職人 Shokunin 62 AI agent skills for OpenCode, Claude Code, Cursor, Windsurf. ChromaDB memory, MCP servers, declarative self-updates. Multi-model, open source, zero cost.
Config is the same across clients — only the file and path differ.
{
"mcpServers": {
"shokunin": {
"args": [
"-y",
"opencode"
],
"command": "npx"
}
}
}Are you the author?
Add this badge to your README to show your security score and help users find safe servers.
62 engineering skills + persistent AI memory. One command. Zero servers.
This server supports HTTP transport. Be the first to test it — help the community know if it works.
Five weighted categories — click any category to see the underlying evidence.
ChromaDB Python project has a pre-authentication code injection vulnerability
A pre-authentication, code injection vulnerability in version 1.0.0 or later of the ChromaDB Python project allows an unauthenticated attacker to run arbitrary code on the server by sending a malicious model repository and trust_remote_code set to true in the /api/v2/tenants/{tenant}/databases/{db}/collections endpoint.
>= 1.0.0source →Click any tool to inspect its schema.
Be the first to review
Have you used this server?
Share your experience — it helps other developers decide.
Sign in to write a review.
Others in ai-ml / data
Dynamic problem-solving through sequential thought chains
Zero-dependency, token-efficient database MCP server for Postgres, MySQL, SQL Server, MariaDB, SQLite.
Workspace template + MCP server for Claude Code, Codex CLI, Cursor & Windsurf. Multi-agent knowledge engine (ag-refresh / ag-ask) that turns any codebase into a queryable AI assistant.
Persistent memory using a knowledge graph
MCP Security Weekly
Get CVE alerts and security updates for Shokunin and similar servers.
Start a conversation
Ask a question, share a tip, or report an issue.
Sign in to join the discussion.
62 engineering skills + persistent AI memory. One command. Zero servers.
v4.2.3 adds freshness decay (time-weighted memory), claim verification (verify_file_path MCP tool), 9 MCP tools (was 8), and 30+ bug fixes.
職人 (shokunin) means artisan in Japanese. These skills aim for that standard: every detail crafted, every edge case handled, every workflow automated.
# One-command install (Windows)
irm https://raw.githubusercontent.com/EliasOulkadi/shokunin/master/install.ps1 | iex
# One-command install (Linux)
bash <(curl -sL https://raw.githubusercontent.com/EliasOulkadi/shokunin/master/install.sh)
# Skills-only install (Windows — no ChromaDB, no MCP)
irm https://raw.githubusercontent.com/EliasOulkadi/shokunin/master/install-skills.ps1 | iex
# Skills-only install (Linux)
bash <(curl -sL https://raw.githubusercontent.com/EliasOulkadi/shokunin/master/install-skills.sh)
OpenCode + VS Code + WezTerm
62 skills + superpowers plugin + 4 subagents
MCP servers: filesystem, fetch, memory + ChromaDB
AI: OpenCode Go (default) + Ollama (local fallback)
Update system: declarative manifest with drift detection
Windows (PowerShell) + Linux (bash)
62 skills across 10 domains. Each skill teaches the agent how to handle a specific domain: with decision tables, error patterns, production checklists, anti-patterns, and cited sources. Not generic prompts. Real engineering guides.
The Docker skill is 1,422 words with a multi-stage Node.js template, BuildKit cache optimization, distroless base images, and CVE scanning. The auth skill references OWASP directly. The database one has real EXPLAIN ANALYZE output. Frontend skills include Emil Kowalski patterns (Sonner, Vaul), Paul Bakaus principles (Impeccable), and Leon Lin variance engines (Taste). Skills are validated by CI on every push: frontmatter, workflow, error handling, sources. All mandatory.
| Domain | Skills | Version |
|---|---|---|
| Infrastructure | docker, kubernetes, terraform, ci-cd, db-admin | v4.0 |
| Backend | auth-architect, api-forge, db-sculptor, error-handler | v4.0 |
| Frontend | component-forge, responsive-engine, motion-craft, landing-craft, aesthetic-web, ui-ux-pro-max, emil-design-eng, impeccable, taste, taste-soft, taste-minimalist | v4.0 |
| Mobile | flutter, react-native | v4.0 |
| Quality | test-commander, performance-profiler, code-review, comprehensive-review, cross-review, zen-review, zen-comprehensive-review | v4.0 |
| Content & Business | communication, con |