发现 Skills

PyTorch-native graph neural networks for molecules and proteins. Use when building custom GNN architectures for drug discovery, protein modeling, or knowledge graph reasoning. Best for custom model development, protein property prediction, retrosynthesis. For pre-trained models and diverse featurizers use deepchem; for benchmark datasets use pytdc.

Creative research ideation and exploration. Use for open-ended brainstorming sessions, exploring interdisciplinary connections, challenging assumptions, or identifying research gaps. Best for early-stage research planning when you do not have specific observations yet. For formulating testable hypotheses from data use hypothesis-generation.

Generate a complete video plan with optimized title, thumbnail, and hook concepts based on research. Orchestrates specialized skills (youtube-title, youtube-thumbnail, youtube-video-hook) to create production-ready video plans. Use after research is complete or when the user wants to plan a new video.

Design and execute social engineering penetration tests, including phishing, vishing (voice phishing), smishing (SMS phishing) and physical pretexting activities, to measure personnel security resilience and identify training gaps.

Generate structured cyber threat intelligence reports at strategic, operational, and tactical levels, tailored to specific audiences (including executives, security operations teams, and technical analysts). Suitable for producing finished intelligence products from raw collection data, creating industry threat briefings, or providing post-event intelligence assessments. Applicable to requests involving CTI report writing, threat briefings, intelligence products, finished intelligence, or executive security reports.

Process, parse, create, and manipulate Microsoft Word (.docx) documents programmatically using libraries like docx or mammoth.js for document generation and data extraction. Use when generating Word documents from templates, extracting text and formatting from .docx files, creating reports and invoices, parsing resumes and forms, converting Word to HTML, creating mail merge documents, or automating document workflows.

When the user wants to create, optimize, or audit customer stories or case study pages. Also use when the user mentions "case studies," "customer stories," "success stories," "testimonials page," "case study," "customer proof," "social proof page," or "results page." For testimonial components, use testimonials-generator.

Comprehensive memory storage system for AI employees in IT companies who communicate via Slack. Automatically classifies and stores diverse information types (Slack messages, Confluence docs, emails, meetings, projects, decisions, feedback) in an organized folder structure with efficient indexing and retrieval. Use when managing or searching employee memory, storing conversations, documenting decisions, tracking projects, or organizing any work-related information.

Discovers KrakenD features, checks edition availability (CE vs EE), and provides implementation examples

Generates xUnit.net tests in C#. Covers Fact/Theory, constructor injection, IClassFixture, and FluentAssertions. Use when user mentions "xUnit", "[Fact]", "[Theory]", "Assert.Equal", "C# xUnit". Triggers on: "xUnit", "[Fact]", "[Theory]", "Assert.Equal C#", "xUnit.net".

Generate product changelog entries, X/Twitter posts, and Slack announcements for Leather wallet releases. Use when creating release communications including changelog entries for app.leather.io/changelog, announcement tweets (single or threads), and community Slack posts. Inputs may include verbal feature descriptions, Linear projects, or GitHub PRs.

Manage Linear issues via GraphQL API. List, filter, update, prioritize, comment, and search issues. Use when the user asks about Linear, issues, project management, or backlog.

Guidance for recovering data from SQLite Write-Ahead Log (WAL) files that may be corrupted, encrypted, or inaccessible. This Skill should be used when tasks involve database recovery, WAL file analysis, decrypting database files, or recovering missing/corrupted SQLite data. Helps avoid common pitfalls like fabricating data based on patterns instead of actual recovery.

Integration patterns and best practices for adding persistent memory to LLM agents using the Letta Learning SDK

Guidance for creating Python packages and serving them via a local PyPI server. This skill applies when tasks involve building Python packages (with pyproject.toml or setup.py), setting up local package repositories, or serving packages via HTTP for pip installation. Use when the goal is to create installable Python packages and make them available through a local index URL.

Search messages, read threads, and send messages in Slack. Use this skill to look up past discussions, gather context about a topic, or post notifications to channels.

CREATE/REPLAN Stories for Epic (5-10 Stories). Multi-epic routing: auto-groups Stories by correct Epic. Delegates ln-001 for standards research. Self-Check phase.

Download YouTube video transcripts when user provides a YouTube URL or asks to download/get/fetch a transcript from YouTube. Also use when user wants to transcribe or get captions/subtitles from a YouTube video.

Cognitive atom: Plain. Rewrites any content so a smart 12-year-old can understand it. Structure-free — form follows content. Use when the user says 'say it plainly', 'speak human', 'explain', 'plain', or 'grok'.

Official Google SEO guide covering search optimization, best practices, Search Console, crawling, indexing, and improving website search visibility based on official Google documentation

Generate diagrams and visualizations as draw.io (diagrams.net) XML files — flowcharts, architecture, C4 models, ER diagrams, sequence diagrams, mind maps, swimlanes, and more. Trigger when user says "draw.io", "drawio", "diagrams.net", ".drawio file", or wants draw.io format. Also trigger when extending existing .drawio files or when context calls for draw.io (corporate environments, Confluence/Jira integration, multi-page diagrams).

In-depth analysis of investment assets (gold, silver, bitcoin, equities, etc.) to support investment decisions. Use when the user wants to understand an asset's current state, market analysis, patterns, forecasts, or whether it fits their situation. Triggers on "investment analysis", "analyze gold/bitcoin/silver", "should I invest in X", "current state of X", "market analysis", "is X a good investment".

Support reflection and journaling with prompts and structure. Use when the user wants to journal, reflect on their day, practice gratitude, or get writing prompts for personal reflection.

Explores solution spaces systematically through morphological analysis (parameter-option matrices) and resolves technical contradictions using TRIZ inventive principles to generate novel, non-obvious solutions. Use when exploring all feasible design alternatives before prototyping, resolving technical contradictions (speed vs precision, strength vs weight, cost vs quality), generating novel product configurations, finding inventive solutions to engineering problems, identifying patent opportunities, or when user mentions morphological analysis, Zwicky box, TRIZ, inventive principles, systematic innovation, or design space exploration.