code-virtuoso
mcp
Gecti
Health Gecti
- License — License: MIT
- Description — Repository has a description
- Active repo — Last push 0 days ago
- Community trust — 14 GitHub stars
Code Gecti
- Code scan — Scanned 10 files during light audit, no dangerous patterns found
Permissions Gecti
- Permissions — No dangerous permissions requested
Purpose
This project provides a collection of skills, playbooks, and sub-agent definitions designed to enhance AI coding assistants like Claude Code and Cursor. It focuses on software engineering best practices, offering frameworks, role-playing configurations, and operational guides.
Security Assessment
Overall risk: Low. The tool acts primarily as a static knowledge base and configuration layer for compatible AI agents, rather than standalone executable software. A light code scan of 10 files found no dangerous patterns, hardcoded secrets, or requests for dangerous permissions. It does not appear to independently execute shell commands, make suspicious network requests, or access sensitive local data. The installation process relies on the standard Node.js `npx` package runner, which is generally safe for downloading open-source assets.
Quality Assessment
Overall quality is good. The repository uses the permissive MIT license and is actively maintained, with the most recent code push occurring today. The project features automated validation workflows for its skills and agents, indicating a structured approach to maintaining the codebase. Community trust is currently limited but present, with 14 GitHub stars. This is normal for an early-stage or niche utility and does not raise any immediate red flags.
Verdict
Safe to use.
This project provides a collection of skills, playbooks, and sub-agent definitions designed to enhance AI coding assistants like Claude Code and Cursor. It focuses on software engineering best practices, offering frameworks, role-playing configurations, and operational guides.
Security Assessment
Overall risk: Low. The tool acts primarily as a static knowledge base and configuration layer for compatible AI agents, rather than standalone executable software. A light code scan of 10 files found no dangerous patterns, hardcoded secrets, or requests for dangerous permissions. It does not appear to independently execute shell commands, make suspicious network requests, or access sensitive local data. The installation process relies on the standard Node.js `npx` package runner, which is generally safe for downloading open-source assets.
Quality Assessment
Overall quality is good. The repository uses the permissive MIT license and is actively maintained, with the most recent code push occurring today. The project features automated validation workflows for its skills and agents, indicating a structured approach to maintaining the codebase. Community trust is currently limited but present, with 14 GitHub stars. This is normal for an early-stage or niche utility and does not raise any immediate red flags.
Verdict
Safe to use.
Skills, sub-agents, and playbooks for Claude Code, Cursor, and any Agent Skills-compatible AI coding assistant.
README.md
Code Virtuoso
AI agent skill sets for software engineering — built on the Agent Skills open standard. Knowledge, Tools, Frameworks, Playbooks, Roles, and Agents.
Six categories, installable independently or as bundles:
- Knowledge — Design Patterns, Refactoring, SOLID Principles, Debugging, Clean Architecture, Testing, API Design, Security, Scrum, Performance, Microservices, Git Workflow, CI/CD, Accessibility, Database Design. Reference material with progressive disclosure.
- Tools — Agentic Rules Writer, Ticket Writer. Agent configuration, bootstrapping, and backlog authoring tools.
- Frameworks — Symfony Components, Symfony Upgrade, Django Components, LangChain Components. Component-level reference and version upgrade guides for framework-specific development.
- Playbooks — PHP Upgrade, Composer Dependencies. Step-by-step operational procedures for recurring maintenance tasks.
- Roles — Product Manager, Architect, Backend Dev, Frontend Dev, QA Engineer, Project Manager. Reference skills defining responsibilities, workflows, and handoff checklists for each team role.
- Agents — 15 sub-agent definitions (8 specialist + 7 role agents) following the Claude Code sub-agents standard. Specialist agents handle focused tasks (investigation, TDD, code review, refactoring, auditing, documentation, migration planning, test gap analysis). Role agents embody team positions with persistent memory and skill preloading.
Installation
# Interactive — select skills and agents to install
npx skills add krzysztofsurdy/code-virtuoso
# Install specific skills
npx skills add krzysztofsurdy/code-virtuoso --skill design-patterns --skill refactoring
# Install all skills to all agents
npx skills add krzysztofsurdy/code-virtuoso --all
# Install globally (available in all projects)
npx skills add krzysztofsurdy/code-virtuoso -g
# List available skills without installing
npx skills add krzysztofsurdy/code-virtuoso --list
Keeping Skills Updated
# Check for available updates
npx skills check
# Update all installed skills to latest versions
npx skills update
Auto-update (once daily, background)
macOS / Linux — runs silently on each new shell, at most once per day:
echo '_skills_marker="${TMPDIR:-/tmp}/.skills-updated-$(date +%Y%m%d)"
[ ! -f "$_skills_marker" ] && (npx skills update --yes >/dev/null 2>&1 && touch "$_skills_marker" &)' >> ~/.zshrc
Windows (PowerShell) — same behavior, once per day on shell startup:
Add-Content $PROFILE '$marker = "$env:TEMP\.skills-updated-$(Get-Date -Format yyyyMMdd)"; if (-not (Test-Path $marker)) { Start-Job { npx skills update --yes *> $null; New-Item $using:marker -Force } | Out-Null }'
Project-level — auto-update after every git pull via post-merge hook:
printf '#!/bin/sh\nnpx skills update --yes >/dev/null 2>&1 &\n' > .git/hooks/post-merge && chmod +x .git/hooks/post-merge
Knowledge Skills
| Skill | Summary |
|---|---|
| Design Patterns | 26 Gang of Four patterns with PHP 8.3+ implementations |
| Refactoring | 67 refactoring techniques and 22 code smells |
| SOLID | All five SOLID principles with multi-language examples |
| Debugging | Systematic debugging methodology and post-mortem templates |
| Clean Architecture | Clean/Hexagonal Architecture and DDD fundamentals |
| Testing | Testing pyramid, TDD schools, test doubles, strategies |
| API Design | REST and GraphQL design principles and evolution strategies |
| Security | OWASP Top 10, auth patterns, secure coding practices |
| Scrum | Sprint goals, events, roles, and facilitation templates |
| Performance | Profiling, caching, database optimization, N+1 prevention |
| Microservices | Saga, CQRS, event sourcing, circuit breakers, service mesh |
| Git Workflow | Branching strategies, commit conventions, PR patterns, release management |
| CI/CD | Pipeline design, deployment strategies, environment promotion |
| Accessibility | WCAG compliance, ARIA patterns, keyboard navigation, a11y testing |
| Database Design | Schema modeling, indexing strategies, migration patterns, temporal data |
Tool Skills
| Skill | Summary |
|---|---|
| Agentic Rules Writer | Generate rules files for Claude Code, Cursor, Windsurf, Copilot, Gemini, Roo Code, or Amp |
| Ticket Writer | Interactive tool to write tickets of the right type -- story, subtask, issue, bug, epic, or initiative -- each with its own structure and quality checks |
Framework Skills
| Skill | Summary |
|---|---|
| Symfony Components | 38 Symfony components for PHP 8.3+ and Symfony 7.x |
| Symfony Upgrade | Deprecation-first upgrade guide for minor and major Symfony versions |
| Django Components | 33 Django components for Python 3.10+ and Django 6.0 |
| LangChain Components | 17 LangChain ecosystem references — models, agents, tools, retrieval, LangGraph, Deep Agents |
Playbook Skills
| Skill | Summary |
|---|---|
| PHP Upgrade | PHP version upgrade process with Rector, PHPCompatibility, and per-version breaking changes |
| Composer Dependencies | Safe dependency update strategies, security auditing, and automated update tools |
Role Skills
| Skill | Summary |
|---|---|
| Product Manager | Requirements gathering, PRD writing, prioritization, acceptance criteria |
| Architect | System design, component boundaries, API contracts, ADRs |
| Backend Dev | API implementation, data models, TDD workflows |
| Frontend Dev | UI components, accessibility, state management |
| QA Engineer | Test planning, test design, bug reporting, release sign-off |
| Project Manager | PRINCE2-based delivery, risk management, progress tracking |
Agents
See AGENTS.md for detailed agent specifications, delegation patterns, and usage examples.
Specialist Agents
| Agent | Model | Tools | Isolation | Purpose |
|---|---|---|---|---|
| Investigator | haiku | Read, Grep, Glob, Bash | -- | Deep codebase exploration, dependency mapping |
| Implementer | inherit | All | worktree | TDD red-green-refactor execution |
| Reviewer | inherit | Read, Grep, Glob, Bash | -- | Structured code review (SOLID, OWASP, smells) |
| Refactor Scout | sonnet | Read, Grep, Glob, Bash | -- | Code smell scanning, complexity hotspots |
| Dependency Auditor | haiku | Bash, Read, Grep, Glob | -- | CVE checks, outdated packages, license audit |
| Doc Writer | sonnet | Read, Grep, Glob, Bash, Write, Edit | -- | Changelogs, API docs, migration guides |
| Migration Planner | inherit | Read, Grep, Glob, Bash | -- | Migration safety analysis, rollback paths |
| Test Gap Analyzer | sonnet | Read, Grep, Glob, Bash | -- | Missing test coverage, untested edge cases |
Role Agents
| Agent | Model | Tools | Isolation | Memory | Purpose |
|---|---|---|---|---|---|
| Product Manager | sonnet | Read, Grep, Glob, Bash | -- | project | Requirements, PRDs, prioritization |
| Architect | inherit | Read, Grep, Glob, Bash | -- | project | System design, ADRs, trade-offs |
| Backend Dev | inherit | Read, Edit, Write, Bash, Grep, Glob | worktree | -- | API implementation, data models, TDD |
| Frontend Dev | inherit | Read, Edit, Write, Bash, Grep, Glob | worktree | -- | UI components, accessibility, state |
| QA Engineer | sonnet | Read, Grep, Glob, Bash | -- | project | Test plans, bug reports, release sign-off |
| Project Manager | sonnet | Read, Grep, Glob, Bash | -- | project | PRINCE2 stages, risk, progress tracking |
| Scrum Master | sonnet | Read, Grep, Glob, Bash | -- | -- | Sprint planning, goals, retrospectives |
Repository Structure
code-virtuoso/
├── agents/ # Sub-agent definitions (Anthropic standard)
│ ├── investigator.md # Specialist: codebase exploration
│ ├── implementer.md # Specialist: TDD execution
│ ├── reviewer.md # Specialist: code review
│ ├── refactor-scout.md # Specialist: code smell scanning
│ ├── dependency-auditor.md # Specialist: CVE/license audit
│ ├── doc-writer.md # Specialist: documentation generation
│ ├── migration-planner.md # Specialist: migration safety
│ ├── test-gap-analyzer.md # Specialist: coverage gaps
│ ├── product-manager.md # Role: requirements, PRDs
│ ├── architect.md # Role: system design, ADRs
│ ├── backend-dev.md # Role: API implementation
│ ├── frontend-dev.md # Role: UI components
│ ├── qa-engineer.md # Role: test planning
│ ├── project-manager.md # Role: delivery management
│ └── scrum-master.md # Role: sprint facilitation
├── skills/
│ ├── knowledge/
│ │ ├── api-design/
│ │ ├── clean-architecture/
│ │ ├── debugging/
│ │ ├── design-patterns/
│ │ ├── refactoring/
│ │ ├── microservices/
│ │ ├── cicd/
│ │ ├── git-workflow/
│ │ ├── accessibility/
│ │ ├── database-design/
│ │ ├── performance/
│ │ ├── scrum/
│ │ ├── security/
│ │ ├── solid/
│ │ └── testing/
│ ├── roles/
│ │ ├── product-manager/
│ │ ├── architect/
│ │ ├── backend-dev/
│ │ ├── frontend-dev/
│ │ ├── qa-engineer/
│ │ └── project-manager/
│ ├── frameworks/
│ │ ├── django/
│ │ │ └── django-components/
│ │ ├── langchain/
│ │ │ └── langchain-components/
│ │ └── symfony/
│ │ ├── symfony-components/
│ │ └── symfony-upgrade/
│ ├── playbooks/
│ │ ├── php-upgrade/
│ │ └── composer-dependencies/
│ └── tools/
│ ├── agentic-rules-writer/
│ └── ticket-writer/
├── spec/ # Format specifications
│ ├── agent-skills-spec.md
│ ├── skill-spec.md
│ └── agent-spec.md
├── template/ # Starter templates
│ ├── SKILL.md
│ └── agent.md
├── AGENTS.md
├── CONTRIBUTING.md
├── LICENSE
└── README.md
Recommended Companion Tools
Beads — Task Memory for AI Agents
A distributed, git-backed graph issue tracker that gives AI agents persistent, structured memory for long-horizon tasks. Replaces ad-hoc markdown planning files with a dependency-aware task graph stored in a version-controlled database.
GSD — Spec-Driven Development
github.com/gsd-build/get-shit-done
A meta-prompting and context engineering system for Claude Code, OpenCode, Gemini CLI, and Codex. Solves context rot — the quality degradation that happens as Claude fills its context window. Spec-driven development with subagent orchestration and state management.
Grepika — Token-Efficient Code Search
github.com/agentika-labs/grepika
An MCP server that replaces built-in grep/file search with ranked, compact results using ~80% fewer tokens. Combines FTS5 full-text search, parallel grep, and trigram indexing with BM25 ranking.
Contributing
See CONTRIBUTING.md for guidelines on adding or improving skills.
License
MIT
Yorumlar (0)
Yorum birakmak icin giris yap.
Yorum birakSonuc bulunamadi