全部能力

Local LLM operations with Ollama on Apple Silicon, including setup, model pulls, chat launchers, benchmarks, and diagnostics.

Optimizes Pine Script for performance, user experience, and visual appeal on TradingView. Use when improving script speed, reducing load time, enhancing UI,…

USE FOR getting AI-generated POI text descriptions. Requires POI IDs obtained from web-search (with result_filter=locations). Returns markdown descriptions…

Fast structured generation and serving for LLMs with RadixAttention prefix caching. Use for JSON/regex outputs, constrained decoding, agentic workflows with…

Execute the implementation planning workflow using the plan template to generate design artifacts.

Creates and authors slide deck presentations using the PromptSlide framework (Vite + React 19 + Tailwind v4 + Framer Motion). Use when the user wants to create a new slide deck, add or edit slides, customize themes or branding, work with slide animations and transitions, capture slides as images, or visually verify slide appearance. Triggers on mentions of slides, decks, presentations, PromptSlide, slide screenshots, or slide-related tasks.

NHL data via ESPN public endpoints — scores, standings, rosters, schedules, game summaries, play-by-play, injuries, transactions, futures, team/player stats, leaders, and news. Zero config, no API keys. Use when: user asks about NHL scores, standings, team rosters, schedules, game stats, box scores, play-by-play, injuries, transactions, betting futures, team/player statistics, or NHL news. Don't use when: user asks about other hockey leagues (AHL, KHL, college hockey). For other sports use: nfl-data (NFL), nba-data (NBA), wnba-data (WNBA), mlb-data (MLB), football-data (soccer), tennis-data (tennis), golf-data (golf), cfb-data (college football), cbb-data (college basketball), fastf1 (F1). For betting odds use polymarket or kalshi. For news use sports-news.

ADK 智能体的系统化调试 — 追踪读取、日志分析、常见故障诊断与调试循环。

时间序列预测 — LightGBM、Transformers、时序验证、特征工程和生产部署。用于构建时间序列模型时。

A software security skill that integrates with Project CodeGuard to help AI coding agents write secure code and prevent common vulnerabilities. Use this skill…

Use the MemOS Local memory system to search and use the user's past conversations. Use this skill whenever the user refers to past chats, their own preferences…

25+ proven headline formulas that stop the scroll, capture attention, and drive clicks. Templates and examples for every situation. Use when: Writing headlines…

Send, search, and organize Gmail messages, drafts, and labels. Read full threads and get shareable Google Groups permalinks. Use when asked to compose an…

Apply when implementing fulfillment, invoice, or tracking logic for VTEX marketplace seller connectors. Covers the External Seller fulfillment protocol:…

cli-anything-drawio — an installable skill for AI agents, published by hkuds/cli-anything.

Expert guidance for configuring and deploying the OpenTelemetry Collector. Use when setting up a Collector pipeline, configuring receivers, exporters, or…

OpenAI Privacy Filter — bidirectional token-classification model for PII detection and masking in text

Track which stacks across a Pulumi organization use a specific package and at what versions. Use for cross-stack audits, identifying outdated or unmaintained…

This skill should be used when the user asks to 'place a CEX order', 'trade on centralized exchange', 'buy BTC on CEX', 'sell ETH futures', 'open a long…

Browse and recall OpenCode local memory stored on the user's machine: local sessions, plans, conversations, prompt history, and project context. Use immediately when the user asks to check history, previous sessions, past chats, what did we do before, last time, check plans, session history, recall, memory, remember, prior work, previous context, or have we done this before. Auto-trigger proactively when resuming work, continuing a project, referencing prior decisions, debugging repeated issues, revisiting earlier plans, or any follow-up where earlier OpenCode context may help. This means OpenCode local history/files specifically, not ChatGPT/Claude cloud history, generic web search, or unrelated product memory systems. Do NOT use for fresh tasks with no relevant history, or when current files/git already answer the question.