Agent Building skills

Browse reusable Agent Skills, each with a clear purpose and practical guidance.

ai-automation-builder

Comprehensive guide to building AI-powered automation workflows using n8n, Zapier, Make, and custom agent frameworks covering integration patterns, cost optimization, error handling, and production-ready AI workflow design. Use when the user asks about ai automation builder, related techniques, best practices, or needs guidance in this domain. Do NOT use when the request is outside the scope of ai automation builder or requires a different specialized skill.

543 repo starsObserved in 2 repos

Agent Building

GitHub

ai-evaluation-patterns

Guides expert-level ai evaluation patterns implementation: ai-ml and testing decision frameworks, production-ready patterns, and concrete templates for ai evaluation patterns workflows. Use when the user asks about ai evaluation patterns, ai evaluation patterns configuration, or ai-ml best practices for ai projects. Do NOT use when the user needs a different ai ml engineering capability -- check sibling skills in the ai ml engineering subcategory.

543 repo starsObserved in 2 repos

Agent Building

GitHub

ai-image-prompt-debugging

Diagnoses and fixes AI image generation prompt issues including mismatched style descriptors, conflicting terms, underspecified composition, and overcrowded token budgets with revised prompt output. Use when the user asks why their AI image prompt is not producing expected results, wants to fix a failing prompt, or needs to diagnose visual artifacts in generated images. Do NOT use for creating new prompts from scratch (use model-specific prompting skills), style transfer (use ai-image-style-transfer), or upscaling (use ai-image-upscaling).

543 repo starsObserved in 2 repos

Agent Building

GitHub

ai-prompt-crafter

Advanced prompting techniques for any AI model covering system prompts, chain-of-thought reasoning, few-shot examples, structured output formats, context management, multi-turn conversation strategies, and a reusable prompt template library. Use when the user asks about ai prompt crafter, related techniques, best practices, or needs guidance in this domain. Do NOT use when the request is outside the scope of ai prompt crafter or requires a different specialized skill.

543 repo starsObserved in 2 repos

Agent Building

GitHub

ai-safety-engineer

AI safety and alignment engineering covering guardrail implementation, red teaming methodologies, content filtering pipelines, output validation, prompt injection defense, toxicity detection, bias mitigation, and responsible deployment practices for LLM-powered systems. Use when the user asks about ai safety engineer, ai safety engineer best practices, or needs guidance on ai safety engineer implementation. Do NOT use when the user needs a different specialized skill or is asking about an unrelated technology domain.

543 repo starsObserved in 2 repos

Agent Building

GitHub

batch-image-generation

Produces batch image generation strategies with prompt templates using variable placeholders, seed management for consistent series, parameter variation approaches, and output organization systems. Use when the user asks to generate multiple images from a template, create image variations systematically, batch-produce AI art, or organize a large generation workflow. Do NOT use for single-image prompting (use model-specific skills), character consistency (use midjourney-consistency), or prompt debugging (use ai-image-prompt-debugging).

543 repo starsObserved in 2 repos

Agent Building

GitHub

dalle-prompting

Crafts DALL-E 3 and GPT-image-1 prompts using natural language style specification, quality descriptors, composition instructions, and revision dialogue patterns for iterative generation. Use when the user asks to create an image with DALL-E, GPT-image-1, ChatGPT image generation, or OpenAI image generation. Do NOT use for Midjourney prompting (use midjourney-prompting), Stable Diffusion prompting (use stable-diffusion-prompting), or translating prompts between models (use prompt-translation).

543 repo starsObserved in 2 repos

Agent Building

GitHub

llm-fine-tuner

Large language model fine-tuning expertise covering LoRA and QLoRA parameter-efficient methods, full fine-tuning strategies, dataset preparation and curation, instruction tuning, DPO alignment, evaluation frameworks, Hugging Face TRL and PEFT libraries, compute optimization, and deployment of fine-tuned models. Use when the user asks about llm fine tuner, llm fine tuner best practices, or needs guidance on llm fine tuner implementation. Do NOT use when the user needs a different specialized skill or is asking about an unrelated technology domain.

543 repo starsObserved in 2 repos

Agent Building

GitHub

llm-integration-patterns

Guides expert-level llm integration patterns implementation: ai-ml and backend decision frameworks, production-ready patterns, and concrete templates for llm integration patterns workflows. Use when the user asks about llm integration patterns, llm integration patterns configuration, or ai-ml best practices for llm projects. Do NOT use when the user needs a different ai ml engineering capability -- check sibling skills in the ai ml engineering subcategory.

543 repo starsObserved in 2 repos

Agent Building

GitHub

midjourney-prompting

Crafts Midjourney v6/v7 prompts with structured subject, environment, style, medium, lighting, and parameter syntax including --ar, --style, --q, --v, --chaos, --cref, and --sref. Use when the user asks to create a Midjourney prompt, generate AI art with Midjourney, write image prompts for Midjourney, or optimize Midjourney parameters. Do NOT use for DALL-E prompting (use dalle-prompting), Stable Diffusion prompting (use stable-diffusion-prompting), or translating prompts between models (use prompt-translation).

543 repo starsObserved in 2 repos

Agent Building

GitHub