Data & AI skills

Write reliable prompts for Agentica/REPL agents that avoid LLM instruction ambiguity

The English summary is being prepared. Showing the original description.

Generate exactly one finished CRT retro computer-interface illustration from an uploaded portrait, group photo, creature, object, or described theme. Use when the user wants anchored subjects re-authored as an exaggerated circa-1980s bitmap editorial caricature beneath early Macintosh or Minitel-style windows, optionally invoking the exact Chinese presets 街头怪诞, 巨像符号, or 冷面几何. Before generation, collect a named or image-derived palette and aspect ratio through a strict two-stage intake unless supplied. Preserve each intended subject as a distinct identity, one shared pixel lattice, restricted non-skin checkerboard midtones, low-facet geometry, unequal extraction windows, mandatory barrel-curved CRT edges, and the immutable tait-crt-interface-skill title-bar signature. Never trace, auto-pixelate, imitate photographic detail, omit, merge, or duplicate subjects, retry, resize, expose prompts, or ask users to choose a style preset.

The English summary is being prepared. Showing the original description.

Optimize SQL query performance through EXPLAIN analysis, indexing strategies, and query rewriting for PostgreSQL, MySQL, and SQL Server. Use when debugging slow queries, analyzing execution plans, or improving database performance.

The English summary is being prepared. Showing the original description.

Build event streaming and real-time data pipelines with Kafka, Pulsar, Redpanda, Flink, and Spark. Covers producer/consumer patterns, stream processing, event sourcing, and CDC across TypeScript, Python, Go, and Java. When building real-time systems, microservices communication, or data integration pipelines.

The English summary is being prepared. Showing the original description.

Transform raw data into analytical assets using ETL/ELT patterns, SQL (dbt), Python (pandas/polars/PySpark), and orchestration (Airflow). Use when building data pipelines, implementing incremental models, migrating from pandas to polars, or orchestrating multi-step transformations with testing and quality checks.

The English summary is being prepared. Showing the original description.

Engineer effective LLM prompts using zero-shot, few-shot, chain-of-thought, and structured output techniques. Use when building LLM applications requiring reliable outputs, implementing RAG systems, creating AI agents, or optimizing prompt quality and cost. Covers OpenAI, Anthropic, and open-source models with multi-language examples (Python/TypeScript).

The English summary is being prepared. Showing the original description.

Builds dashboards, reports, and data-driven interfaces requiring charts, graphs, or visual analytics. Provides systematic framework for selecting appropriate visualizations based on data characteristics and analytical purpose. Includes 24+ visualization types organized by purpose (trends, comparisons, distributions, relationships, flows, hierarchies, geospatial), accessibility patterns (WCAG 2.1 AA compliance), colorblind-safe palettes, and performance optimization strategies. Use when creating visualizations, choosing chart types, displaying data graphically, or designing data interfaces.

The English summary is being prepared. Showing the original description.

Strategic guidance for designing modern data platforms, covering storage paradigms (data lake, warehouse, lakehouse), modeling approaches (dimensional, normalized, data vault, wide tables), data mesh principles, and medallion architecture patterns. Use when architecting data platforms, choosing between centralized vs decentralized patterns, selecting table formats (Iceberg, Delta Lake), or designing data governance frameworks.

The English summary is being prepared. Showing the original description.

Builds form components and data collection interfaces including contact forms, registration flows, checkout processes, surveys, and settings pages. Includes 50+ input types, validation strategies, accessibility patterns (WCAG 2.1), multi-step wizards, and UX best practices. Provides decision trees from data type to component selection, validation timing guidance, and error handling patterns. Use when creating forms, collecting user input, building surveys, implementing validation, designing multi-step workflows, or ensuring form accessibility.

The English summary is being prepared. Showing the original description.

Assembles component outputs from AI Design Components skills into unified, production-ready component systems with validated token integration, proper import chains, and framework-specific scaffolding. Use as the capstone skill after running theming, layout, dashboard, data-viz, or feedback skills to wire components into working React/Next.js, Python, or Rust projects.

The English summary is being prepared. Showing the original description.

Real-time communication patterns for live updates, collaboration, and presence. Use when building chat applications, collaborative tools, live dashboards, or streaming interfaces (LLM responses, metrics). Covers SSE (server-sent events for one-way streams), WebSocket (bidirectional communication), WebRTC (peer-to-peer video/audio), CRDTs (Yjs, Automerge for conflict-free collaboration), presence patterns, offline sync, and scaling strategies. Supports Python, Rust, Go, and TypeScript.

The English summary is being prepared. Showing the original description.

Data pipelines, feature stores, and embedding generation for AI/ML systems. Use when building RAG pipelines, ML feature serving, or data transformations. Covers feature stores (Feast, Tecton), embedding pipelines, chunking strategies, orchestration (Dagster, Prefect, Airflow), dbt transformations, data versioning (LakeFS), and experiment tracking (MLflow, W&B).

The English summary is being prepared. Showing the original description.

Optimizing vector embeddings for RAG systems through model selection, chunking strategies, caching, and performance tuning. Use when building semantic search, RAG pipelines, or document retrieval systems that require cost-effective, high-quality embeddings.

The English summary is being prepared. Showing the original description.

Data ingestion patterns for loading data from cloud storage, APIs, files, and streaming sources into databases. Use when importing CSV/JSON/Parquet files, pulling from S3/GCS buckets, consuming API feeds, or building ETL pipelines.

The English summary is being prepared. Showing the original description.

Builds tables and data grids for displaying tabular information, from simple HTML tables to complex enterprise data grids. Use when creating tables, implementing sorting/filtering/pagination, handling large datasets (10-1M+ rows), building spreadsheet-like interfaces, or designing data-heavy components. Provides performance optimization strategies, accessibility patterns (WCAG/ARIA), responsive designs, and library recommendations (TanStack Table, AG Grid).

The English summary is being prepared. Showing the original description.

Generate Nano Banana Pro (Gemini 3 Pro Image) prompts for e-commerce product photography. Given a user-uploaded product photo, this skill identifies the main subject, asks the user to choose a scene type, then outputs a professional, ready-to-paste English prompt optimized for Nano Banana Pro's image-to-image capabilities. Use this skill whenever the user uploads a product image and wants to generate an e-commerce photo, product shot, commercial image, or marketing visual using Nano Banana Pro / Gemini. Trigger phrases include: "ecom shot", "电商图", "产品图", "商品图", "product photo", "e-commerce image", "make a product shot", "generate a Nano Banana prompt for this product", "帮我做一张电商主图", "白底图", "商拍", "产品摄影", "hero shot", "packshot", or any request involving turning a casual product photo into a professional commercial image. Also trigger when the user mentions Nano Banana / Gemini image generation with a product photo.

The English summary is being prepared. Showing the original description.

Query stock quotes for US stocks, Hong Kong stocks, and A-shares. Use when the user asks about a stock price, market quote, or stock performance — including phrases like "查一下 BABA", "BABA 现在多少", "阿里巴巴股价", "茅台今天", "港股 9988", "美股行情", or any mention of a specific stock ticker or company name wanting price/change data. Also trigger for market overview requests like "大盘怎么样", "美股今天", "港股行情".

The English summary is being prepared. Showing the original description.

Provide real-time weather forecasts for any city worldwide. Use this skill whenever the user asks about weather, temperature, or climate conditions — including phrases like "weather in [city]", "what's the weather like", "weather forecast", "is it going to rain", "how hot is it", or any mention of checking current or upcoming weather conditions for a location. Also trigger when users ask about what to wear today, whether to bring an umbrella, or any question where weather data would help.

The English summary is being prepared. Showing the original description.

Get the current date (with day of week) and time (HH:MM:SS) in a specified timezone. Auto-trigger when needing to know current time, date, or day of week — including when guessing user's location based on schedule, answering "what time is it", "what day is it", "today is what date", or any context where accurate real-time clock data is needed. Also trigger proactively at the start of conversations to ground yourself in the current time.

The English summary is being prepared. Showing the original description.

Use this skill when the user uploads Excel (.xlsx/.xls) or CSV files and wants to perform data analysis, generate statistics, create summaries, pivot tables, SQL queries, or any form of structured data exploration. Supports multi-sheet Excel workbooks, aggregation, filtering, joins, and exporting results to CSV/JSON/Markdown.

The English summary is being prepared. Showing the original description.

Use this skill when the user requests to generate, create, or write professional research reports including but not limited to market analysis, consumer insights, brand analysis, financial analysis, industry research, competitive intelligence, investment due diligence, or any consulting-grade analytical report. This skill operates in two phases — (1) generating a structured analysis framework with chapter skeleton, data query requirements, and analysis logic, and (2) after data collection by other skills, producing the final consulting-grade report with structured narratives, embedded charts, and strategic insights.

The English summary is being prepared. Showing the original description.

Read your Instagram niche and profile from real data via Apify, no login. Scan a hashtag for the posts traveling now (likes, comments, owner) to see the format and hook that works. Pull profile stats for any handle, yours or a competitor's: followers, posts, bio, category. Instagram hides who liked or commented on other accounts, so this is discovery plus profiles, not engagers. Triggers on "what works in my niche", "scan the hashtag", "competitor stats". Not for writing captions (use ig-caption-writer).

The English summary is being prepared. Showing the original description.

Create a persistent HeyGen avatar — a reusable face + voice identity for the agent, the user, or any named character — powered by HeyGen Avatar V technology. Prompt-based creation by default (description → HeyGen builds it); photo upload is optional for real-person digital twins. Use when: (1) giving the agent a face + voice so it can present videos ("bring yourself to life", "create your avatar", "give yourself an avatar", "design a presenter", "set up an avatar", "let's make an avatar"), (2) the user wants to appear in videos as themselves ("create my avatar", "I want my face in a video", "digital twin of me", "build me an avatar"), (3) building a named character presenter ("create an avatar called Cleo", "design a character named X"), (4) establishing HeyGen identity before making videos — the correct FIRST step when no avatar exists yet. Chain signal: when the user says both an identity/avatar action AND a video action in the same request ("create an avatar AND make a video", "set up identity THEN create a video", "design a presenter AND immediately record"), run heygen-avatar first, then heygen-video. Returns avatar_id + voice_id — pass directly to heygen-video to create HeyGen videos. NOT for: generating videos (use heygen-video), translating videos, or TTS-only tasks.

The English summary is being prepared. Showing the original description.

Detect and recover text that was accidentally typed with the Taiwanese Bopomofo / Zhuyin (注音) keyboard while the input method (IME) was stuck in English/ASCII mode — what Taiwanese users call 注音亂碼 or 注音文 — producing meaningless-looking letter+digit sequences such as "su3cl3a8", "cl3", "g4", "2k7", "vu,4", or such garbled runs embedded in an otherwise normal request (e.g. "help me fix su3cl3a8", "看看這個 PR qk4ru.6", "幫我改 su3cl3a8xk7"). Use this skill whenever a user message contains short ASCII tokens that look like keyboard gibberish, do not form real English words, and cannot be understood normally — especially tokens with digits interspersed among letters (tone keys 3/4/6/7 or vowel keys 8/9/0), which are a strong sign of Mandarin phonetic keystrokes typed in the wrong input mode. Run scripts/decode_bopomofo.py to deterministically map the keystrokes back to 注音 symbols with a confidence score, then interpret the intended Traditional Chinese in context and continue the user's original request without making them retype. Do NOT trigger on genuine technical strings — code, file paths, URLs, git hashes, CLI flags, package names, version numbers — the script's exclusion rules and confidence tiers already filter these out. Especially valuable for Taiwanese developers who forget to switch input methods when prompting AI coding agents.

The English summary is being prepared. Showing the original description.