yikart
Official@yikart
Offers specialized media processing and content generation capabilities for video synthesis, image manipulation, and multi-format digital asset management.
Agent Skills by yikart
Showing 33 vetted skills indexed across 1 GitHub repositories.
impeccable
Designs, audits, and refines production-grade frontend interfaces through structured sub-commands.
imagegen-frontend-web
Generates per-section horizontal website design reference images with art-directed composition rules.
karpathy-guidelines
Applies behavioral guidelines to reduce common LLM coding mistakes during code writing and review.
design-taste-frontend
Generates non-templated frontend designs for landing pages, portfolios, and redesigns using inferred design direction.
vercel-react-best-practices
Applies Vercel performance optimization rules when writing and refactoring React and Next.js code.
setup-matt-pocock-skills
Configures issue tracker, triage labels, and domain docs for engineering skills.
handoff
Write a conversation summary handoff document for the next agent session.
improve-codebase-architecture
Identifies shallow modules and proposes deepening refactors to improve codebase testability.
triage
Triage GitHub issues through a label-driven state machine with agent briefs.
prototype
Build throwaway terminal or UI prototypes to validate logic and design decisions.
diagnose
Diagnose hard bugs and performance regressions through a structured reproduce-hypothesise-fix workflow.
to-issues
Breaks plans and PRDs into vertical-slice issues on a project issue tracker.
zoom-out
Generates a high-level map of relevant modules and callers for unfamiliar code areas.
write-a-skill
Create new agent skills with proper structure, frontmatter, and bundled resources.
grill-with-docs
Stress-tests plans against domain glossaries and records decisions in CONTEXT.md and ADRs.
caveman
Compresses AI responses by removing filler words while preserving technical accuracy.
tdd
Guides test-driven development using the red-green-refactor loop with vertical slicing.
grill-me
Interviews the user question-by-question to stress-test plans and design decisions.
to-prd
Generates a PRD from conversation context and publishes it to the project issue tracker.
sync-service-docs
Generate and incrementally update API documentation from OpenAPI specifications and source code changes.
composing-videos
Combine multiple video or image files into a single video with optional background audio.
managing-content
Organize media files, drafts, and content collections for publishing workflows.
generating-drama-recaps
Generate narrated drama recap videos from short clips with AI scripts and voice synthesis.
editing-images
Overlays logos and QR codes onto images using the Sharp library.
Frequently Asked Questions About yikart
FAQPage SchemaWhat specific media tasks can be performed using these capabilities?βΌ
These capabilities enable high-fidelity video synthesis, including style transfer, subtitle removal via OCR, and speech cloning. Additionally, users can perform image overlay operations, generate thumbnails from URLs, and manage complex content collections for publishing.
Which technical personas benefit most from these media processing functions?βΌ
Content engineers, creative technologists, and digital media developers benefit from these functions. These capabilities are designed for professionals requiring programmatic control over video composition, image editing, and automated metadata extraction from social media sources.
What are the primary prerequisites for implementing these media processing functions?βΌ
Implementation requires access to the underlying media processing environment and valid input sources such as OpenAPI specifications, raw video files, or image assets. Users must ensure their environment supports the necessary image processing libraries and model inference requirements for video synthesis.