发现 Skills

Expert search specialist mastering advanced information retrieval, query optimization, and knowledge discovery. Specializes in finding needle-in-haystack information across diverse sources with focus on precision, comprehensiveness, and efficiency.

Automated test-data construction capability. Supports three input modes: Traditional mode (based on api_definitions.json interface definitions), Specification mode (based on team custom field rules), and Natural Language mode (based on natural-language descriptions, Faker-driven). Automatically generates test data covering four dimensions — positive, boundary, negative/exceptional, and security — and supports output formats YAML/JSON/Excel/CSV.

This skill should be used when the user asks to "audit page SEO", "on-page SEO check", "SEO score", "page optimization", "what SEO issues does this page have", "what is wrong with this page SEO", "score my page", or "why is this page not ranking". Performs comprehensive on-page SEO audits to identify optimization opportunities including title tags, meta descriptions, headers, content quality, internal linking, and image optimization. For server, speed, and crawl issues, see technical-seo-checker. For full EEAT content quality scoring, see content-quality-auditor.

Use this skill when a user asks to add schema markup, generate structured data, produce JSON-LD, create rich snippets, or requests FAQ schema, HowTo schema, Product schema, Article schema, LocalBusiness schema, Organization schema, BreadcrumbList, star ratings in Google, rich results, voice search optimization, event markup, or help with structured data validation errors. Generates Schema.org JSON-LD for FAQPage, HowTo, Article/BlogPosting, Product, AggregateRating, LocalBusiness, Organization, BreadcrumbList, Event, and Recipe types. Produces validated markup targeting Google Rich Results, Bing structured data, and AI system understanding (FAQ schema can improve AI citation chances). Validates against Google Rich Results Test requirements. For broader technical SEO, see technical-seo-checker. For meta tag optimization, see meta-tags-optimizer.

Use when testing argument hints

OpenAI Codex CLI orchestration for AI-assisted development using the gpt-5.3-codex model family. Model variants: gpt-5.3-codex (medium), gpt-5.3-codex-high, gpt-5.3-codex-xhigh. Capabilities: code generation, refactoring, automated editing, parallel task execution, session management, code review, architecture analysis, and Context7 MCP integration. Actions: analyze, implement, review, fix, refactor with Codex. Keywords: Codex CLI, gpt-5.3-codex, codex exec, code generation, refactoring, parallel execution, session resume, code review, second opinion, independent review, architecture validation, Context7 MCP. Use when: delegating complex code tasks to Codex, running multi-agent workflows, executing automated reviews, implementing features with AI assistance, resuming previous sessions, or querying OpenAI documentation. Triggers: 'use codex', 'codex exec', 'run with codex', 'codex resume', 'implement with codex', 'review with codex', 'codex docs'.

Analyze marketing performance with key metrics, trend analysis, and optimization recommendations. Use when building performance reports, reviewing campaign results, analyzing channel metrics (email, social, paid, SEO), or identifying what's working and what needs improvement.

Use this skill when a user asks to 'remove AI writing patterns', 'humanize this text', 'make this sound more natural', 'remove AI-generated traces', 'fix robotic writing', or otherwise eliminate AI writing patterns from prose. Supports both English and Chinese text. Based on Wikipedia's 'Signs of AI writing' guide, it detects and fixes inflated symbolism, promotional language, superficial -ing analyses, vague attributions, AI-specific vocabulary, negative parallelisms, and excessive conjunctive phrases.

When the user wants to research, profile, or analyze competitors from their URLs. Also use when the user mentions 'competitor profile,' 'competitor research,' 'competitor analysis,' 'profile this competitor,' 'analyze competitor,' 'competitive intelligence,' 'competitor deep dive,' 'who are my competitors,' 'competitor landscape,' 'competitor dossier,' 'competitive audit,' or 'research these competitors.' Input is a list of competitor URLs. Output is structured competitor profile markdown files. For creating comparison/alternative pages from profiles, see competitor-alternatives. For sales-specific battle cards, see sales-enablement.

When the user wants to optimize, improve, or increase conversions on any marketing page — including homepage, landing pages, pricing pages, feature pages, or blog posts. Also use when the user says "CRO," "conversion rate optimization," "this page isn't converting," "improve conversions," "why isn't this page working," "my landing page sucks," "nobody's converting," "low conversion rate," "bounce rate is too high," "people leave without signing up," or "this page needs work." Use this even if the user just shares a URL and asks for feedback — they probably want conversion help. For signup/registration flows, see signup-flow-cro. For post-signup activation, see onboarding-cro. For forms outside of signup, see form-cro. For popups/modals, see popup-cro.

图片分析与识别，可分析本地图片、网络图片、视频、文件。适用于 OCR、物体识别、场景理解等。当用户发送图片或要求分析图片时必须使用此技能。

Use this skill when adding authentication, handling user input, working with secrets, creating API endpoints, or implementing payment/sensitive features. Provides a comprehensive security checklist and proven patterns.

Test-Driven Development (TDD) workflow principles. RED→GREEN→REFACTOR cycle.

Master network protocol reverse engineering including packet analysis, protocol dissection, and custom protocol documentation. Use when analyzing network traffic, understanding proprietary protocols, or debugging network communication.

Design and implement algorithmic trading strategies with entry/exit rules, position sizing, and risk parameters

Get real-time crypto buy/sell activity from Smart Money wallets, KOL influencer wallets, and personally followed wallets via GMGN API — alpha signals, whale tracking, meme token copy-trading ideas on Solana, BSC, or Base. Use when user asks what smart money or KOLs are buying, wants whale alerts, on-chain alpha, or copy-trade signals. (For a specific wallet address, use gmgn-portfolio.)

Find and identify the CNetworkGameServer global pointer and CServerSideClientBase_ClientPrintf virtual function in CS2 binary using IDA Pro MCP. Use this skill when reverse engineering CS2 server.dll or libserver.so to locate the CNetworkGameServer instance by searching for the "tried to sprint to a non-client" debug string reference and analyzing the function that validates client slot indices and calls ClientPrintf via vtable.

Security standards for Flutter applications based on OWASP Mobile. Use when applying OWASP Mobile security standards or when securing a Flutter application.

Extract formatting from existing Word documents and generate new documents with the same format but different content. Use this skill when users need to create multiple documents with consistent formatting, replicate document templates, or maintain corporate document standards across different content.

The orchestration layer for AI-native creative production. This skill coordinates multiple AI tools—video, image, audio, digital humans, effects—into cohesive campaigns, productions, and creative systems. As AI tools proliferate, the challenge shifts from "can we create this?" to "how do we orchestrate these capabilities into something coherent?" The AI Creative Director thinks in systems, not tools. In pipelines, not one-offs. In brand consistency across AI-generated assets. This is where creative vision meets technical orchestration. The AI Creative Director doesn't just use AI tools—they compose them into creative instruments that produce at scales and speeds previously impossible. Use when "AI creative director, orchestrate AI, AI campaign, multi-tool, AI workflow, AI pipeline, coordinate AI, AI production, AI creative system, full AI production, AI at scale, orchestration, creative-direction, ai-production, workflow, pipeline, multi-tool, scale, quality-control" mentioned.

Transform vague feature ideas into clear, testable requirements using EARS format. Capture user stories, define acceptance criteria, identify edge cases, and validate completeness before moving to design.

Comprehensive L&D framework for upskilling DevOps/IaC/Automation teams to become AI Agent Engineers. Covers LLM literacy, RAG, agent frameworks, multi-agent systems, and LLMOps. Designed to help traditional automation teams compete with OpenAI and Anthropic.

Python library for accessing, analyzing, and extracting data from SEC EDGAR filings. Use when working with SEC filings, financial statements (income statement, balance sheet, cash flow), XBRL financial data, insider trading (Form 4), institutional holdings (13F), company financials, annual/quarterly reports (10-K, 10-Q), proxy statements (DEF 14A), 8-K current events, company screening by ticker/CIK/industry, multi-period financial analysis, or any SEC regulatory filings.

McKinsey-style PowerPoint presentation design framework with Python-pptx automation. Creates consultant-grade decks from scratch using a comprehensive design system including typography hierarchy, color palettes, layout patterns, and line treatments. Trigger when users need professional presentations, slide decks, or pitch materials.