发现 Skills
为真实工作流程挑选经过整理的 Skill,连接、安装并开始使用。
python-ddd
Domain-Driven Design patterns for Python — aggregates, value objects, repositories, domain events, CQRS, and application services. Async-first with Pydantic v2 and SQLAlchemy 2.0.
python-messaging
Async messaging and middleware patterns for Python — in-process events, background tasks, Redis queues, Celery, Redis Streams, and Kafka. Graduated complexity from simple to enterprise scale.
security-baseline
OWASP-aware secure coding awareness. Provides security rules, common vulnerability patterns, and safe coding practices adapted to the project's language and framework.
trellis-bootstrap
Initialize Trellis AI workflow system in a project. Use when user mentions "Trellis", "initialize Trellis", "setup Trellis", "install Trellis", or wants to add AI-assisted development workflow to their project. This is a one-time setup skill.
internationalization-i18n
Implement internationalization (i18n) best practices for web and mobile applications to support multiple languages and locales.
monorepo
Best practices for developing monorepos with TypeScript, React, Next.js, Expo, Turborepo, and related technologies
check-app-stats
このアプリの利用統計を確認(Cognitoユーザー数、AgentCore呼び出し回数、Bedrockコスト、Tavily API残量)
ai-search-hub
Run the AI Search Hub browser automation scripts for Yuanbao, LongCat, Doubao, Qwen, Gemini, and Grok. Use this skill when the user wants to ask one of those sites a prompt, auto-start or attach to a Chrome DevTools session on port 9222, seed an isolated debug browser profile from the user's local browser data, detect whether login is required, wait for the user to finish logging in if needed, and then continue automatically.
swiftui-architecture
WHEN building SwiftUI views, managing state, setting up shared services, or making architectural decisions; NOT for UIKit or legacy patterns; provides pure SwiftUI data flow without ViewModels using @State, @Binding, @Observable, and @Environment.
eg-contrib-translate
Step-by-step guide to implement Gateway API to IR and IR to xDS translation for a new feature in envoyproxy/gateway
eg-route
Create routing rules for HTTP, gRPC, TCP, or UDP traffic
review
Reviews code changes for complexity and simplification opportunities. Use before creating PRs or when reviewing changesets.
pygame-graphics-testing
Patterns for testing pygame-based graphics and visual output
long-running-tasks
Orchestrate multi-phase background development using coding agents (Codex, Claude Code). Use when a project requires continuous autonomous work across multiple tasks/phases — spawning workers, detecting stalls, recovering from failures, and reporting progress. Solves the "fire-and-forget" problem where one-shot agent sessions finish and nobody spawns the next task.
primeng-developer
Generates PrimeNG code and guidance for Angular projects using `primeng` with `@primeuix/themes` and `@primeuix/styles`. Covers installation, design-token theming (Aura / Lara / Nora / Material presets), Styled vs Unstyled modes, the PassThrough (`pt`) customization API, component usage across all categories (form controls, buttons, overlays, layout, data display, display, menus), ReactiveForms / Signal Forms integration, accessibility, and v18→v21 migration renames. Use when the user mentions PrimeNG, `primeng`, `p-*` components, Aura/Lara/Nora theme presets, OR when the Angular project's `package.json` contains `primeng` or `@primeuix/*` dependencies. Pairs with `angular-developer` for Angular fundamentals.
flamegraphs
Flamegraph generation and interpretation skill. Use when converting perf, Valgrind Callgrind, or other profiler output into SVG flamegraphs using Brendan Gregg's FlameGraph tools, or when reading flamegraphs to identify performance bottlenecks. Activates on queries about flamegraphs, stackcollapse, flamegraph.svg, identifying hot frames, wide vs tall frames, or performance visualization.
mijia-control
Control and monitor Xiaomi Mijia smart home devices. Use this skill when the user wants to: 1) Switch device status (on/off, brightness, etc.) 2) List available home devices 3) Run automation scenes 4) Check environmental statistics.
skill-finder
Helps users discover and install agent skills from the open skills ecosystem (skills.sh). Use when users ask 'how do I do X', 'find a skill for X', 'is there a skill that can...', want to search for tools/templates/workflows, or express interest in extending agent capabilities.
sql-optimization-patterns
Master SQL query optimization, indexing strategies, and EXPLAIN analysis to dramatically improve database performance and eliminate slow queries. Use when debugging slow queries, designing database schemas, or optimizing application performance.
security
API security expertise including authentication, authorization, OWASP compliance, and vulnerability detection.
sql
Expert SQL development with focus on query optimization, indexing strategies, and data modeling.
detect-s3-cross-account-copy
Detect successful AWS S3 cross-account object copies from OCSF 1.8 API Activity records emitted by ingest-cloudtrail-ocsf. Emits an OCSF 1.8 Detection Finding (class 2004) tagged with MITRE ATT&CK T1537 (Transfer Data to Cloud Account) when a principal from one AWS account performs a successful S3 `CopyObject` into a bucket owned by another account. Use when the user mentions "S3 cross-account copy", "cross-account CopyObject", "AWS exfil to another cloud account", or "T1537 via CloudTrail". Do NOT use as a generic S3 object-write detector, to infer every exfiltration path, or to claim all cross-account storage movement is covered.
detect-system-prompt-extraction
Detect MCP tool-call responses that look like leaked system-prompt or hidden instruction material from native or OCSF Application Activity records emitted by ingest-mcp-proxy-ocsf. Emits an OCSF 1.8 Detection Finding (class 2004) tagged with MITRE ATLAS AML.T0004 / AML.T0041 when a `tools/call` response contains explicit system-prompt markers such as `<system_prompt>`, "You are ChatGPT", "developer message", or "hidden instructions". Use when the user mentions "system prompt leakage", "prompt extraction", "hidden instructions exposed", or "LLM07 via MCP". Do NOT use for generic jailbreak language, semantic prompt leakage claims, or tool-description inspection.
mthds-explain
Explain and document MTHDS bundles. Use when user says "what does this pipeline do?", "explain this workflow", "explain this method", "walk me through this .mthds file", "describe the flow", "document this pipeline", "how does this work?", or wants to understand an existing MTHDS method bundle.