Deep Learning
671 skills in Data & AI > Deep Learning
import-updater
Update import statements across the codebase when modules are moved or renamed. This skill should be used after refactoring operations to ensure all imports remain functional and properly organized.
east-ui
Type-safe UI component library for the East language. Use when writing East programs that define user interfaces with declarative components. Triggers for: (1) Writing East programs with @elaraai/east-ui, (2) Creating layouts with Box, Flex, Stack, Grid, (3) Forms with Input, Select, Checkbox, Switch, Slider, (4) Data display with Table, TreeView, DataList, Gantt, Planner, (5) Charts with Chart.Line, Chart.Bar, Chart.Area, Chart.Pie, Chart.Scatter, (6) Overlays with Dialog, Drawer, Popover, Menu, Tooltip, (7) State management with State.readTyped, State.writeTyped.
frontend-dev-guidelines
Frontend development guidelines for React/TypeScript with Next.js and Tailwind CSS. Modern patterns including Suspense, lazy loading, file organization with features directory, Tailwind styling, performance optimization, and TypeScript best practices. Use when creating components, pages, features, fetching data, styling, routing, or working with frontend code.
github-pr-collector
Collecte et analyse les Pull Requests GitHub avec leurs commentaires d'agents de review IA (CodeRabbit, GitHub Copilot, Codex, etc.). Utilise GitHub CLI pour récupérer les données, extrait les métadonnées des agents avec jq, et génère une structure organisée par PR et par importance dans le dossier .scd du projet. Extensible pour supporter de nouveaux agents de review.
implementation-plan-reviewer
Use when reviewing implementation plans before execution, especially plans derived from design documents. Performs exhaustive analysis to ensure the plan is detailed enough for agents to execute without guessing interfaces, data shapes, or dependencies. Verifies timeline structure, parallel/sequential work organization, QA checkpoints, and agent responsibilities.
repo-sweep
Comprehensive pre-production repository audit for preparing repos for public release. Use when the user wants to perform a "final sweep", "production check", "pre-release audit", or prepare a repository to be made public. Audits metadata files across all project types (Fabric mods, Node/npm, Go, Python, etc.) for correct username/organization, checks README links, and identifies leftover development artifacts like planning docs, test scripts, and temporary files. Interactive cleanup with user confirmation.
structural-review
Use when manuscript has poor logical flow, unclear section organization, or weak paragraph transitions - assesses section-level coherence, paragraph progression, and experimental logic
vanilla-rails-views
Use when writing ERB templates, partials, view helpers, or Turbo Stream responses - covers partial organization, optional locals, CSS class patterns, collection rendering
synthesis-matrix
Create evidence synthesis matrices for systematic reviews. Use when: (1) Organizing extracted data, (2) Comparing study characteristics, (3) Identifying patterns across studies, (4) Preparing synthesis for manuscripts.
skill-authoring
Guide for authoring effective skills. Use when creating, building, updating, designing, packaging, reviewing, evaluating, or improving skills that extend Claude's capabilities with specialized knowledge, workflows, or tool integrations. Helps with skill structure, SKILL.md frontmatter, progressive disclosure, resource organization (scripts/assets/reference files), initialization templates, validation, and packaging. Also triggers when asking how to create a skill, what makes a good skill, learning about skill development, or troubleshooting skill issues. Includes proven design patterns for workflows and output quality.
architect-detective
⚡ PRIMARY TOOL for: 'what's the architecture', 'system design', 'how are layers organized', 'find design patterns', 'audit structure', 'map dependencies'. Uses claudemem v0.3.0 AST structural analysis with PageRank. GREP/FIND/GLOB ARE FORBIDDEN.
constituicao-federal
Especialista na Constituição Federal do Brasil de 1988, direitos fundamentais, organização do Estado e poder judiciário
brainstorming-facilitation
This skill provides guidance for facilitating interactive brainstorming sessions, selecting creative techniques from 61 options across 10 categories, executing coaching-style dialogues, or organizing generated ideas into actionable plans
skill-creator
Create new Claude Code skills with proper structure, documentation, and best practices. Use when building custom skills for specific domains, workflows, or organizational needs.
execution-phase
TDD-paired Gantt-style execution with compact waves. Each story gets tester agent (writes tests) BEFORE implementation agent (passes tests). Waves execute continuously with /compact between each wave. Respects dependencies, spawns up to 10 concurrent agents. Use when orchestrating parallel implementation workflows with test-first discipline.
multi-tenant
Multi-tenant architecture patterns including org_id claim management, JWT token structure with organization context, database isolation strategies for MongoDB and PostgreSQL, theme switching per organization, tenant provisioning workflows, data isolation patterns, and cross-tenant security. Activate for multi-tenancy implementation, tenant isolation, and organization-scoped data access.
performing-systematic-debugging-for-stubborn-problems
Applies a modified Fagan Inspection methodology to systematically resolve persistent bugs and complex issues. Use when multiple previous fix attempts have failed repeatedly, when dealing with intricate system interactions, or when a methodical root cause analysis is needed. Do not use for simple troubleshooting. Triggers after multiple failed debugging attempts on the same complex issue.
global-conventions
Follow project-wide development conventions for project structure, documentation, version control, code review, environment configuration, dependency management, and security practices. Use this skill when setting up new projects, organizing file structures, writing project documentation, creating Git branches and commits, configuring environment variables, managing dependencies, setting up CI/CD pipelines, or implementing security practices. Apply when working on project setup tasks, creating documentation files (README.md, ARCHITECTURE.md, DATABASE_SCHEMA.md, API_REFERENCE.md, SETUP.md), Git workflow operations, .env files, package.json/bun.lockb, Docker configurations, or any cross-cutting project concerns. This skill ensures hybrid code organization (global shared code by type + feature-specific code with nested subdirectories), required documentation (README, ARCHITECTURE, DATABASE_SCHEMA, API_REFERENCE, SETUP - written before coding then updated), GitHub Flow workflow (main branch production-ready, feat
inbox-assistant
Manage Gmail inbox with AI-powered triage, cleanup, and restore. Use when the user mentions inbox, email triage, clean inbox, email cleanup, check email, email summary, delete emails, manage inbox, or wants to organize their email.
pytorch-quantization
Techniques for model size reduction and inference acceleration using INT8 quantization, including Post-Training Quantization (PTQ) and Quantization Aware Training (QAT). (quantization, int8, qat, fbgemm, qnnpack, ptq, dequantize)