发现 AI Agent Skills

Crash-hunter skill for iOS 26 / Swift 6.2 clinic-architecture codebases that finds and fixes concurrency, memory, and I/O bugs using TDD. Covers data races, actor isolation, retain cycles, SwiftData context misuse, and sync-related failures in Domain/Data/App boundaries. Use when debugging crashes or hard-to-reproduce failures in ios-* and swift-* clinic modules.

Python project conventions for this codebase. Use when creating a new Python project, configuring Python tools (ruff, pyright, ty, pytest, bandit, vulture), writing or reviewing pyproject.toml, setting up Nx targets for Python, or asked about Python tooling setup, uv, or the language:python tag. Covers the project.json pattern, pyproject.toml structure, targetDefaults, tool execution via uv run, and ty pre-1.0 configuration rules.

Analyzes events through legal lens using statutory interpretation, case law analysis, legal reasoning, constitutional principles, and multiple legal frameworks (common law, civil law, international law). Provides insights on legal rights, obligations, liabilities, remedies, and compliance requirements. Use when: Legal disputes, contracts, regulations, compliance, rights analysis, liability assessment. Evaluates: Legal obligations, rights, liabilities, remedies, precedent, statutory authority, constitutionality.

Install and configure Apollo.io API authentication. Use when setting up a new Apollo integration, configuring API keys, or initializing Apollo client in your project. Trigger with phrases like "install apollo", "setup apollo api", "apollo authentication", "configure apollo api key".

Implement AI image generation capabilities using the z-ai-web-dev-sdk. Use this skill when the user needs to create images from text descriptions, generate visual content, create artwork, design assets, or build applications with AI-powered image creation. Supports multiple image sizes and returns base64 encoded images. Also includes CLI tool for quick image generation.

Expert knowledge for Azure Application Gateway development including troubleshooting, best practices, decision making, architecture & design patterns, limits & quotas, security, configuration, integrations & coding patterns, and deployment. Use when configuring App Gateway v2/Containers, WAF/TLS, AKS/AGIC ingress, Key Vault certs, or HTTP routing rules, and other Azure Application Gateway related development tasks. Not for Azure Load Balancer (use azure-load-balancer), Azure Front Door (use azure-front-door), Azure Virtual Network (use azure-virtual-network), Azure Web Application Firewall (use azure-web-application-firewall).

Framework for state-of-the-art sentence, text, and image embeddings. Provides 5000+ pre-trained models for semantic similarity, clustering, and retrieval. Supports multilingual, domain-specific, and multimodal models. Use for generating embeddings for RAG, semantic search, or similarity tasks. Best for production embedding generation.

Use when Elixir Ecto patterns including schemas, changesets, queries, and transactions. Use when building database-driven Elixir applications.

Unified Diary System: A context-preserving automated logger for multi-project development.

Fetch and summarize review comments from the active pull request

Home Assistant automation creation and management. Use when working with HA triggers, conditions, actions, scripts, scenes, or blueprints.

Fetch Bilibili (哔哩哔哩) video comments for UP主 self-analysis. Use when the user asks to collect, download, export, or analyze comments on a Bilibili video (BV号 / URL / UID). Produces JSONL + summary.json suitable for further Claude Code analysis (sentiment, keywords, audience trends). Read-only; does not post/edit/delete.

Diagnose React runtime performance with React Doctor traces, live render outlines, Long Animation Frames, interaction timing, and component render evidence. Use when invoked as `/performance` for a slow interaction, unexpected re-renders, or a measured before-and-after comparison.

Persistent SEO workflow for Claude Code — run a technical SEO audit, build a hub-and-spoke keyword strategy, write page-type-aware content briefs, and draft SEO-optimized articles, persisting every artifact to a .seoagent/ workspace so the work compounds across sessions. Use when auditing a site's technical SEO, planning a keyword/content strategy, writing content briefs, drafting SEO articles with structured data, or resuming SEO work started in a previous session.

Chooses the right Material UI styling approach (sx, styled, theme overrides, global CSS) from official MUI guidance. Use when styling @mui/material components, customizing themes, overriding slots, or comparing sx vs styled.

已废弃的叙事型 PPT/幻灯片生成器（2026-08-07 起停止维护，不再接收更新）。做新 deck 请用 deck-creator：本 skill 的方法论（First Law 用户原话优先 / ABCDEFG 叙事框架 / baoyu-slide-deck 委托协议 / 四层目录治理）已整体并入 deck-creator 的 Route A · narrative，装有 deck-creator 的环境不要调用本 skill。外部用户：这是保留安装兼容的最终版本，将在后续大版本中物理移除。

Design observability strategies: SLI/SLO frameworks, alerting, and dashboards. Use when instrumenting a production service, tuning alert rules, designing Grafana dashboards, defining SLOs and error budgets, or reducing alert fatigue.

Mendelian randomization (MR) causal inference — does an exposure, risk factor, or biomarker CAUSALLY affect a disease/outcome, using genetic variants as instrumental variables (IEU OpenGWAS / EpiGraphDB MR-EvE). Use this whenever the user asks if X causes Y, whether an observational association is actually causal or just correlation, if a biomarker/trait is a causal risk factor, wants to triangulate epidemiology against genetic evidence, or mentions Mendelian randomization, instrumental-variable analysis, two-sample MR, or genetic causal evidence — even if they never say "MR" (e.g. "is LDL cholesterol actually causal for heart disease?", "does BMI cause type 2 diabetes or just correlate?", "is CRP a causal driver of stroke?"). Covers trait-label resolution, MR effect direction/magnitude, instrument quality (MOE score), method agreement (IVW vs MR-Egger vs weighted median), bidirectional MR for reverse causation, and distinguishing causation from genetic correlation. Not for plain GWAS association lookups (use the GWAS skills) or fitting your own instruments from raw summary statistics.