发现 Skills

Explain Solana AMM liquidity, slippage, volatility, and LP mechanics for tokens. Use to brief teams or design initial liquidity.

This skill should be used when the user asks to "design multi-agent system", "implement supervisor pattern", "create swarm architecture", "coordinate multiple agents", or mentions multi-agent patterns, context isolation, agent handoffs, sub-agents, or parallel agent execution.

Relay messages to AI agents on any OpenAI-compatible API. Supports multi-turn conversations with session management. List agents, send messages, reset sessions.

Search and retrieve ServiceNow documentation, release notes, and developer docs (APIs, references, guides). Uses docs.servicenow.com via Zoomin and developer.servicenow.com APIs for developer topics.

Build agentic AI applications with OpenAI's Responses API - the stateful successor to Chat Completions. Preserves reasoning across turns for 5% better multi-turn performance and 40-80% improved cache utilization. Use when: building AI agents with persistent reasoning, integrating MCP servers for external tools, using built-in Code Interpreter/File Search/Web Search, managing stateful conversations, implementing background processing for long tasks, or migrating from Chat Completions to gain polymorphic outputs and server-side tools.

Write JavaScript/TypeScript for business applications (frontend and backend) with CRUD, API integration, and data transforms that are correct, readable, and easy to trust. Use when building or reviewing features involving forms, API responses, list/detail views, aggregations, or request/response shaping so outputs need minimal inspection.

Final verification against spec with full evidence chain. Use after sdlc-execute to confirm feature is complete.

Next.js development tooling via MCP. Inspect routes, components, build info, and debug Next.js apps. Use when working on Next.js applications, debugging routing, or inspecting app structure. NOT for general React or non-Next.js projects.

Look up CE.SDK Vanilla JavaScript reference docs, guides, and configuration pages. Use when the user needs CE.SDK docs for Vanilla JavaScript — configuration, UI customization, export options, feature guides, or getting-started instructions. Also triggered by "IMG.LY", "CreativeEditor", "CE.SDK", or "cesdk" when the user needs an existing Vanilla JavaScript doc page. Not for writing code (use build) or concept explanations (use explain). <example> Context: User asks about Vanilla JavaScript configuration user: "How do I configure the editor in Vanilla JavaScript?" assistant: "I'll use /cesdk:docs-js to look up configuration options." </example> <example> Context: User needs vanilla JS setup user: "How do I use CE.SDK without a framework?" assistant: "Let me use /cesdk:docs-js to find the relevant documentation." </example>

A professional skill for App Evaluation (evaluating app's performance with score) and App Improvement (giving professional suggestions for improving the app's performance).

Guide for creating, managing, and using Claude Code Agent Skills. Use when the user asks about Skills, wants to create a new Skill, or needs help with SKILL.md files.

When the user wants to set up, improve, or audit analytics tracking and measurement. Also use when the user mentions "set up tracking," "GA4," "Google Analytics," "conversion tracking," "event tracking," "UTM parameters," "tag manager," "GTM," "analytics implementation," or "tracking plan." For A/B test measurement, see ab-test-setup.

Use when block order in a single file obscures the public surface or disrupts top-down comprehension. Goal: file structure exposes the public surface first and supporting details in a clear top-down flow without behavior change.

After Effects automation through the Model Context Protocol. Use when users request creating, modifying, or animating content in Adobe After Effects, including compositions, layers, keyframes, effects, expressions, text animations, lower thirds, title cards, logo reveals, or any motion graphics tasks. Trigger on phrases like "create in After Effects", "animate this", "make a motion graphic", "add keyframes", "apply effects", or when users mention AE-specific concepts like compositions, precomps, expressions, or time remapping.

Monitor WhatsApp Web for important messages and create action files in the AI Employee vault.

End-to-end PowerPoint presentation generator. Use whenever the user wants to create, edit, or export a .pptx file, convert to PDF, add watermarks/logos/footers, apply brand templates, build a slide deck from any content, generate charts/diagrams, fetch stock images, or add animations/transitions. Trigger on: "make a presentation", "create slides", "generate pptx", "make a deck", "export to pdf", "add watermark", "college logo on slides", "apply template", "slide deck for report", "add chart", "generate diagram", "add image", "add animations", "/slidify", or any request involving .pptx files. Always use this skill — never generate pptxgenjs/python-pptx code from memory without it.

Generate a vertical story image for TikTok or Instagram book promotion with cover art, hook text, and author branding.

Scan repository agent configuration files for known malicious patterns

Use when encountering Swift 6 concurrency errors, Sendable conformance warnings, actor isolation issues, "global variable is not concurrency-safe" errors, or migrating codebases to Swift 6 language mode

Manage Synology NAS via direct API calls: Download Station (add/pause/resume/delete torrents, magnets, URLs), File Station (browse folders, create folders, file info), and RSS Feeds (list, view items, download). Use when managing downloads on a Synology NAS or browsing NAS files.

Invoke this skill when building any Deep Agents application. Covers create_deep_agent(), harness architecture, SKILL.md format, and configuration options.

INVOKE THIS SKILL at the START of any LangChain/LangGraph/Deep Agents project, before writing any agent code. Determines which framework layer is right for the task: LangChain, LangGraph, Deep Agents, or a combination. Must be consulted before other agent skills.

Use when reasoning about the consistency-availability-partition-tolerance trade-off for distributed data systems: Brewer's CAP conjecture (2000), Gilbert & Lynch's 2002 formal proof, why P is not optional in any real distributed system, the CP-vs-AP dichotomy that follows, PACELC as the extension that names the latency-vs-consistency trade-off that exists even without partition, the relationship between CAP's C and ACID's C (different concepts with the same letter), and the choice procedure of naming what the system must guarantee under partition. Do NOT use for single-node transactional guarantees (use acid-fundamentals), choosing an isolation level (use transaction-isolation), the design of replication topologies (use replication-patterns), or sharding decisions (use sharding-strategy).

Master Anthropic's prompt engineering techniques to generate new prompts or improve existing ones using best practices for Claude AI models.