Loading...
Loading...
Found 313 Skills
Use this skill when writing code that calls the Gemini API for text generation, multi-turn chat, multimodal understanding, image generation, streaming responses, background research tasks, function calling, structured output, or migrating from the old generateContent API. This skill covers the Interactions API, the recommended way to use Gemini models and agents in Python and TypeScript.
Systematic X (Twitter) operations skill for founders, indie developers, and tech professionals. Implements a daily Plan-Do-Check-Act closed loop with content strategy (5-pillar system), multimodal creation, thread growth playbook, engagement and community building, product promotion integration, persona development, competitor analysis, and data-driven continuous improvement. Use when managing an X account, planning content, analyzing tweet performance, engaging with community, running competitive analysis, or optimizing posting strategy.
Build Zalo Mini Apps - lightweight web apps running inside Zalo super-app. This skill provides ZaUI components (Button, Input, Modal, Tabs, Avatar, etc.), JavaScript APIs (authorize, getUserInfo, getPhoneNumber, getLocation, Storage, Camera), Checkout SDK for payments, design guidelines, and development tools. Use when building Mini Apps, using ZaUI components, calling Zalo APIs, integrating payments, converting web apps to Mini Apps, or following Zalo design standards.
Build, debug, and maintain GNOME Shell extensions using GJS (GNOME JavaScript). Covers extension anatomy (metadata.json, extension.js, prefs.js, stylesheet.css), ESModule imports, GSettings preferences, popup menus, quick settings, panel indicators, dialogs, notifications, search providers, translations, and session modes. Use when the user wants to: (1) Create a new GNOME Shell extension, (2) Add UI elements like panel buttons, popup menus, quick settings toggles/sliders, or modal dialogs, (3) Implement extension preferences with GTK4/Adwaita, (4) Debug or test an extension, (5) Port an extension to a newer GNOME Shell version (45-49+), (6) Prepare an extension for submission to extensions.gnome.org, (7) Work with GNOME Shell internal APIs (Clutter, St, Meta, Shell, Main).
Work with state-of-the-art machine learning models for NLP, computer vision, audio, and multimodal tasks using HuggingFace Transformers. This skill should be used when fine-tuning pre-trained models, performing inference with pipelines, generating text, training sequence models, or working with BERT, GPT, T5, ViT, and other transformer architectures. Covers model loading, tokenization, training with Trainer API, text generation strategies, and task-specific patterns for classification, NER, QA, summarization, translation, and image tasks. (plugin:scientific-packages@claude-scientific-skills)
Use when building with DaisyUI — Tailwind CSS component class library. Covers class naming conventions, component classes (btn, card, modal, drawer, tab, badge, alert, etc.), color modifiers, size modifiers, theming with data-theme and CSS variables, OKLch colors, responsive patterns, installation, and class reference lookup via MCP tools.
Builds sophisticated admin interfaces and frontend components using Magento's UI Component framework. Use when creating admin grids, forms, modals, or data-driven interfaces. Masters XML configuration, KnockoutJS templates, data providers, and complex form/grid implementations.
Guide Claude through SCSA, MetaTiME, CellVote, CellMatch, GPTAnno, and weighted KNN transfer workflows for annotating single-cell modalities.
Train or fine-tune sentence-transformers models across `SentenceTransformer` (bi-encoder; dense or static embedding model; for retrieval, similarity, clustering, classification, paraphrase mining, dedup, multimodal), `CrossEncoder` (reranker; pair scoring for two-stage retrieval / pair classification), and `SparseEncoder` (SPLADE, sparse embedding model; for learned-sparse retrieval). Covers loss selection, hard-negative mining, evaluators, distillation, LoRA, Matryoshka, and Hugging Face Hub publishing. Use for any sentence-transformers training task.
Adversarial robustness engineering for ML/AI—evasion, poisoning, extraction, membership-inference threat models; robust training, sanitization, detectors; ASR/certified evals; lab model attacks; data-pipeline integrity; production I/O guardrails (classical ML and LLM/multimodal). Use for adversarial examples, robustness suites, poison audits, deploy guardrails—not LLM app red team (ai-redteam), governance (ai-risk-governance), safety classifier R&D (ml-research-engineer-safeguards), safeguard serving (ml-infrastructure-engineer-safeguards), privacy research (privacy-research-engineer-safeguards), AppSec pentest (penetration-tester).
Data framework for building LLM applications with RAG. Specializes in document ingestion (300+ connectors), indexing, and querying. Features vector indices, query engines, agents, and multi-modal support. Use for document Q&A, chatbots, knowledge retrieval, or building RAG pipelines. Best for data-centric LLM applications.
React game UI patterns using shadcn/ui, Tailwind, and Framer Motion for polished game interfaces. Use when building HUDs, resource bars, scoreboards, modals, tooltips, card components, or any game UI. Includes micro-interactions, animations, responsive layouts, and accessibility for games. Triggers on requests for game interface components, UI animations, or shadcn/ui game patterns.