发现 Skills

Socket.io rooms, namespaces, adapters, middleware, and real-time patterns.

Apply LDA, NMF, and other computational methods to discover patterns in large text corpora with appropriate parameter tuning

OWASP Top 10, security headers, CSP, XSS prevention, and vulnerability prevention.

Generate XAML styles, templates, and resource dictionaries with theme support for WPF applications

Script Creation - Short-video script writing and storyboard design Responsibilities: Produce content based on viral templates; design golden 3-second opening plans (3+ variants); write storyboard scripts (including shot language / scene atmosphere / character actions / dialogue / BGM); design punchlines/hooks and emotional hooks; plan ending guidance; automatically recommend Vidu video generation configurations (model version / generation method / duration / aspect ratio); ensure consistency of character appearance; deliver complete storyboard information to video generation (Leo). Applicable scenarios: (1) Short-video script writing (2) Storyboard design (3) Content creation (4) Video planning

> v6 core: Polymarket market probabilities + Binance "Square" news = integrated directional judgment. Both YES and NO can be bought.

You are a Quant. Perform a full morning inventory and produce a daily positions report.

Orchestration Protocol v4.2 for coding tasks. Non-blocking, event-driven architecture with persistent tmux sessions. Use for implementing features, fixing bugs, refactoring code, building components, creating PRs, or other development work that requires continuous runtime and automation. Trigger phrases include: run-by-protocol, task-card, orchestration, follow-workflow, development, implement, build, refactor, fix-bug, and bugfix. Not intended for code reading, quick questions, or configuration changes that take under 15 minutes.

Automatic generation and cleanup of CPA authentication files

This is an example of a project-specific skill. Use this as a template for your own project.

Load when user says "archive project", "archive [project-name]", "move to archived". Moves completed projects to 05-archived/ folder for clean project list.

Skill activation engine that ensures relevant marketplace skills are invoked for every task. TRIGGER WHEN: ALWAYS at conversation start and before every task. DO NOT TRIGGER WHEN: dispatched as a subagent.

Render a mindmap JSON outline into Obsidian MarkMind Rich format. Use this skill after generating a mindmap outline (via generate-mindmap or any other source) to convert it into a .md file ready for the Obsidian MarkMind plugin. TRIGGER WHEN: the user says 'markmind', 'render to markmind', or needs MarkMind Rich output from an existing mindmap JSON structure. DO NOT TRIGGER WHEN: the user wants an interactive HTML mindmap (use forcegraph-exporter) or a plain text outline.

You MUST use this before ANY creative or implementation work -- creating features, building components, adding functionality, modifying behavior, or any non-trivial task. Explores user intent, requirements and design before implementation. A conversation that starts as a question but progresses into "which approach should we take?" or "here's the architecture" IS a brainstorming session and MUST invoke this skill before any implementation begins. DO NOT TRIGGER WHEN: (1) user says 'brainstorm', 'design', 'build', 'create', 'add', 'implement', 'develop', 'make', or gives any task involving new code; (2) the conversation has evolved into architectural discussion -- comparing approaches, evaluating trade-offs, drawing architecture diagrams, making technology choices, or discussing how components connect -- even if no explicit trigger word was used. A conversation that starts as a question but progresses into "which approach should we take?" or "here's the architecture" IS a brainstorming session and MUST invoke this skill before any implementation begins. DO NOT TRIGGER WHEN: user has a spec/plan ready, is fixing a specific bug, or doing a one-line change.

Analyze staged git changes and generate conventional commit messages with correct type prefixes (feat, fix, chore, refactor, docs, test, style, perf, ci, build). Handles monorepo scopes by detecting package/workspace boundaries. Use when writing commit messages, committing code, preparing git commits, or when the user mentions conventional commits, commit message formatting, or needs help describing their changes for version control.

Used to diagnose whether a company's profitability meets required standards. Activated when a user discusses profit targets, performance benchmarking, or scaling success criteria. Not applicable to: pure information queries (e.g., "What is the industry average profit margin?"), or questions about basic financial concepts. Key triggers: mentions of profit margin, profitability gap, scaling standards, or benchmarking competitors.

Concatenates a project's or workspace's documentation (.md files in the /docs directory) and agent configuration (the .agent directory) for NotebookLM.

Use when reviewing code for anti-patterns. Keywords: anti-pattern, common mistake, pitfall, code smell, bad practice, code review, is this an anti-pattern, better way to do this, common mistake to avoid, why is this bad, idiomatic way, beginner mistake, fighting borrow checker, clone everywhere, unwrap in production, should I refactor

Acuris EUDI Wallet Verifier — a hosted OID4VP relying-party service at https://eudi.acuris-geo.com that accepts EU Digital Identity Wallet presentations (SD-JWT VC PID), validates the credential against EU 27 member-state trust lists (LOTL → TSL → x5c → CRL), and cross-checks the disclosed residence address against Acuris's address-validation pipeline. Use when the user is integrating EUDI Wallet verification into a bank KYC / branch onboarding flow, building a relying-party backend that initiates verification sessions and polls for results, generating OID4VP presentation_definitions, handling SD-JWT VC responses, or interpreting verification_status, accuracy_type, and credential_validity in poll responses.

Use when you have a spec or requirements for a multi-step task, before touching code

Safely restructure code without changing behavior. Use when refactoring, cleaning up code smells, or improving code quality.

Build document analysis applications using the Azure AI Document Intelligence SDK for Java.

To access Anthropic's official brand identity and style resources, use this Skill.

Specialized skill for building production-ready Discord bots. Covers Discord.js (JavaScript) and Pycord (Python), gateway intents, slash commands, interactive components, rate limiting, and sharding.