Loading...
Loading...
Found 46 Skills
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).
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
Read and understand novel texts, and summarize them into smooth story outlines. Suitable for initial novel screening and generating 500-800 word story outlines
Extract successful patterns from the current session and write to project_memory.json
Patent writing assistant for Chinese patents. Helps with patent search, disclosure document writing, and patent workflow guidance. Triggers when: Writing a patent application, creating a patent disclosure document, conducting patent search and analysis, or planning patent strategy for a project. Commands: - /patent search <keywords> - Conduct patent search - /patent disclosure <invention> - Write disclosure document - /patent report <invention> - Generate self-search report - /patent workflow - Show patent workflow Capabilities: Patent search platform guidance, disclosure document templates, patent three-property analysis, writing tips and best practices, and workflow timeline estimation.
Convert Markdown to WeChat Official Account HTML. Supports API mode (fast) and AI mode (themed). Features writer style assistant, AI trace removal (humanizer), and draft upload.
Use during chapter writing to automatically check character behavior, world rules, and timeline consistency - alerts when detecting potential contradictions before they become major issues
This skill should be used when the user wants to remove AI writing patterns from prose. Use when drafting, editing, or reviewing text to eliminate predictable AI tells.