d-wwei

Build institutional-grade comparable company analyses with operating metrics, valuation multiples, and statistical benchmarking in Excel/spreadsheet format. **Perfect for:** - Public company valuation (M&A, investment analysis) - Benchmarking performance vs. industry peers - Pricing IPOs or funding rounds - Identifying valuation outliers (over/under-valued) - Supporting investment committee presentations - Creating sector overview reports **Not ideal for:** - Private companies without comparable public peers - Highly diversified conglomerates - Distressed/bankrupt companies - Pre-revenue startups - Companies with unique business models

Build and maintain a calendar of upcoming catalysts across a coverage universe — earnings dates, conferences, product launches, regulatory decisions, and macro events. Helps prioritize attention and position ahead of events. Triggers on "catalyst calendar", "upcoming events", "what's coming up", "earnings calendar", "event calendar", or "catalyst tracker".

View or update the catalyst calendar — usage: /catalysts [timeframe, e.g. 'next 2 weeks']

Build a pre-earnings preview with scenarios — usage: /earnings-preview [company ticker]

Analyze quarterly earnings and create an earnings update report — usage: /earnings [company name or ticker] [quarter, e.g. Q3 2024]

Create an initiating coverage report — usage: /initiate [company ticker]

Update a financial model with new data — usage: /model-update [company ticker]

Draft a morning meeting note

Full browser control skill for AI agents. Multi-channel web access (search, fetch, Jina, CDP) with real Chrome session inheritance. Read, click, fill, upload, screenshot — including pages behind authentication. Three-layer safety system. Sub-agent parallel dispatch. Site experience memory. Auto-detects macOS, Windows, and Linux.

Search the public web and fetch page content as clean Markdown. Powered by omni-search-skill (optional companion). Provides search, fetch, resolve, and crawl operations.

Browser control with mode routing. /browse = auto-detect, /browse here = foreground (operate on the page user is looking at), /browse bg = background (CDP, no user disruption). Supports parallel sub-agent dispatch in bg mode.

Multi-agent orchestrator. Use when the current session should act as the Plan Agent for parallel worker agents across tmux/cmux sessions, with task splitting, worker spawning, daemon supervision, and merge orchestration.

Launch the hidden Apex Manager war-room easter egg in a separate terminal window without blocking the current agent session.

Better Work is a professional execution protocol for AI coding agents. Use when: (1) the task has failed 2+ times or the agent is looping on the same approach; (2) the agent is about to say 'I can't', suggest manual work too early, or blame environment/tooling without verification; (3) the task spans multiple steps, files, or sessions and needs lightweight planning/state tracking; (4) the agent is being passive by not searching, not reading source, not verifying, or waiting for the user to drive; (5) the user signals frustration like 'try again', 'dig deeper', 'verify it', 'make a plan', or similar. Applies to code, debugging, config, deployment, infra, research, APIs, writing, and analysis. Do NOT trigger on first-attempt failures or for tiny one-shot tasks that do not benefit from structure.

Better Work is a professional execution protocol for AI coding agents. Use when: (1) the task has failed 2+ times or the agent is looping on the same approach; (2) the agent is about to say 'I can't', suggest manual work too early, or blame environment/tooling without verification; (3) the task spans multiple steps, files, or sessions and needs lightweight planning/state tracking; (4) the agent is being passive by not searching, not reading source, not verifying, or waiting for the user to drive; (5) the user signals frustration like 'try again', 'dig deeper', 'verify it', 'make a plan', or similar. Applies to code, debugging, config, deployment, infra, research, APIs, writing, and analysis. Do NOT trigger on first-attempt failures or for tiny one-shot tasks that do not benefit from structure.

Universal writing skill for AI agents. 9 writing modes (tech articles, marketing copy, research reports, Xiaohongshu notes, technical docs, GitHub READMEs, creative writing, rewrite/polish, editorial review) + 9 core modules (research, core-finding, writing DNA, humanizer/polish, review, style learning, adaptation, SEO/GEO, writing memory, visualization). 6-phase pipeline with deep-thinking methodology. Bilingual (EN/ZH).

Invoke various LLMs (GLM-5, Kimi-k2.5, Llama 3.1, etc.) via NVIDIA NIM API to save main agent tokens and leverage specialized model capabilities.

通用深度学习助手。将任何内容（文档/URL/主题/粘贴文本）转化为结构化、自适应的完整学习系统。 核心特性：多源知识库构建（含质量过滤）、领域专家视角地图、模块化自适应教学、 概念解剖深挖模式、Make It Easier 模式、三步错题诊断、间隔复习系统、进度持久化、成就激励。 适用于任何 AI Agent（Claude Code, Codex, Gemini, OpenClaw 等）。 子命令：resume（继续上次）、go over（复习到期）、concept/dissect/概念解剖 <概念>、<主题/URL/文件> 新建学习。

Use when an article needs illustrations, diagrams, or images. Analyzes article content, identifies illustration points, routes to the best engine (Mermaid, D2, AI generation, stock photos, HTML rendering), and generates or searches for matching visuals. Standalone or integrated as a stage in great-writer pipeline.

End-to-end road trip and travel itinerary planner that produces navigation-ready guides. Use this skill whenever the user asks to plan a road trip, self-drive tour, multi-day driving itinerary, or travel route — even if they just mention a destination and dates. Also trigger when the user asks for driving directions between multiple stops, wants to optimize a travel route, or needs a day-by-day travel guide with navigation links. Covers route planning, driving time verification, holiday/closure checks, parking details, weather forecasting, cultural-layer research, pre-trip homework recommendations. Generates markdown documents, interactive HTML guides with embedded Leaflet maps, and shareable PNG portable cards for offline IM sharing.

认知底座的包管理器。搜索、安装、更新、卸载认知底座——给 AI agent 安装认知义体的一站式工具。

Interview-first PRD skill with integrated product validation. Use when the user asks to write, refine, review, or structure a PRD / 产品需求文档, make a product decision ("要不要做这个"), plan a new feature, or evaluate a product idea. Triggers: "写 PRD", "做需求文档", "要不要做XX", "写个 PRD", "产品决策", "新功能规划", "市场分析", "优化这份 PRD", "把 MRD 转成 PRD", "先访谈再写需求".

Content creation pipeline orchestrator for any AI agent. Chains great-writer -> brilliant-visualizer -> typeset -> deliver into a complete write-to-deliver flow. Optional multi-platform publishing via /publish skill (superb-publisher). Loose coupling: depends only on skill names and I/O contracts, not sub-skill internals. Works with Claude Code, Codex, Gemini CLI, and any agent that supports skill loading.