Aadarsh Sharma
Community@Aadi-110i
Full Stack Developer | Next.js, React, Node.js, PostgreSQL Building scalable web applications and AI-powered solutions.
Agent Skills by Aadarsh Sharma
Showing 110 vetted skills indexed across 1 GitHub repositories.
Aadi-110illm-models
Access Claude, Gemini, Kimi, GLM and other LLMs via OpenRouter through the inference.sh CLI.
Aadi-110iai-rag-pipeline
Builds RAG pipelines combining web search tools with LLMs via the inference.sh CLI.
Aadi-110ipython-executor
Execute Python code in a sandboxed environment with 100+ pre-installed libraries.
Aadi-110ithreejs-skills
Create interactive 3D scenes and WebGL visualizations using Three.js.
Aadi-110iui-ux-pro-max
Generates design systems and UI/UX recommendations from a searchable design rule database.
Aadi-110iseo-content-brief
Creates SEO content briefs with keyword research, SERP analysis, and heading structure.
Aadi-110ielevenlabs-stt
Transcribe audio with ElevenLabs Scribe models including diarization, timestamps, and forced alignment.
Aadi-110itools-ui
Renders React components for tool call lifecycle states including pending, approval, and results.
Aadi-110ielevenlabs-sound-effects
Generate sound effects from text descriptions using ElevenLabs via the inference.sh CLI.
Aadi-110iinfsh-cli
Run 250+ cloud AI apps for image, video, LLM, search, and Twitter tasks via the inference.sh CLI.
Aadi-110iagent-browser
Automates browser interactions via Chrome DevTools Protocol with accessibility-tree snapshots.
Aadi-110ispeech-to-text
Transcribe audio files to text using ElevenLabs Scribe and Whisper models via the inference.sh CLI.
Aadi-110ipython-sdk
Build AI applications and agents in Python using the inference.sh SDK.
Aadi-110iqwen-image-2-pro
Generate images with Alibaba Qwen-Image-2.0-Pro via the inference.sh CLI.
Aadi-110ibuilding-inferencesh-apps
Build, test, and deploy Python or Node.js applications on the inference.sh platform.
Aadi-110iai-music-generation
Generate music and songs via the inference.sh CLI using ElevenLabs, Diffrythm, and Tencent models.
Aadi-110ip-image
Generate and edit images with Pruna P-Image models via the inference.sh CLI.
Aadi-110iagent-tools
Run 250+ cloud AI apps for image, video, LLM, search, and Twitter tasks via the inference.sh CLI.
Aadi-110ipress-release-writing
Writes AP-style press releases with inverted pyramid structure and fact-checking.
Aadi-110iimage-to-video
Convert still images into animated videos using AI inference models via the belt CLI.
Aadi-110ihumanizer-zh
Rewrites Chinese text to remove AI writing patterns and restore natural human voice.
Aadi-110inewsletter-curation
Create curated email newsletters with content sourcing, commentary templates, and growth strategies.
Aadi-110inano-banana-2
Generate and edit images with Google Gemini 3.1 Flash Image Preview via the inference.sh CLI.
Aadi-110ireact-native
Renders JSON specs into native mobile UIs using React Native components.
Frequently Asked Questions About Aadarsh Sharma
FAQPage SchemaWhat tasks can I accomplish with Aadarsh Sharma's skill registry?▼
You can generate AI images (FLUX, GPT-Image-2, Qwen), videos (Veo, Seedance, Wan), music, sound effects, and voiceovers, plus transcribe audio, clone voices, build RAG research pipelines, design UI/UX, create 3D Three.js scenes, and produce marketing assets like pitch decks, press releases, and thumbnails.
Who is the target audience for these skills?▼
Full-stack developers, content creators, marketers, and product teams. The bio highlights Next.js, React, Node.js, and PostgreSQL expertise, and the skills serve engineers building AI-powered web apps alongside creators producing video, audio, social media, and e-commerce visual content.
How do I install and run these skills?▼
Most skills execute through the inference.sh CLI using Bash(belt *) commands. JavaScript/TypeScript integration uses npm install @inferencesh/sdk, while Python uses pip install inferencesh. Skills like agent-browser run via npx agent-browser, and UI components come from ui.inference.sh for React/Next.js.
Are these skills open-source and what do they cost?▼
Licensing varies per skill: gpt-image-2 is MIT, 3d-web-experience is Apache 2.0, while pptx and frontend-design carry proprietary licenses. Most generation skills route through inference.sh, where model usage (Veo, ElevenLabs, FLUX) is billed per inference rather than being free.
What prerequisites and dependencies are required?▼
You need the inference.sh CLI installed for the majority of media-generation skills, Node.js/npm or Python/pip for the SDKs, and Bash access. The python-executor sandbox ships with NumPy, Pandas, Playwright, and OpenCV pre-installed; baoyu-image-gen requires bun or npx binaries.