All authors
Claude Skills by frank-luongt
github.com/frank-luongt1,201 skills8 installs1,314 views
- Model Merging<!-- AUTO-GENERATED by export-skills.py — DO NOT EDIT --> --- name: model-merging description: Model merging techniques (TIES, DARE, SLERP, Task Arithmetic). Use when combining multiple fine-tuned models without additional training. ---Votes: 0GitHub stars: 31
- Model Pruning<!-- AUTO-GENERATED by export-skills.py — DO NOT EDIT --> --- name: model-pruning description: Model pruning and sparsification techniques. Use when reducing model size through structured or unstructured weight removal. ---Votes: 0GitHub stars: 31
- Modern Javascript PatternsComprehensive guide for mastering modern JavaScript (ES6+) features, functional programming patterns, and best practices for writing clean, maintainable, and performant code.Votes: 0GitHub stars: 31
- Moe Training<!-- AUTO-GENERATED by export-skills.py — DO NOT EDIT --> --- name: moe-training description: Mixture-of-Experts (MoE) training and architecture patterns. Use when building or training sparse MoE models for compute-efficient scaling. ---Votes: 0GitHub stars: 31
- Monorepo ArchitectExpert in monorepo architecture, build systems, and dependency management at scale. Masters Nx, Turborepo, Bazel, and Lerna for efficient multi-project development. Use PROACTIVELY for monorepo setup, build optimization, or scaling development workflows across teams.Votes: 0GitHub stars: 31
- Monorepo ManagementBuild efficient, scalable monorepos that enable code sharing, consistent tooling, and atomic changes across multiple packages and applications.Votes: 0GitHub stars: 31
- Multi Agent Brainstorming<!-- AUTO-GENERATED by export-skills.py — DO NOT EDIT --> --- name: multi-agent-brainstorming description: "Structured multi-agent design review with enforced roles: designer, skeptic, constraint guardian, user advocate, and arbiter. Use when validating system designs, surfacing hidden assumptions, stress-testing architectures before implementation, or preventing premature design approval." ---Votes: 0GitHub stars: 31
- Multi Agent PatternsMulti-agent architectures distribute work across multiple language model instances, each with its own context window. When designed well, this distribution enables capabilities beyond single-agent limits. When designed poorly, it introduces coordination overhead that negates benefits. The critical insight is that sub-agents exist primarily to isolate context, not to anthropomorphize role division.Votes: 0GitHub stars: 31
- N8n Code PythonExpert guidance for writing Python code in n8n Code nodes. ---Votes: 0GitHub stars: 31
- Nanogpt<!-- AUTO-GENERATED by export-skills.py — DO NOT EDIT --> --- name: nanogpt description: NanoGPT minimal GPT training implementation. Use when learning GPT internals or prototyping small-scale language models from scratch. ---Votes: 0GitHub stars: 31
- Nemo CuratorNVIDIA's toolkit for preparing high-quality training data for LLMs.Votes: 0GitHub stars: 31
- Nemo Evaluator<!-- AUTO-GENERATED by export-skills.py — DO NOT EDIT --> --- name: nemo-evaluator description: NVIDIA NeMo Evaluator for comprehensive model assessment. Use when running multi-backend evaluations with custom benchmarks and adapters. ---Votes: 0GitHub stars: 31
- Nemo Guardrails<!-- AUTO-GENERATED by export-skills.py — DO NOT EDIT --> --- name: nemo-guardrails description: NVIDIA NeMo Guardrails toolkit for LLM safety. Use when implementing programmable safety rails, topic control, or output validation for AI apps. ---Votes: 0GitHub stars: 31
- Next Best PracticesApply these rules when writing or reviewing Next.js code. Maintained by Vercel — the authoritative source for Next.js patterns.Votes: 0GitHub stars: 31
- Nextjs App Router PatternsComprehensive patterns for Next.js 14+ App Router architecture, Server Components, and modern full-stack React development.Votes: 0GitHub stars: 31
- Nist Csf<!-- AUTO-GENERATED by export-skills.py — DO NOT EDIT --> --- name: nist-csf description: NIST Cybersecurity Framework (CSF 2.0) reference for assessing, building, and improving organizational cybersecurity posture across six core functions. ---Votes: 0GitHub stars: 31
- Nnsightnnsight (/ɛn.saɪt/) enables researchers to interpret and manipulate the internals of any PyTorch model, with the unique capability of running the same code locally on small models or remotely on massive models (70B+) via NDIF. **GitHub**: [ndif-team/nnsight](https://github.com/ndif-team/nnsight) (730+ stars) **Paper**: [NNsight and NDIF: Democratizing Access to Foundation Model Internals](https://arxiv.org/abs/2407.14561) (ICLR 2025)Votes: 0GitHub stars: 31
- Nodejs Backend PatternsComprehensive guidance for building scalable, maintainable, and production-ready Node.js backend applications with modern frameworks, architectural patterns, and best practices.Votes: 0GitHub stars: 31
- NotebooklmInteract with Google NotebookLM to query documentation with Gemini's source-grounded answers. Each question opens a fresh browser session, retrieves the answer exclusively from your uploaded documents, and closes.Votes: 0GitHub stars: 31
- Notion AutomationAutomate Notion operations through Composio's Notion toolkit via Rube MCP.Votes: 0GitHub stars: 31
- Observability Engineer<!-- AUTO-GENERATED by export-skills.py — DO NOT EDIT --> --- name: observability-engineer description: Build production-ready monitoring, logging, and tracing systems. --- You are an observability engineer specializing in production-grade monitoring, logging, tracing, and reliability systems for enterprise-scale applications.Votes: 0GitHub stars: 31
- Observability Monitoring Monitor SetupYou are a monitoring and observability expert specializing in implementing comprehensive monitoring solutions. Set up metrics collection, distributed tracing, log aggregation, and create insightful dashboards that provide full visibility into system health and performance.Votes: 0GitHub stars: 31
- Observability Monitoring Slo ImplementYou are an SLO (Service Level Objective) expert specializing in implementing reliability standards and error budget-based engineering practices. Design comprehensive SLO frameworks, establish meaningful SLIs, and create monitoring systems that balance reliability with feature velocity.Votes: 0GitHub stars: 31
- One Drive AutomationAutomate OneDrive operations including file upload/download, search, folder management, sharing links, permissions management, and drive browsing through Composio's OneDrive toolkit.Votes: 0GitHub stars: 31
- Openai Agents SdkBuild production-grade multi-agent AI applications using the OpenAI Agents SDK with handoffs, guardrails, tracing, and MCP server integration.Votes: 0GitHub stars: 31
- Openapi Spec GenerationComprehensive patterns for creating, maintaining, and validating OpenAPI 3.1 specifications for RESTful APIs.Votes: 0GitHub stars: 31
- Openapi To TypescriptConvert OpenAPI 3.0 specifications to TypeScript interfaces and type guards. **Input**: OpenAPI file (JSON or YAML) **Output**: TypeScript file with interfaces, request/response types, and type guardsVotes: 0GitHub stars: 31
- Openrlhf<!-- AUTO-GENERATED by export-skills.py — DO NOT EDIT --> --- name: openrlhf description: OpenRLHF scalable RLHF training framework. Use when training models with PPO, DPO, or reward modeling at scale across multiple nodes. ---Votes: 0GitHub stars: 31
- Opportunity Solution TreeA visual framework from Teresa Torres' *Continuous Discovery Habits* that connects a **desired outcome** to **customer opportunities**, **potential solutions**, and **assumption tests** — ensuring you build what matters most. ---Votes: 0GitHub stars: 31
- Oracle Fusion AiConnect AI agents to Oracle Fusion Cloud applications (ERP, HCM, SCM) using REST APIs, and leverage Oracle's 50+ pre-built AI agents for enterprise workflows.Votes: 0GitHub stars: 31
- Outcome RoadmapTransform output-focused roadmaps (feature lists with dates) into outcome-focused roadmaps that communicate **why** you're building what you're building — and what success looks like. ---Votes: 0GitHub stars: 31
- Outlines<!-- AUTO-GENERATED by export-skills.py — DO NOT EDIT --> --- name: outlines description: Outlines structured text generation with guaranteed JSON/regex output. Use when enforcing structured outputs from local LLMs with grammar-based decoding. ---Votes: 0GitHub stars: 31
- Outlook AutomationAutomate Microsoft Outlook operations through Composio's Outlook toolkit via Rube MCP.Votes: 0GitHub stars: 31
- Outlook Calendar AutomationAutomate Outlook Calendar operations through Composio's Outlook toolkit via Rube MCP.Votes: 0GitHub stars: 31
- Owasp Api Top10<!-- AUTO-GENERATED by export-skills.py — DO NOT EDIT --> --- name: owasp-api-top10 description: OWASP API Security Top 10 (2023) risk identification, prevention patterns, and testing guidance for securing REST/GraphQL APIs ---Votes: 0GitHub stars: 31
- Owasp Top10<!-- AUTO-GENERATED by export-skills.py — DO NOT EDIT --> --- name: owasp-top10 description: OWASP Top 10 (2021) web application security risks with prevention controls, detection techniques, and remediation guidance ---Votes: 0GitHub stars: 31
- Page CroYou are an expert in **page-level conversion optimization**. Your goal is to **diagnose why a page is or is not converting**, assess readiness for optimization, and provide **prioritized, evidence-based recommendations**. You do **not** guarantee conversion lifts. You do **not** recommend changes without explaining *why they matter*. ---Votes: 0GitHub stars: 31
- Payment Integration<!-- AUTO-GENERATED by export-skills.py — DO NOT EDIT --> --- name: payment-integration description: Integrate Stripe, PayPal, and payment processors. Handles checkout ---Votes: 0GitHub stars: 31
- Pci ComplianceMaster PCI DSS (Payment Card Industry Data Security Standard) compliance for secure payment processing and handling of cardholder data.Votes: 0GitHub stars: 31
- Pci Dss V4<!-- AUTO-GENERATED by export-skills.py — DO NOT EDIT --> --- name: pci-dss-v4 description: PCI-DSS v4.0 requirements reference covering 12 requirements, customized approach, SAQ types, and assessment preparation for cardholder data environments. ---Votes: 0GitHub stars: 31
- Pdf<!-- AUTO-GENERATED by export-skills.py — DO NOT EDIT --> --- name: pdf description: Comprehensive PDF manipulation toolkit for extracting text and tables, creating new PDFs, merging/splitting documents, and handling forms. When Claude needs to fill in a PDF form or programmatically process, generate, or analyze PDF documents at scale. ---Votes: 0GitHub stars: 31
- PeftFine-tune LLMs by training <1% of parameters using LoRA, QLoRA, and 25+ adapter methods.Votes: 0GitHub stars: 31
- PhoenixOpen-source AI observability and evaluation platform for LLM applications with tracing, evaluation, datasets, experiments, and real-time monitoring.Votes: 0GitHub stars: 31
- PineconeThe vector database for production AI applications.Votes: 0GitHub stars: 31
- Podcast GenerationGenerate real audio narratives from text content using Azure OpenAI's Realtime API.Votes: 0GitHub stars: 31
- Postgres Best PracticesComprehensive performance optimization guide for Postgres, maintained by Supabase. Contains rules across 8 categories, prioritized by impact to guide automated query optimization and schema design.Votes: 0GitHub stars: 31
- Postgresql<!-- AUTO-GENERATED by export-skills.py — DO NOT EDIT --> --- name: postgresql description: Design a PostgreSQL-specific schema. Covers best-practices, data types, indexing, constraints, performance patterns, and advanced features ---Votes: 0GitHub stars: 31
- Postmark AutomationAutomate Postmark transactional email operations through Composio's Postmark toolkit via Rube MCP.Votes: 0GitHub stars: 31
- Postmortem WritingComprehensive guide to writing effective, blameless postmortems that drive organizational learning and prevent incident recurrence.Votes: 0GitHub stars: 31
- Pptx<!-- AUTO-GENERATED by export-skills.py — DO NOT EDIT --> --- name: pptx description: "Presentation creation, editing, and analysis. When Claude needs to work with presentations (.pptx files) for: (1) Creating new presentations, (2) Modifying or editing content, (3) Working with layouts, (4) Adding comments or speaker notes, or any other presentation tasks" ---Votes: 0GitHub stars: 31