465 skills · sorted by relevance
Edit images with AI models hosted on fal.ai. Use the skill to change an image's style, remove its background or unwanted objects, or repaint selected areas through inpainting, which replaces part of an image.
Find JavaScript code that changes existing objects or arrays, then replace those updates with modified copies. Review shared state and browser behavior to make data changes easier to trace and check fixes in context.
Style Three.js objects with realistic, cartoon, or custom materials. Choose material types, adjust textures and reflections, create glass or metal effects, and use shader code for custom appearance while considering rendering performance.
Animate 3D objects in Three.js using timed keyframes, bone movement, and shape changes. Play animations stored in GLTF models, control playback speed and looping, blend actions, and create motion through code.
Add glow, depth-based blur, color correction, and other finishing effects to Three.js scenes. Covers combining effects with EffectComposer, writing custom shaders for screen effects, handling window resizing, and adjusting rendering workload.
Create and edit bitmap images, such as photos, illustrations, product mockups, and game assets. Use reference images for visual variations, replace backgrounds, remove objects, or make transparent cutouts while preserving specified parts of an existing image.
Extend an existing Twenty app with data fields, layouts, custom screens, automated logic, workflows, and permissions. The skill guides code organization, entity creation, type checking, linting, and syncing definitions to the active remote.
Manage files and storage buckets in Tigris through its official CLI. Agents can upload and download objects, generate temporary sharing URLs, take snapshots, and manage access keys and permissions with structured JSON output.
Analyze single-cell RNA-seq data with Scanpy, from quality checks and normalization to cell grouping, exploratory marker genes, and plots. Bundled scripts also prepare sample-level count summaries and support conversion of R objects to h5ad.
Create, update, search, and organize Anytype notes and tasks through a command-line tool. It also supports properties, tags, file uploads, and chat access, with JSON output for use in scripts.
Investigate Kubernetes permissions and cluster behavior in CTF sandboxes. Trace role-based access control, service accounts, and automated controllers to explain workload changes, secret exposure, and differences between configuration files and live objects.
Create or repair a JSON specification for an editable PowerPoint deck. Define exact object positions, sizes, styles, and layering, alongside reading order and image descriptions, so the build process follows an explicitly authored layout.
Connect ViewModels, objects that manage screen state and actions, through messages without direct references. The skill covers event broadcasts, requests for values, window-specific channels, and recipient registration and cleanup using CommunityToolkit.Mvvm.
Turn descriptions of 3D shapes and CAD tasks into FreeCAD Python scripts. Create models with adjustable dimensions, automate repeated operations with macros, convert meshes and solids, or build custom dialogs and workbench tools.
Investigate Spring configuration and Beans, the objects Spring manages, using Arthas. Check configuration sources, find registered objects by name or type, and inspect registration details while prioritizing read-only queries.
Deploy decoy accounts, service entries, and policy objects in Active Directory to detect suspicious activity. Configure monitoring rules for Windows security events and validate alerts for credential misuse, reconnaissance, and movement between systems.
Use ROADrecon and roadtx during authorized Microsoft Entra ID testing to inspect directory objects and authentication tokens, which represent access permissions. Explore collected configuration offline, test token exchanges, and assess conditional access and device controls.
Inspect suspicious PDFs without opening them in a reader. Use PDFiD, pdf-parser, and peepdf to examine internal objects, extract scripts, embedded files, and URLs, and document how the suspected attack works.
Inspect suspicious PDFs without opening them in a document viewer. Use peepdf, pdfid, and pdf-parser to examine internal objects, extract embedded code and files, and report threat indicators such as URLs and hashes.
Review Active Directory permissions with ldap3, a Python library for directory queries. Identify excessive access granted to non-administrative accounts, explain potential privilege escalation paths, and produce a JSON report with affected objects and remediation recommendations.
Control street, building, and vehicle light sources in CARLA. Switch groups on or off, adjust their color and brightness, and enable automatic nighttime lighting to prepare illuminated city scenes or blackouts.
Build PHP 8.3+ applications with Laravel or Symfony, including typed models, services, APIs, and tests. Use static analysis, which checks code without running it, alongside automated tests to verify the implementation.
Investigate insecure deserialization, where restoring objects from stored or transmitted data can execute unwanted code. Covers multiple languages, input format recognition, vulnerable processing points, verification methods, and documentation of affected libraries and entry points.
Build and deploy AI agents on Cloudflare Workers using the Agents SDK. Supports persistent conversation state, live WebSocket connections, scheduled tasks, and tool integration, with guidance for connecting browser or React chat interfaces.