Agent skills for Claude Code

Design, audit, and optimize how AI agents receive and manage context.

This skill should be used when the user asks to "test for insecure direct object references," "find IDOR vulnerabilities," "exploit broken…

Refines, polishes, and standardizes SCI and IEEE engineering research papers, cover letters, and review responses with strict technical…

Reviews, standardizes, and redraws academic figures and data plots to comply with strict IEEE publication requirements.

Download Instagram posts, reels, or carousels by URL or shortcode using instaloader.

Automate Ignisign tasks via Rube MCP (Composio).

Synchronizes visual assets with development specifications to ensure implementation matches design intent.

Generates infographic image card series with 12 visual styles, 8 layouts, and 3 color palettes.

Generate AI images using Gemini image generation API.

Converts entire directories of images into unified, structured Markdown documents using AWS Bedrock multimodal LLMs.

Still-to-video conversion guide: model selection, motion prompting,

Generate and edit images using OpenAI's Image API for project assets — UI mockups, icons, illustrations, social cards, and visual…

Multi-perspective academic paper review with dynamic reviewer personas.

Automate Imgbb tasks via Rube MCP (Composio).

Execute one bounded RED to GREEN experiment from bead or caller intent; return derived subject identity and check facts.

**MANDATORY prerequisite** — you MUST invoke this skill BEFORE calling the `get_design_context` Figma MCP tool.

Implements a feature from its specification.

Create agent-executable implementation plan based on codebase exploration

Implements Syncfusion .NET MAUI DigitalGauge (SfDigitalGauge) control to display alphanumeric characters in LED-style digital format.

Implements Figma designs 1:1 using OneKey component library (restore the design draft).

File upload endpoints in ASP.NET minimal APIs (.NET 8+)