This skill should be used when the user asks to "implement LLM-as-judge", "compare model outputs", "create evaluation rubrics", "mitigate evaluation bias", or mentions direct scoring, pairwise...
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...
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...
Offensive AI security testing and exploitation framework. Systematically tests LLM applications for OWASP Top 10 vulnerabilities including prompt injection, model extraction, data poisoning, and...
Create a Platform Strategy Pack (platform-as-product charter, interface map, lifecycle stage, ecosystem/moat model, governance, metrics, roadmap). Use for platform strategy, developer platforms,...
Meta's 7-8B specialized moderation model for LLM input/output filtering. 6 safety categories - violence/hate, sexual content, weapons, substances, self-harm, criminal planning. 94-95% accuracy....
Meta's 7-8B specialized moderation model for LLM input/output filtering. 6 safety categories - violence/hate, sexual content, weapons, substances, self-harm, criminal planning. 94-95% accuracy....
Provides PyTorch-native distributed LLM pretraining using torchtitan with 4D parallelism (FSDP2, TP, PP, CP). Use when pretraining Llama 3.1, DeepSeek V3, or custom models at scale from 8 to 512+...
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,...
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,...
Pollinations.ai API for AI generation - text, images, videos, audio, and analysis. Use when user requests AI-powered generation (text completion, images, videos, audio, vision/analysis,...
Run Claude Code CLI with GLM-4.7 model for AI code generation. Use when you need to generate code, debug, analyze files, or get AI programming assistance. Requires: Claude Code CLI + GLM-4.7 API...
Playwright E2E testing specialist for web applications. Invoke for browser automation, E2E tests, Page Object Model, test flakiness, visual testing. Keywords: Playwright, E2E, browser testing,...
Playwright E2E testing specialist for web applications. Invoke for browser automation, E2E tests, Page Object Model, test flakiness, visual testing. Keywords: Playwright, E2E, browser testing,...
Technical specification and design document expert. Use when writing design docs, RFCs, ADRs, or evaluating technology choices. Covers C4 model, system design, and architecture documentation.
Generate or edit images using AI models (FLUX, Gemini). Use for general-purpose image generation including photos, illustrations, artwork, visual assets, concept art, and any image that is not a...
Use when the user asks to run Gemini CLI for any tasks or if big context (>200k) is needed. Ideal for Code Review, Plan Review, Multi-file Analysis, and any task that requires large context...
Execute Hugging Face Hub operations using the `hf` CLI. Use when the user needs to download models/datasets/spaces, upload files to Hub repositories, create repos, manage local cache, or run...
Prisma ORM expert for schema design, migrations, query optimization, relations modeling, and database operations. Use PROACTIVELY for Prisma schema issues, migration problems, query performance,...
Prisma ORM expert for schema design, migrations, query optimization, relations modeling, and database operations. Use PROACTIVELY for Prisma schema issues, migration problems, query performance,...