Loading...
Loading...
Found 79 Skills
Edits, rewrites, or improves text for clarity, tone, grammar, or style.
Writing Assistant - Triggered when users say "I want to write XX", "Help me sort out topics", "How to form a framework", "Help me organize my thoughts". Automatically select the optimal path based on the clarity of the user's viewpoint: take the "Framework → Content" path for clear viewpoints, and take the "Mining → Topic Selection → Framework → Content" path for vague viewpoints.
This skill provides comprehensive support for the writing process from ideation through revision. Use this skill when helping users write essays, articles, or creative pieces through interactive collaboration. The skill supports co-evolving outline and prose, voice-based input processing, multiple writing styles, and connection to the user's PKM system for enriched content.
Use this skill when the user needs help with personal writing — either starting a new piece from scratch (inspiration/brainstorming) or reviewing and polishing an existing article (proofreading/editing). Invoke immediately when: the user shares an article and asks for feedback, wants to improve their writing style, feels stuck on what to write, wants help structuring a travel piece/TIL note/personal essay, or asks to review Chinese writing quality. Trigger phrases: 帮我改文章, 检查一下, 润色, 校对, 不知道写什么, 帮我构思, 写游记, 记录 TIL, 写点什么. NOT for diary writing (use diary-assistant) or formal business communications.
Use for any work on a research manuscript in Chinese or English — polishing, proofreading, or "make this sound like a real paper"; Chinese-English academic translation; drafting or tightening an abstract, introduction, related work, method, experiment, discussion, limitation, or conclusion; reviewer responses, rebuttals, and response letters; cover letters, highlights, and AI-use disclosure statements; title and contribution-statement optimization; terminology, tense, abbreviation, and symbol consistency across a draft; editing LaTeX source without breaking \cite, \ref, or math. Trigger this whenever a user shares paragraph-length text that reads like a paper, mentions SCI/EI/IEEE/Elsevier/Springer, a journal or conference name, a reviewer comment, or a thesis chapter — even if they only say "改一下" or "help me with this paragraph." Do not use it to invent citations, datasets, experimental numbers, or to evade plagiarism and AI detection.
Case Radar. Given a new thing (new tool/new concept/new ecosystem), scan the ecosystem to find interesting real-world cases, focusing on capturing "authentic assets" (screenshots/source code/demos) instead of GitHub homepage, and output a browsable HTML case collection. Triggered when users say "See what people are doing with X", "Scan the X ecosystem", "What new ways are there to use X in the market", "Show me authentic cases of X", or "/case-radar". Not suitable for: ① In-depth research with clear objectives (use long-research) ② Writing articles/creating PRDs (use writing-assistant / prd-doc-writer) ③ Pure knowledge-seeking without needing HTML (just ask directly).
Systematic Learning Material Generator. Given a new field/technology/concept, AI conducts independent research, builds a knowledge system, and generates HTML learning materials (including framework/cases/engineering/controversies + blind spots). Triggered when the user says "I want to learn X / Help me systematically break down X / I want to master the field of X / Help me organize the full picture of X / Conduct in-depth research on X and explain it systematically / Master X thoroughly". Not applicable for "Is X feasible / Why Y" (use long-research), "What interesting cases are there in X" (use case-radar for scattered cases), "Organize these materials into HTML" (use readable-output to process existing materials), article writing (use writing-assistant), design drafts (use design-exploration).
Autonomous execution workflow for complex long-running tasks. This applies to scenarios where users have a complex or vague task (e.g., "Help me figure out X / Help me evaluate Y / Help me organize this pile of stuff / Help me compare N solutions / Help me run a research"), and expect the AI to decompose, execute, and verify the task on its own, only reaching out to the user at critical moments. It enables unattended autonomous execution for 1-2 hours through the process of "Task Confirmation → Task Queue → Batch Execution → Periodic Queue Verification → Triggered Reporting". It is triggered when users say phrases like "Help me figure out / Evaluate / Organize / Compare / Run a research / Run it on your own don't bother me / Long-running task / Run autonomously". **Not applicable to**: UI design (use design-exploration), to-do priority judgment (use priority-judge), article writing (use writing-assistant), backlog management (use backlog-manager), vision exploration (use vision-exploration), naming (use product-naming), implementation coding tasks with clear specs (code directly).
Xiaohongshu (RED) title formula tool. It helps you select the suitable formula from 75 proven hit templates, use it correctly and understand the logic behind the formula selection. Trigger methods: /dbs-xhs-title, /xiaohongshu-title, "help me write a Xiaohongshu title", "Xiaohongshu title formula" Xiaohongshu title formula tool. Pick the right formula from 75 proven templates. Trigger: /dbs-xhs-title, "xiaohongshu title", "RED title formula"
SERP-informed outline generation with H2/H3 heading hierarchy, competitive content gap analysis, section-by-section word count targets, chart and image placement markers, FAQ question planning, and internal linking zones. Skeleton only: structure, H2/H3 hierarchy, word counts, FAQ slots. Use blog-brief instead if you need full competitive analysis, statistics research, and image suggestions. Lighter than a full content brief, generates article skeleton and structure only, ready for /blog write to consume. Use when user says "outline", "blog outline", "content outline", "structure blog", "plan sections", "article skeleton", "heading structure", "SERP analysis", "competitive outline", "plan article".
Analyze the writing style characteristics of articles, extract style dimensions and store them in the style material library. It can fuse multiple style materials to generate or update the main style profile (my_style.json). Use this skill when users say "analyze style", "extract writing style", "learn this tone", "analyze my writing style", "absorb this style", "update my style". Even if users just share an article and express interest in its style, consider using this skill.
Automatically reminds when important story elements (characters, plot lines, foreshadowing) haven't appeared for 10+ chapters - prevents 'disappeared character syndrome' and dropped plot threads in long-form fiction