Skill UI

Automate Dropbox file management, search, upload, download, folder operations, and sharing links through Rube MCP and Composio. Includes setup, workflows, parameters, and pitfalls.

Proofread email drafts for grammar, spelling, punctuation and article errors while preserving the writer's voice, and strip tracking parameters from links only on request. Returns the corrected draft plus a clear change list.

Expert guidance for using ffuf in authorized web penetration testing: content discovery, subdomain and parameter fuzzing, authenticated raw requests, auto-calibration, filtering, and result analysis.

This skill helps users find the best AI models for specific tasks by querying Hugging Face benchmark leaderboards. It analyzes hardware constraints like GPU VRAM or CPU memory to filter compatible models. The output includes a comparison table with benchmark scores, parameter sizes, licenses, and device compatibility status. It also suggests whether models can run locally or require API access.

Offensive security skill for hunting API security misconfigurations: mass assignment, JWT none/algorithm confusion, server-side prototype pollution, and server-side parameter pollution in backend URL construction. Requires explicit written authorization and a controlled lab or target scope.

Methodology for hunting open redirect flaws in web apps: parameter discovery, bypass payloads, DOM-based sinks, OAuth auth-code theft chains and SSRF escalation. Docs-only, for authorized bug bounty and pentest use.

This skill provides systematic methodologies for identifying and exploiting Insecure Direct Object Reference (IDOR) vulnerabilities in web applications. It covers detection techniques using parameter manipulation, exploitation via Burp Suite, and remediation strategies. Requires authorized security assessments and multiple test accounts to verify cross-user access. Outputs include vulnerability reports, proof of concept, and remediation recommendations.

A skill for reverse engineering front-end web applications. It helps locate API signature chains, analyze encrypted request parameters, sample runtime behavior, and reproduce logic locally in Node.js for evidence-based output. Suitable for security assessments and understanding client-side encryption.

This skill generates production-grade JUnit 5 unit and integration tests in Java. It covers assertions, parameterized tests, lifecycle hooks, mocking with Mockito, and nested tests. Ideal for developers needing robust testing strategies and best practices for Java projects.

Builds two parameterized UI modes—iridescent white and colorful black—using OKLCH palettes, procedural WebGL spectral fields with CSS fallback, vision gating, screenshot QA, and total/per-color intensity reports.

A human-in-the-loop studio for iteratively tuning AI outputs or reviewing complex media/prose. It allows users to directly manipulate visual parameters (color, typography, layout) or annotate documents in real-time, moving beyond static comparison grids or vague prompts. Perfect for designers and content creators who need hands-on, visual feedback.

Automated visual tuning: a vision or video model rates rendered variants in a loop. Render labeled variants into one artifact, ask the model to rate them and suggest better values, render suggestions, pick the best, repeat until good. Ideal for aesthetics, timing, layout, color grading, and other subjective visual parameters without numeric metrics.