مرور مهارت‌ها

Craft professional README.md files for GitHub open source projects. Generates hero sections, installation instructions, feature tables, and architecture diagrams. Use when creating or revising a README, documenting a CLI tool, library, or open source project, or when user asks about README structure, badges, or project documentation.

CLAUDE.md file generation and optimization for Claude Code projects. Capabilities: initialize project instructions, analyze codebase context, optimize existing CLAUDE.md, apply Anthropic best practices, reduce token usage, improve effectiveness. Actions: init, create, optimize, enhance CLAUDE.md files. Keywords: CLAUDE.md, project instructions, Claude Code setup, project context, codebase analysis, Anthropic best practices, token optimization, project configuration, AI instructions, coding guidelines, project rules, workspace setup. Use when: initializing CLAUDE.md for new projects, optimizing existing project instructions, setting up Claude Code for a codebase, improving AI coding guidelines.

Build MCP servers in Python with FastMCP to expose tools, resources, and prompts to LLMs. Supports storage backends, middleware, OAuth Proxy, OpenAPI integration, and FastMCP Cloud deployment. Prevents 30+ errors. Use when: creating MCP servers, or troubleshooting module-level server, storage, lifespan, middleware, OAuth, background tasks, or FastAPI mount errors.

Activates when the user asks about AI prompts, needs prompt templates, wants to search for prompts, or mentions prompts.chat. Use for discovering, retrieving, and improving prompts.

Master advanced prompt engineering techniques to maximize LLM performance, reliability, and controllability in production. Use when optimizing prompts, improving LLM outputs, or designing production prompt templates.

Add a professional footer to README files with engagement prompts, community channels, and call-to-action for subscriptions. Use when you need to enhance your README with a footer that encourages interaction and builds community.

Generate AI video prompts for TikTok Thailand content across coffee, home decor, and kitchen niches. Use when user needs prompts for video creative concepts, script outlines, shot-by-shot scripts, voiceover/caption text, or hashtags. Skill considers Thai market characteristics including Thai-English language mixing, local trending topics, cultural nuances, and engagement patterns.

PROACTIVELY search auto-generated documentation when receiving ANY user instruction. Search for function signatures, API documentation, class definitions, and code comments BEFORE implementing anything. Your codebase documentation is valuable - use it first.

PROACTIVELY search conversation history when receiving user instructions. Find previous discussions, decisions, and context BEFORE starting new work. Your memory is valuable - use it.

Expert in designing, optimizing, and evaluating prompts for Large Language Models. Specializes in Chain-of-Thought, ReAct, few-shot learning, and production prompt management. Use when crafting prompts, optimizing LLM outputs, or building prompt systems. Triggers include "prompt engineering", "prompt optimization", "chain of thought", "few-shot", "prompt template", "LLM prompting".

Patterns for building Battery CLI commands with Commander.js. Use this skill when creating new CLI commands, adding options/flags, formatting output, handling errors, or implementing interactive prompts.

Creates interactive HTML playgrounds — self-contained single-file explorers that let users configure something visually through controls, see a live preview, and copy out a prompt. Use when the user asks to make a playground, explorer, or interactive tool for a topic.

Dockerfile security linting and best practice validation using Hadolint with 100+ built-in rules aligned to CIS Docker Benchmark. Use when: (1) Analyzing Dockerfiles for security misconfigurations and anti-patterns, (2) Enforcing container image security best practices in CI/CD pipelines, (3) Detecting hardcoded secrets and credentials in container builds, (4) Validating compliance with CIS Docker Benchmark requirements, (5) Integrating shift-left container security into developer workflows, (6) Providing remediation guidance for insecure Dockerfile instructions.

OpenAI's model connecting vision and language. Enables zero-shot image classification, image-text matching, and cross-modal retrieval. Trained on 400M image-text pairs. Use for image search, content moderation, or vision-language tasks without fine-tuning. Best for general-purpose image understanding.

Fine-tune LLMs using reinforcement learning with TRL: SFT for instruction tuning, DPO for preference alignment, PPO/GRPO for reward optimization, and reward model training. Use when need RLHF, align model with preferences, or train from human feedback. Works with HuggingFace Transformers.

Large Language and Vision Assistant. Enables visual instruction tuning and image-based conversations. Combines CLIP vision encoder with Vicuna/LLaMA language models. Supports multi-turn image chat, visual question answering, and instruction following. Use for vision-language chatbots or image understanding tasks. Best for conversational image analysis.

Distill learnings from completed features and propose amendments to constitution.md or prompt.md. Use after feature completion. Triggers on: capture learnings, learn from feature, distill learnings, relentless learn.

Comprehensive guide for building Model Context Protocol (MCP) servers with support for tools, resources, prompts, and authentication. Use when: (1) Creating custom MCP servers, (2) Integrating external APIs with Claude, (3) Building tool servers for specialized domains, (4) Creating resource providers for documentation, (5) Implementing authentication and security

Expert in Langfuse - the open-source LLM observability platform. Covers tracing, prompt management, evaluation, datasets, and integration with LangChain, LlamaIndex, and OpenAI. Essential for debugging, monitoring, and improving LLM applications in production. Use when: langfuse, llm observability, llm tracing, prompt management, llm evaluation.

Caching strategies for LLM prompts including Anthropic prompt caching, response caching, and CAG (Cache Augmented Generation) Use when: prompt caching, cache prompt, response cache, cag, cache augmented.