490 skills · sorted by relevance
Turn marketing plans, launches, and campaigns into magazine-style HTML slides that connect brand activity to growth and sales opportunities. The skill develops the narrative, slide content, and visual direction for presentations supporting launch or budget decisions.
Read, create, and adjust PowerPoint presentations, including slide layouts and templates. Use it for executive decks, training materials, and product reviews; the catalogue entry points agents to an upstream bundle containing the full workflow and supporting files.
Turn screenshots, reference links, and rough visual preferences into a reusable DESIGN.md, a record of design decisions, and practical handoff instructions for building prototypes, presentations, redesigns, or image remixes.
Create a three-page editorial motion sequence with dark backgrounds, serif typography, staged text reveals, and chapter transitions. The result is a single HTML file suited to fashion-inspired storytelling and short visual presentations.
Create a brand overview image combining logo concepts, colors, typography, and examples across digital and physical materials. The skill bases the visual direction on the brand’s purpose and audience, arranging connected panels in a clear presentation grid.
Build document search with AgentDB that finds related content by meaning. Store documents as numerical representations, combine similarity search with metadata filters, and retrieve relevant passages for systems that generate answers using source material.
Research a topic across multiple web sources before writing articles, reports, or presentations. Gather facts, examples, and expert views, then check current information, competing perspectives, and limitations to build a well-supported understanding.
Convert text, code, or documents into 384-dimensional vectors, numerical representations used for meaning-based search, similarity comparison, and clustering. Save vectors to files, check their dimensions and magnitude, and optionally record metadata in AgentDB.
Convert chat messages into template strings for local model runtimes such as Ollama or llama.cpp. Optionally route queries among a few registered intents using embeddings, numerical representations of meaning, without calling a model.
Search document collections by meaning using embeddings, numerical representations of text. Compare text similarity, route queries among a few predefined patterns, and use a compressed search index when memory is limited.
Build document search with AgentDB that finds related content by meaning. Store documents as numerical representations, combine similarity search with metadata filters, and retrieve relevant passages for systems that generate answers using source material.
Verify documents, spreadsheets, presentations, and web deliverables before sharing them. Combine file checks with inspection of freshly rendered output, and scan for unfinished text to catch clipped content, layout problems, and leftover placeholders.
Plan a presentation around what the audience needs to understand or decide. Develop its outline, titles, evidence, and visual choices, with guidance tailored to live talks or decks people will read on their own.
Create maps from real geographic data for presentations, documents, graphics, and websites. Use d3-geo for static maps suitable for export, or Leaflet with OpenStreetMap tiles for street maps that users can pan and zoom.
Create navigable HyperFrames presentations with step-by-step reveals, clickable branches, and speaker notes. You can also turn an existing page into a deck while preserving its visual design, motion, and interactive behavior.
Choose Rust types for operating system paths in Codex server protocols and internal code. Guides new definitions and explicitly requested migrations while preserving client compatibility and handling paths from different operating systems.
Apply consistent deprecation notices to public Remotion APIs that remain available. Use TypeScript annotations and documentation formatting to mark APIs as no longer recommended, identify replacements, and review whether both representations follow the conventions.
Implement caching and data conversion for syncable entities in Twenty's server code. Build lookup maps, convert stored records and inputs into flat representations, and resolve references to universal identifiers for later validation and processing.
Create and edit text documents, spreadsheets, and presentations from the command line. Import existing Office or ODF files, update content and styles, and export documents, with JSON project files and undo and redo support.
Apply corporate brand standards to PowerPoint, Excel, and PDF documents. The skill guides colors, fonts, layouts, logo placement, and writing style, with scripts for applying formatting and checking compliance.
Build and troubleshoot TorchDrug 0.2.1 workflows for molecular property prediction, molecule generation, protein modeling, and knowledge graph reasoning. Connect datasets, models, training tasks, and evaluation while checking version compatibility and common implementation errors.
Work with Waypoint models to analyze microbiome samples, the communities of microbes in a sample. Convert taxonomic abundance tables, generate numerical sample representations, configure further training for prediction tasks, and evaluate models on the Compass benchmark.
Create and review scientific figures with Matplotlib, Seaborn, or Plotly. The skill covers panel layouts, uncertainty, missing data, accessible color choices, and exported file checks, helping prepare figures for papers, presentations, or web publication.
Turn supplied data or optional research into infographic drafts for reports, presentations, or social posts. Choose layouts and visual styles, generate PNG images, and use automated reviews to guide revisions while retaining review logs.