Skill Claude CodeCodex
Build production-ready LLM agents with LangGraph, tool use, memory, streaming, and error handling. Use when designing or implementing an AI agent, multi-agent system, or agentic workflow.
Skill Claude CodeCodex
Design REST APIs with consistent naming, error handling, versioning, and pagination. Use when designing a new API, reviewing an existing one, or writing an OpenAPI spec.
Skill Claude CodeCodex
Senior backend architect persona — scalable system design, database architecture, API contracts, microservices, observability, and security-first engineering.
Skill Claude CodeCodex
Global AI/ML job hunt — USA, Europe, Singapore, Dubai, remote-first startups. Daily fetch, score, and track Senior AI/ML Engineer roles with LangChain/LangGraph/agent stack.
Skill Claude CodeCodex
CI/CD pipeline design and review — GitHub Actions, pipeline best practices, secrets management, deployment strategies, and release automation.
Skill Claude CodeCodex
Structured code review across five axes — correctness, security, performance, maintainability, and test coverage. Use when user asks to review code, check a PR, or audit a diff.
Skill Claude CodeCodex
Track, estimate, and optimize LLM API costs across providers. Use when user wants to understand their LLM spending, reduce costs, or compare provider pricing for a given workload.
Skill Claude CodeCodex
Production data pipeline patterns — ETL/ELT design, orchestration with Airflow/Prefect, idempotency, incremental loads, and data quality.
Skill Claude CodeCodex
Systematic root cause analysis for bugs, errors, and unexpected behavior. Use when user reports something broken, an error they can't explain, or unexpected output.
Skill Claude CodeCodex
Generate accurate, useful documentation for code — README files, API docs, inline docstrings, and changelogs. Use when user needs to document code, write a README, or generate API reference docs.
Skill Claude CodeCodex
FastAPI production patterns — routing, dependency injection, background tasks, streaming, error handling, and async. Use when building or reviewing a FastAPI service.
Skill Claude CodeCodex
Expert frontend developer persona — React/Vue/Angular, performance optimization, Core Web Vitals, accessibility. Builds responsive web apps with pixel-perfect precision.
Skill Claude CodeCodex
Git branching, commit conventions, rebase vs merge, conflict resolution, and release tagging. Use when setting up a git workflow, writing commits, resolving conflicts, or preparing a release.
Skill Claude CodeCodex
Kubernetes production patterns — manifests, resource sizing, health probes, scaling, secrets, networking, and troubleshooting.
Skill Claude CodeCodex
Evaluate LLM outputs systematically using LLM-as-judge, human evaluation frameworks, and regression testing. Use when assessing model quality, comparing models, or preventing quality regression.
Skill Claude CodeCodex
Production ML engineering workflow — data contracts, reproducible training, evaluation gates, deployment, and monitoring. Use when building, reviewing, or hardening ML systems beyond notebooks.
Skill Claude CodeCodex
Production Next.js 14+ patterns — App Router, Server Components, data fetching, caching, performance, and deployment best practices.
Skill Claude CodeCodex
Production OpenAI API patterns — model selection, prompt engineering, function calling, streaming, error handling, cost control, and structured outputs.
Skill Claude CodeCodex
Authorized penetration tester persona — offensive security specialist for network, web app, cloud, and Active Directory assessments. Requires explicit authorization.
Skill Claude CodeCodex
Systematic performance profiling and optimization for Python and web backends — measure first, fix second, verify the fix.
Skill Claude CodeCodex
Generate clear, complete pull request descriptions from a diff or commit list. Use when user needs to write a PR description, wants to document a change, or asks for a commit summary.
Skill Claude CodeCodex
Analyze and improve LLM prompts for clarity, precision, and output quality. Use when a prompt produces inconsistent results, the model ignores instructions, outputs are too long/short, or quality is below expectations.
Skill Claude CodeCodex
Python best practices — type hints, async/await, dataclasses, error handling, and performance patterns. Use when writing new Python code, reviewing Python, or modernizing legacy code.
Skill Claude CodeCodex
Evaluate RAG pipeline quality across faithfulness, relevance, and hallucination metrics. Use when user asks to test, benchmark, or improve a RAG system, or when RAG outputs look wrong.
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: