AI Skills

Home Assistant automations, scripts, and blueprints. Use when the user requests automation/script syntax, triggers/conditions/actions, blueprint usage, run modes, or troubleshooting, and when mapping those needs to ha-mcp automation/script tools.

MCP 服务器构建方法论 — 系统化构建生产级 MCP 工具，让 AI 助手连接外部能力

Build complete call graphs with GrepAI trace. Use this skill for recursive dependency analysis.

>

Code refactoring expert for improving code structure, readability, and maintainability. Use when user asks to refactor, clean up, or improve code quality.

Web crawling and scraping tool with LLM-optimized output. 网页爬虫爬取工具 | Web crawler, web scraper, spider. DuckDuckGo search, site crawling, dynamic page scraping. 智能搜索爬取 | Free, no API key required.

Memory is the cornerstone of intelligent agents. Without it, every interaction starts from zero. This skill covers the architecture of agent memory: short-term (context window), long-term (vector stores), and the cognitive architectures that organize them. Key insight: Memory isn't just storage - it's retrieval. A million stored facts mean nothing if you can't find the right one. Chunking, embedding, and retrieval strategies determine whether your agent remembers or forgets. The field is fragm

Web search using Tavily's LLM-optimized API. Returns relevant results with content snippets, scores, and metadata.

MongoDB development guidelines with Payload CMS, Mongoose, aggregation pipelines, and TypeScript best practices.

Apple Human Interface Guidelines for Apple Watch. Use when building watchOS apps, complications, or workout features. Triggers on tasks involving Watch UI, Digital Crown, glanceable interfaces, or wrist-based interactions.

>

When the user wants to plan, brief, source, or measure organic creator / influencer / UGC marketing for their app — including TikTok creators, Instagram Reels, YouTube Shorts, micro-influencers, paid creator briefs, UGC ad creative for Meta/TikTok, affiliate programs, and seeding strategy. Use when the user mentions "creators", "influencers", "TikTok marketing", "UGC", "user-generated content", "creator briefs", "creator outreach", "influencer marketing", "Reels", "Shorts", "creator gifting", "seeding", "affiliate", "Whop", "TikTok Spark Ads", "Instagram collab posts", or "I want my app to go viral on TikTok". For paid social ad campaigns (Meta/TikTok ad accounts), see ua-campaign. For PR / press, see press-and-pr. For viral in-app loops, see referral-program.

Create custom tools for Vapi voice assistants including function tools, API request tools, transfer call tools, end call tools, and integrations with Google Calendar, Sheets, Slack, and more. Use when adding capabilities to voice agents, building tool servers, or integrating external APIs.

Fetches issue context, auto-detects task type, maps to branch prefix, presents brief.

>

Generate and prioritize US equity long-side edge research tickets from EOD observations, then export pipeline-ready candidate specs for trade-strategy-pipeline Phase I. Use when users ask to turn hypotheses/anomalies into reproducible research tickets, convert validated ideas into `strategy.yaml` + `metadata.json`, or preflight-check interface compatibility (`edge-finder-candidate/v1`) before running pipeline backtests.

Use when designing Kotlin Multiplatform expect/actual or interface boundaries for platform services, native SDKs, source sets, Compose Multiplatform UI, permissions, files, settings, sensors, or platform interop.

Use when planning or executing authorized red team engagements, attack path analysis, or offensive security simulations. Covers MITRE ATT&CK kill-chain planning, technique scoring, choke point identification, OPSEC risk assessment, and crown jewel targeting.

Agent skill from steelan9199/wechat-publisher.

Automate Instagram tasks via Rube MCP (Composio): create posts, carousels, manage media, get insights, and publishing limits. Always search tools first for current schemas.

Build high-performance async APIs with FastAPI, SQLAlchemy 2.0, and Pydantic V2. Master microservices, WebSockets, and modern Python async patterns.

Perform AI-powered web searches with real-time information using Perplexity models via LiteLLM and OpenRouter. This skill should be used when conducting web searches for current information, finding recent scientific literature, getting grounded answers with source citations, or accessing information beyond the model's knowledge cutoff. Provides access to multiple Perplexity models including Sonar Pro, Sonar Pro Search (advanced agentic search), and Sonar Reasoning Pro through a single OpenRouter API key.

Warning system for identifying potentially malicious software distribution repositories

Screen post-earnings gap-up stocks for PEAD (Post-Earnings Announcement Drift) patterns. Analyzes weekly candle formation to detect red candle pullbacks and breakout signals. Supports two input modes - FMP earnings calendar (Mode A) or earnings-trade-analyzer JSON output (Mode B). Use when user asks about PEAD screening, post-earnings drift, earnings gap follow-through, red candle breakout patterns, or weekly earnings momentum setups.

Scans HubSpot for stale deals, duplicate contacts, and missing fields, then fixes what the owner approves. Accepts optional scope argument for deals, contacts, or all.

Validate data quality in market analysis documents and blog articles before publication. Use when checking for price scale inconsistencies (ETF vs futures), instrument notation errors, date/day-of-week mismatches, allocation total errors, and unit mismatches. Supports English and Japanese content. Advisory mode -- flags issues as warnings for human review, not as blockers.

Research prediction markets as data sources or oracle signals for products, agents, dashboards, and corporate decision intelligence. Use for source-grounded analysis of market-implied probabilities, caveats, and integration patterns without investment advice.

Interact with the Cargo platform via CLI. Use when the user wants to execute an action, run a workflow, trigger a batch, message an AI agent, query orchestration runtime tables (runs/batches/spans/records) with SQL, fetch segment records, or inspect a model schema.

Download workflow run results, export segment data, and monitor run metrics using the Cargo CLI. Use when the user wants run metrics, error rates, data export, or download results for their Cargo workspace. For billing and credit usage, use the cargo-billing skill instead.

Crafts high-converting outreach messages and email sequences for cold outreach, LinkedIn DMs, and follow-ups. Use when user needs personalized outreach messages that book calls and get replies.