AI Skills
Installable SKILL.md packages that extend AI coding agents with reliable workflows and domain-specific judgment — ranked by installs, sourced from skills.sh.
figma-code-connect-components
Connect Figma design components to code components for automatic design-system synchronization.
fal-restore
Restore and fix image quality — deblur, denoise, fix faces, and restore old documents.
paywall-upgrade-cro
Design and optimize upgrade screens, paywalls, and upsell modals for SaaS conversion.
qianwen-model-selector
Recommend the best Qwen model and parameters for your task.
monitoring-operations
Set up OCI metrics, alarms, and log collection without common gotchas like namespace confusion and missing data handling.
fal-kling-o3
Generate images and videos with Kling O3, Kling's most powerful model family, via fal.ai.
documentation-templates
Ready-to-use templates for README, API docs, code comments, and AI-friendly documentation.
deep-learning-pytorch
Expert guidance for deep learning, transformers, diffusion models, and LLM development with PyTorch.
figma-generate-design
Build and update full-page Figma screens using design system components, variables, and styles instead of hardcoded values.
minecraftconsoles-lce
Expert C++ skill for building, running, and extending Minecraft Legacy Console Edition with dedicated server and LAN multiplayer.
fal-upscale
Upscale images and videos to higher resolution using AI super-resolution models on fal.ai
github-issue-triage
Triage GitHub issues with streaming analysis—one background task per issue for real-time results.
picoclaw-ai-assistant
Ultra-lightweight AI assistant in Go that runs on $10 hardware with <10MB RAM and single-binary deployment.
book-study
Systematic reading coach with knowledge compilation, mastery testing, and spaced repetition for deep book learning.
project-health
All-in-one project configuration and health management for Claude Code.
figure-generation
Generate publication-quality scientific figures with matplotlib/seaborn using query expansion, code generation, and VLM visual feedback.
prompt-engineer
Transform vague prompts into optimized ones using proven AI frameworks automatically.
replicate
Discover, compare, and run AI models via Replicate's API for image, audio, and video generation.
figma-create-new-file
Create a new blank Figma Design or FigJam file for design workflows.
adk-evals
Write, run, and debug automated conversation tests for ADK agents with assertions on responses, tools, state, and workflows.
add-sfx
Add a new sound effect to @remotion/sfx library
obsidian-wiki-ingest
Automate document ingestion into Obsidian wiki with deduplication, frontmatter, and cross-linking.
data-report
Transform CSV, Excel, or JSON data into polished visual report pages with KPI cards and interactive charts.
faq-page
Collapsible FAQ page with search and category filtering for support content.
fal-realtime
Real-time streaming AI image generation via fal.ai for rapid creative iteration.
fal-train
Train custom LoRA models on fal.ai for personalized image generation tailored to brands, characters, or styles.
using-mobile-native-capabilities
Build LWCs that access native mobile device capabilities—barcode scanning, biometrics, location, NFC, payments, and more.
qianwen-video-generation
[QianWen] Generate videos using Wan models. Supports text-to-video, image-to-video, first+last frame, reference-based role-play, and video editing (VACE). TRIGGER when: user wants to create, generate, or edit video content, mentions video generation/animation/video clips/Wan models, or explicitly invokes this skill by name (e.g. use qianwen-video-generation). DO NOT TRIGGER when: user wants to generate images (use qianwen-image-generation), understand/analyze existing videos (use qianwen-vision), text-only tasks.
venice-audio-speech
|
eol-message
Write a clear, empathetic EOL announcement with rationale, customer impact, and next steps. Use when retiring a product, feature, or plan without creating avoidable confusion.