bilge-development-kit

Full codebase audit: architecture health, dependencies, complexity, tech debt. Use when: "audit", "health check", "codebase analysis", "tech debt", "architecture review", "dependency check", "code quality"

Structured brainstorming with multiple approaches and tradeoffs. Use when: "brainstorm", "explore options", "what are my options", "compare approaches", "pros and cons", "which is better", "how should I", "alternatives"

Build error diagnosis and resolution. Use when: "build failed", "compile error", "bundler error", "fix build", "npm error", "type error", "won't compile"

Scaffold a new application with interactive dialogue. Use when: "create", "build me", "make an app", "new project", "scaffold", "generate app", "start new"

Generate a new custom skill from natural language description. Use when: "create skill", "new skill", "make a skill", "add command", "custom workflow", "skill template", "generate skill"

Systematic debugging with hypothesis-driven investigation. Use when: "debug", "not working", "bug", "broken", "error", "unexpected behavior", "fix issue", "investigate"

Production deployment with pre-flight checks and verification. Use when: "deploy", "ship", "release", "go live", "push to prod", "publish", "launch"

Add or update features in an existing application. Use when: "enhance", "add feature", "update", "improve", "extend", "integrate", "make it", "add support for", "upgrade"

One-command project onboarding. Scans tech stack, maps architecture, generates CLAUDE.md, initializes Memory Bank, reports warnings. Use when: "onboard", "setup project", "initialize", "get started", "make project-aware", "scan project"

Coordinate 3+ specialist agents for complex multi-domain tasks. Use when: "orchestrate", "full stack", "coordinate agents", "multi-agent", "complex task", "end to end"

Create a structured project plan from a task description. Use when: "plan", "design", "architect", "outline", "break down", "how should I build", "strategy", "roadmap"

Local development server management. Use when: "preview", "start server", "localhost", "dev server", "run app", "start app", "stop server"

Safe push pipeline: pre-push checks, test validation, smart commit, and push. Use when: "push", "commit and push", "ship it", "pushla", "gönder", "commit", "hazırla ve gönder"

Safe, systematic code refactoring with test safety net. Use when: "refactor", "clean up", "simplify", "modernize", "extract", "rename across", "reduce complexity", "tech debt"

Memory Bank system for cross-session persistence. Use when: "remember", "save context", "memory bank", "persist", "session context", "what did we do", "update memory"

Comprehensive code review with multi-agent analysis. Use when: "review", "code review", "check my code", "review PR", "audit code", "is this good", "review changes"

Comprehensive security audit with OWASP Top 10 analysis. Use when: "security", "vulnerability", "audit", "pentest", "check secrets", "is it secure", "owasp", "security scan"

Display project and agent status with live data. Use when: "status", "progress", "what's running", "where are we", "show state", "dashboard"

Test generation and execution with coverage analysis. Use when: "test", "write tests", "run tests", "coverage", "unit test", "test this", "add tests"

AI-powered design system with 50+ styles, 95+ palettes, 57 font pairings. Use when: "design", "UI", "UX", "design system", "color palette", "typography", "landing page design", "make it beautiful"

Testing and benchmarking LLM agents including behavioral testing, capability assessment, reliability metrics, and production monitoring. Covers evaluation frameworks, benchmark design, metrics collection, A/B testing, and continuous evaluation pipelines for AI agent systems.

Manage multiple local CLI agents via tmux sessions (start/stop/monitor/assign) with cron-friendly scheduling. Includes agent performance optimization workflows.

A hybrid memory system that provides persistent, searchable knowledge management for AI agents (Architecture, Patterns, Decisions).

Memory is the cornerstone of intelligent agents. Without it, every interaction starts from zero. This skill covers the architecture of agent memory: short-term (context window), long-term (vector s...

Tools are how AI agents interact with the world. A well-designed tool is the difference between an agent that works and one that hallucinates, fails silently, or costs 10x more tokens than necessar...

Build container-based Foundry Agents with Azure AI Projects SDK (ImageBasedHostedAgentDefinition). Use when creating hosted agents with custom container images in Azure AI Foundry.

Expert in designing and building autonomous AI agents. Masters tool use, memory systems, planning strategies, and multi-agent orchestration. Use when: build agent, AI agent, autonomous agent, tool ...

"Build production-ready LLM applications, advanced RAG systems, and"

Every product will be AI-powered. The question is whether you'll build it right or ship a demo that falls apart in production. This skill covers LLM integration patterns, RAG architecture, prompt ...

Expert in building products that wrap AI APIs (OpenAI, Anthropic, etc.) into focused tools people will pay for. Not just 'ChatGPT but different' - products that solve specific problems with AI. Cov...

Build production Apache Airflow DAGs with best practices for operators, sensors, testing, and deployment. Use when creating data pipelines, orchestrating workflows, or scheduling batch jobs.

You are an API mocking expert specializing in realistic mock services for development, testing, and demos. Design mocks that simulate real API behavior and enable parallel development.

Use when working with code refactoring context restore

Build AI agents that interact with computers like humans do - viewing screens, moving cursors, clicking buttons, and typing text. Covers Anthropic's Computer Use, OpenAI's Operator/CUA, and open-so...

SOTA Computer Vision Expert (2026). Specialized in YOLO26, Segment Anything 3 (SAM 3), Vision Language Models, and real-time spatial analysis.

Build scalable data pipelines, modern data warehouses, real-time streaming, data quality frameworks, and data-driven feature development. Implements Apache Spark, dbt, Airflow, Great Expectations, and cloud-native data platforms. Use PROACTIVELY for data pipeline design, analytics infrastructure, data quality, or modern data stack implementation.

"Expert data scientist for advanced analytics, machine learning, and"

Execute autonomous multi-step research using Google Gemini Deep Research Agent. Use for: market analysis, competitive landscaping, literature reviews, technical research, due diligence. Takes 2-10 ...

"Build high-performance async APIs with FastAPI, SQLAlchemy 2.0, and"

Create production-ready FastAPI projects with async patterns, dependency injection, and comprehensive error handling. Use when building new FastAPI applications or setting up backend API projects.