发现 Skills

Azure AI Text Translation SDK for real-time text translation, transliteration, language detection, and dictionary lookup. Use for translating text content in applications. Triggers: "text translation", "translator", "translate text", "transliterate", "TextTranslationClient".

Azure AI Search SDK for .NET (Azure.Search.Documents). Use for building search applications with full-text, vector, semantic, and hybrid search. Covers SearchClient (queries, document CRUD), SearchIndexClient (index management), and SearchIndexerClient (indexers, skillsets). Triggers: "Azure Search .NET", "SearchClient", "SearchIndexClient", "vector search C#", "semantic search .NET", "hybrid search", "Azure.Search.Documents".

Create Pydantic models following the multi-model pattern with Base, Create, Update, Response, and InDB variants. Use when defining API request/response schemas, database models, or data validation in Python applications using Pydantic v2.

Operate and debug the live Minecraft bot through its built-in MCP REPL server. Use this when your workflow requires starting the bot with `pnpm dev`, connecting to the local MCP endpoint, inspecting cognitive state, logs, or interaction history, injecting synthetic chat or game events, or running targeted REPL code against the running “brain” during investigation and development.

Execute complete user flow testing with Playwright MCP, testing end-to-end journeys through the application

LangChain 1.0 使用指南。提供 Agent、Tool、Memory、Middleware 等核心概念的快速参考。当用户需要创建 AI Agent、集成 LangChain、或解决 LangChain 相关问题时激活。

Use when generating physical PBIR JSON files (pages, visuals) from a report blueprint. Triggers: "implement PBIR", "generate visual JSON", "create page.json", "visual binding", "PBIR template", "implement report from blueprint", "add visual to page", "visual.json structure", "report.json", "pages.json".

Systematically add test coverage for all local code changes using specialized review and development agents. Add tests for uncommitted changes (including untracked files), or if everything is commited, then will cover latest commit.

Refined AI short-drama IP creation toolkit (v0.6.0). Three-phase architecture: Phase 1 Creation (script + reference images, iterative) → Phase 1.5 Storyboard frames (each grid produces 1–4 candidate stills = video keyframe; industrial core layer) → Phase 2 Production (episode-by-episode unlock, automatic selection among 4 video modes). v0.6.0 key upgrades: ① Ref library craftsmanship bias iron rule (modern skyscrapers tend to render photorealistically; ancient architecture often yields chibi-style humans — avoid these pitfalls during early IP design) ② JiMeng 5.0 failure modes + sensitive-word list (three fail categories distinguished / prompt hard limit 1500 characters / villain-word replacement table / ambiguous-word list) ③ Storyboard 8-segment prompt template (CHARACTER/BACKGROUND/ACTION/SCENE/CAMERA/LIGHT/TEXT/STYLE) with mandatory NOT humans clause. Continues upgrades from v0.3.0: Phase 1.5 storyboard layer, 4-mode video, ref optimum 5–8. v0.2.0 notes: bash → Python subprocess migration, 36-grid × 4–10s variations, seven guaranteed-viral tactics for Hongguo, industrial ref library 80–150 images, single prompts 300–500 characters. Must-trigger conditions: user mentions short drama, micro-short drama, vertical-screen drama, AI short drama, AI webcomic, scriptwriting, storyboards, JiMeng/Seedance production, Hongguo/Fanqie/Douyin IP adaptation, crowd-pleasing binge dramas, rebirth, time-travel, zhuixu/son-in-law trope, chasing-wife plots, divine-doctor/geomancer plots, AI webcomic spectacles, or requests like "help me make a short drama."

STM32 + FreeRTOS embedded development expert. Supports the full Cortex-M family, native FreeRTOS v10+ and CMSIS-RTOS v2 APIs. Useful for creating tasks, queues, semaphores, integrating standard libraries and HAL peripherals, memory optimization, low-power tickless mode, STM32CubeMX configuration, and debugging/analysis (SEGGER SystemView / Percepio TRACEalyzer).

Implements combat systems including hitboxes, damage calculation, stun mechanics, melee combat, ranged weapons, and ability systems. Use when building fighting games, shooters, RPG combat, or any game with player-vs-player or player-vs-NPC combat.

Expert guidance for using the GitLab CLI (glab) to manage GitLab issues, merge requests, CI/CD pipelines, repositories, and other GitLab operations from the command line. Use this skill when the user needs to interact with GitLab resources or perform GitLab workflows.

Create brand-safe content for athletes. Personal branding strategy, engagement optimization, crisis communication, sponsor integration.

Maintain project state across multiple conversations over days or weeks. Track tasks, decisions, blockers, and resources. Auto-update when a project is mentioned. Generate status reports and proactive reminders.

Assemble 2–3 complementary experts to collaboratively analyze anything. Experts work together to explore topics from multiple expert angles.

Analyze matchups, injuries, weather, Vegas lines. Recommend sit/start decisions with confidence levels for NFL, NBA, MLB, NHL, soccer.

FAQ identification from support tickets, step-by-step tutorial creation, screenshot/video script guidance, search optimization, and self-service deflection tracking.

Side-by-side stat comparisons with context. Adjust for era, pace of play, league differences. Advanced metrics explained in plain English.

Design sport-specific practice sessions. Drills by skill level and time, warm-up, skill work, scrimmage, cool-down.

Market salary research, accomplishment quantification, negotiation scripts, total compensation analysis, timing strategy.

Convert content between platforms (blog to Twitter thread, article to LinkedIn post, etc.). Optimize for each platform's format, tone, and best practices. Use when user wants to adapt content for different social media platforms.

Export a local Agent profile as a portable .akita-agent package file. Use when a user wants to share, back up, or distribute an Agent with its skills and configuration.

Compete against other AI agents in PROMPTWARS - a game of social engineering and persuasion.

API-first email platform designed for AI agents. Create and manage dedicated email inboxes, send and receive emails programmatically, and handle email-based workflows with webhooks and real-time events. Use when you need to set up agent email identity, send emails from agents, handle incoming email workflows, or replace traditional email providers like Gmail with agent-friendly infrastructure.