Skills your agents can run
Plug-and-play capabilities — vetted, versioned, and runnable from any Mighty agent.
为指定的 Markdown 文章添加完整的 frontmatter 头信息，包括 title、slug、category、readingTime 等字段。当用户需要格式化文章、添加文章头信息时使用此 Skill。
Read a Confluence page and recursively explore its child pages up to 3 levels deep. Use when users want to comprehensively read a Confluence page tree, understand hierarchical documentation, or analyze content across parent and child pages.
Guidance for creating interactive maps in Obsidian using the LeafletJS plugin — covers real-world tile maps and offline image maps, generating markers from note YAML (latitude/longitude), linking markers to notes, custom icons and popups, tile and overlay layers, importing GeoJSON and GPX tracks, drawing polylines and polygons, and common issues with bounds and zoom levels.
Convert markdown vault to RDF/TTL knowledge graph. Extract persons, projects, meetings, and relationships into semantic triples.
Mindmap Generator - Auto-activating skill for Visual Content. Triggers on: mindmap generator, mindmap generator Part of the Visual Content skill category.
将重要内容记录到 Obsidian Memory 文件夹，自动按日期整理并添加时间戳
Governance + tooling pattern for storing research artifacts, tagging, and discovery.
Curated repository of experiment hypotheses, assumptions, and historical learnings.
Paper reader for non-academics. Takes a paper and extracts its ideas for personal use. Focuses on understanding, not academic critique. Use when the user shares an arXiv link, paper URL, PDF, or asks to analyze a research paper. Trigger words: 'read paper', 'analyze paper', 'paper', or when the user shares an academic paper.
Persistent research knowledge base that accumulates papers, ideas, experiments, claims, and their relationships across the entire research lifecycle. Inspired by Karpathy's LLM Wiki pattern. Use when a user says "knowledge base", "research wiki", "add paper", "wiki query", "query knowledge base", or wants to build/query a persistent field map.
Save notes to notepad.md for compaction resilience
Universal Learner - Automatically extracts reusable elements from prompts in any field, continuously learning and accumulating knowledge
Create and edit Obsidian Flavored Markdown with wikilinks, embeds, callouts, properties, and other Obsidian-specific syntax. Use this skill when working with .md files in Obsidian, or when the user mentions wikilinks, callouts, frontmatter, tags, embeds, or Obsidian notes.
Research across Notion and synthesize into structured documentation; use when gathering info from multiple Notion sources to produce briefs, comparisons, or reports with citations.
AI深度分析语音记录，揭示行为模式、认知偏见和战略盲点。不只是数据汇总，而是直击本质的战略洞察和否定性指导。提取可沉淀的核心原则和工作偏好，构建个人工作模式知识库。
Store and retrieve knowledge in the Alhazen TypeDB knowledge graph - remember, recall, organize papers and notes
Automatically download books from Z-Library and upload them to Google NotebookLM. Supports PDF/EPUB formats, automatic conversion, one-click knowledge base creation.
Obsidian-flavored Markdown extensions including callouts, embeds, and wikilinks
Create comprehensive ontological documentation for Grey Haven systems — extract domain concepts from TanStack Start and FastAPI codebases, model semantic relationships, generate visual representations of system architecture, and document business domains. Use when onboarding, documenting architecture, or analyzing legacy systems.
This skill should be used when user wants to access, capture, or reference Claude Code session history. Trigger when user says "capture session", "save session history", or references past/current conversation as a source - whether for saving, extracting, summarizing, or reviewing. This includes any mention of "what we discussed", "today's work", "session history", or when user treats the conversation itself as source material (e.g., "from our conversation").