XXE
13-Dimension Book Breakdown
Based on the book content, excerpts, or reading notes you provide, this Skill deeply breaks down a book across 13 dimensions—from its origins and context to transfer and internalization. It guides the full process of understanding, critique, reconstruction, and internalization, turning the author’s knowledge into your own.
Deep Critical Analysis
Deliver high-quality critical analysis of any viewpoint: strengthen both sides of the argument through steelmanning, distinguish facts from value judgments, balance inductive and deductive reasoning, and reconstruct ideas from first principles. Conclude with a careful assessment that includes confidence levels, conditions of applicability, and questions that still need to be verified. Supports short viewpoints as well as long-form text or file input, with online search available to strengthen the factual basis.
Plain-Language Visual Guide
Break down the core principles of any complex topic into plain language that anyone can understand at a glance. Use only familiar, everyday things as analogies—no jargon, English abbreviations, or abstract concepts. The final output is a colorful visual explainer page centered on large graphics with very little text.
Structured Image Master
Converts user input natural language character or scene descriptions into structured image/video generation prompts (JSON format). When users describe a character, person, advertising image, video protagonist, or say 'generate a prompt for me', 'convert to image generation format', 'I want to generate a character', 'write an image generation prompt', this skill must be used. Even if the user description is brief, it should proactively complete and output a full structured prompt. It is recommended to use with Image2 for better results!
AI Video Director
Automatically expands plain-language descriptions of video and image scenes into director-level structured prompts for generation tools such as Seedance 2.0, Runway, Luma, Pika, Kling, and Stable Diffusion. This Skill must be triggered whenever the user mentions "generate a video," "video prompt," "video storyboard," "continue the scene," or "keep the character consistent," mentions "Seedance," "Runway," "Kling," or "Luma," or describes any video or image scene they want to generate. It should also be triggered when the user simply says "help me generate an XX image" or "a video of an XX scene."
WriteIn-Depth Business Feature Writer
A deep-writing skill for founder interviews, company case studies, profile features, and industry reporting. It does more than simply polish your draft—it recreates the full reporting and writing workflow used by professional media: diagnosing source materials, identifying follow-up interview needs, researching background, verifying facts, shaping the structure, planning visuals, and writing the article. The final deliverable is a complete long-form content package suitable for WeChat Official Accounts or media publication, including the article, headline, summary, condensed version, fact-checking notes, and cover and illustration concepts. It’s designed for creators and teams who need to turn interview notes, research materials, or scattered information into a professional, measured, insight-driven business feature.
English Document Deep Dive
Intelligent adaptive translation and in-depth analysis for highly specialized English documents. Automatically identifies the document type and level of specialization, then selects an efficient basic mode or an advanced deep-analysis mode. Covers complete translation, authoritative web-based fact-checking, structured extraction, professional interpretation, and multiple rounds of final review and proofreading—aiming to stay 100% faithful to the original meaning, maintain consistent terminology, minimize errors and omissions, and meet professional standards. **Risk notice:** This tool uses AI for automated information processing and generation. Although it is governed by strict rules and review procedures, the risks of model misjudgment, missing information, and “hallucinations” cannot be completely eliminated. All outputs are provided for reference only. For high-risk decisions involving legal matters, compliance, investment and financing, medicine, or similar areas, always verify the output against the original text and have a qualified professional conduct the final review and confirmation.
WriteCreate Great Lateral Puzzles
A systematic engine for creating lateral-thinking puzzles, built around 8 mechanism templates, 5 narrative structures, and a routing workflow. It covers everything from building a complete cause-and-effect solution first to designing misdirection and breaking down clues, with difficulty controls and ethical guardrails for a professional-grade creative process that supports batch generation, interactive co-creation, and diagnostic refinement. This is more than a collection of ideas—it’s a structured methodology for producing high-quality puzzles consistently, with results that can be validated and reviewed.
ResearchDual-Anchor Brainstorming
Strictly grounded in Dario Amodei’s core decision-making philosophy, this Skill can reproduce the full workflow of expert-level trend forecasting, opportunity breakdowns, dialectical analysis, and decision judgment on a 1:1 basis. Its dual closed loop—“experience anchors + first principles”—precisely breaks down opportunities, analyzes risks dialectically, and delivers actionable decision plans.
WriteSeedance 2.5 Prompt Director
An industrial-grade prompt optimization system designed for Seedance 2.5, combining the expertise of a director, cinematographer, and technical artist. It quickly transforms rough ideas into director-level prompts ready for generation, covering the full range of scenarios from creation from scratch and troubleshooting to fine-tuning, iteration, and reference material integration. The system uses a 3×3 temporal structure to control narrative pacing, four-dimensional industrial controls to precisely manage visual, physical, spatial, temporal, and stylistic attributes, and standardized subject anchoring with negative constraints. It addresses issues such as subject drift, flickering, and loss of style control at the source, helping produce stable, high-quality, cinematic motion visuals.