuation lightly normalized. Full text: https://raw.githubusercontent.com/stark-ai-de/agent-skills/HEAD/plugins/stark-ai-developer/README.md

## Skills

- animated-readme-logo: Create, transform, animate, or audit GitHub README logos and their verified SVG/PNG/GIF delivery. Use when a repository needs branding assets, not ordinary README prose or app/site motion.
- architecture-compass: Set up ADR governance, audit architecture and drift, or plan and execute bounded ADR-guided refactors. Use when work needs binding architecture decisions, provider-to-local mapping, architecture PR review, and durable runtime or source-boundary changes.
- codegraph-ast-grep: Set up, update, or diagnose CodeGraph and ast-grep so coding agents can use semantic repository scope and structural syntax evidence automatically. Use when a repository needs an idempotent CodeGraph/ast-grep installation, stable tool and index migrations, MCP reconnection, persisted agent guidance…
- codex-memory-curator: Audit and safely curate Codex memory, including stale claims, cross-repo leakage, sensitive entries, and memory configuration. Use when reviewing or cleaning Codex memory, not generic repository docs.
- codex-spec-interviewer: Turn ambiguous coding requests into verified Codex implementation specs. Use when the user wants requirements, an implementation plan, or a spec before coding; include source checks, needed ADRs, and agreed delivery. Do not use for already specified direct implementation or memory cleanup.
- drawio-diagrams: Create, edit, review, or export editable draw.io diagrams. Use when the user needs.drawio architecture, flow, sequence, network, or other technical diagrams; not data plots or artistic images.
- jev-capability-advisor: Recommend available skills or MCP tools using TypeSafe Jev, or explicitly choose one next skill. Use when the user requests capability advice, candidate inspection, selection evaluation, or reusable host integration. Native client selection remains the default and fallback.

Descriptions come from the frontmatter of each SKILL.md, punctuation lightly normalized.