Total 32,447 skills, AI & Machine Learning has 5234 skills
Showing 12 of 5234 skills
File-based memory system using Tiago Forte's PARA method. Use this skill whenever you need to store, retrieve, update, or organize knowledge across sessions. Covers three memory layers: (1) Knowledge graph in PARA folders with atomic YAML facts, (2) Daily notes as raw timeline, (3) Tacit knowledge about user patterns. Also handles planning files, memory decay, weekly synthesis, and recall via qmd. Trigger on any memory operation: saving facts, writing daily notes, creating entities, running weekly synthesis, recalling past context, or managing plans.
Build AI agents and automate Claude Code programmatically using the Claude Agent SDK and headless CLI mode. Use this skill when you need to build an agent, create a Claude agent, make a bot, work with the agent SDK, run Claude in headless mode, write programmatic agent code, automate with Claude, create an MCP server builder, or query Claude programmatically. Covers the Python SDK, the claude -p headless interface, custom tool creation with SDK MCP servers, hooks for deterministic control, session management, and CLI flag reference. Authentication uses existing ~/.claude/ config — no API keys required.
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.