Total 31,795 skills, AI & Machine Learning has 5133 skills
Showing 12 of 5133 skills
Systematic LLM prompt engineering: analyzes existing prompts for failure modes, generates structured variants (direct, few-shot, chain-of-thought), designs evaluation rubrics with weighted criteria, and produces test case suites for comparing prompt performance. Triggers on: "prompt engineering", "prompt lab", "generate prompt variants", "A/B test prompts", "evaluate prompt", "optimize prompt", "write a better prompt", "prompt design", "prompt iteration", "few-shot examples", "chain-of-thought prompt", "prompt failure modes", "improve this prompt". Use this skill when designing, improving, or evaluating LLM prompts specifically. NOT for evaluating Claude Code skills or SKILL.md files — use skill-evaluator instead.
Expert GPU optimization for modern consumer GPUs (8-24GB VRAM). Use this skill when you need to optimize GPU training, speed up CUDA code, reduce OOM errors, tune XGBoost for GPU, migrate NumPy to CuPy, make a model faster, manage GPU memory, optimize VRAM usage, or benchmark PyTorch. Covers mixed precision, gradient checkpointing, XGBoost GPU acceleration, CuPy/cuDF migration, vectorization, torch.compile, and diagnostics. NVIDIA GPUs only. PyTorch, XGBoost, and RAPIDS frameworks.
Technical guide for creating a new Paperclip agent adapter. Use when building a new adapter package, adding support for a new AI coding tool (e.g. a new CLI agent, API-based agent, or custom process), or when modifying the adapter system. Covers the required interfaces, module structure, registration points, and conventions derived from the existing claude-local and codex-local adapters.
DEPRECATED: Use the model's native extended thinking instead. Structured, reflective problem-solving through sequential chain-of-thought reasoning that replaced the Sequential Thinking MCP server.
Evaluate AI contribution in projects using the AI Assessment Scale (AIAS) 5-level framework. Measure AI involvement from no AI to full AI exploration across development stages.
Use this skill when you need guidance on which skill to use for any task. Recommends the perfect skill, creates skill combinations, and helps you discover capabilities you didn't know you had.
Provides strategic insights on AI-driven software democratization and agent-based development trends from Replit's perspective. Use when discussing the future of software engineering, AI agent infrastructure requirements, democratization of coding, or when analyzing how AI will transform software creation from expert-only to universal access. Triggers include questions about software engineering automation trends, agent sandbox environments, SWE-bench benchmarks, or strategic implications of AI coding assistants for startups and enterprises.
Distill Opus-level reasoning into optimized instructions for Haiku 4.5 (and Sonnet). Generates explicit, procedural prompts with n-shot examples that maximize smaller model performance on a given task. Use when user says "down-skill", "distill for Haiku", "optimize for Haiku", "make this work on Haiku", "generate Haiku instructions", or needs to delegate a task to a smaller model with high reliability.
Set up Symphony (OpenAI's Codex orchestrator) for a user's repo. Use when the user mentions Symphony setup, configuring Symphony, getting Symphony running, or wants to connect their repo to Linear for autonomous Codex agents. Also use when the user says "set up symphony", "configure symphony for my repo", or references WORKFLOW.md configuration.
Linear GraphQL patterns for Symphony agents. Use `linear_graphql` for all operations — comments, state transitions, PR attachments, file uploads, and issue creation. Never use schema introspection.
Trains and fine-tunes vision models for object detection (D-FINE, RT-DETR v2, DETR, YOLOS), image classification (timm models — MobileNetV3, MobileViT, ResNet, ViT/DINOv3 — plus any Transformers classifier), and SAM/SAM2 segmentation using Hugging Face Transformers on Hugging Face Jobs cloud GPUs. Covers COCO-format dataset preparation, Albumentations augmentation, mAP/mAR evaluation, accuracy metrics, SAM segmentation with bbox/point prompts, DiceCE loss, hardware selection, cost estimation, Trackio monitoring, and Hub persistence. Use when users mention training object detection, image classification, SAM, SAM2, segmentation, image matting, DETR, D-FINE, RT-DETR, ViT, timm, MobileNet, ResNet, bounding box models, or fine-tuning vision models on Hugging Face Jobs.
Daily self-reflection and personal growth. Triggered by heartbeat at end of day. Review the day's experiences, extract lessons, update personality, and write a diary entry.