| 6.4 | skills.sh | agent-browser agent-browser wraps playwright for ai-driven web automation, exposing six functions (open, snapshot, interact, screenshot, execute, close) with element refs and session persistence for multi-step workflows. |
| 4.8 | skills.sh | product-changelog product-changelog provides guidelines and templates for writing user-centric release notes, covering categorization, semantic versioning, visual inclusion, and multi-channel distribution, but lacks executable procedures. |
| 4.4 | skills.sh | image-to-video converts still images to animated video via the belt CLI, covering model selection across wai 2.5 i2v, seedance, fabric, and grok video with guidance on motion prompting and camera movement setup. |
| 4.3 | skills.sh | web-search web-search provides command-line interfaces to tavily and exa via inference.sh, covering search and content extraction. gaps in procedure detail and error handling limit operational readiness. |
| 4.2 | skills.sh | press-release-writing press-release-writing scaffolds ap-style drafting with belt cli integration and tavily search for fact verification, but lacks procedural detail on actual composition, editorial workflow, and common failure modes. |
| 4.2 | skills.sh | ai-image-generation ai-image-generation wraps 50+ inference models (flux, gemini, grok, seedream) through inference.sh cli. covers text-to-image, inpainting, upscaling, and lora fine-tuning across budget and high-fidelity tiers. |
| 4.2 | skills.sh | dialogue-audio dialogue-audio generates multi-speaker conversation audio via dia tts through inference.sh cli. covers speaker tagging and basic conversation flow but lacks emotion control, pacing detail, and post-production guidance. |
| 4.2 | skills.sh | technical-blog-writing technical-blog-writing provides scaffolding for developer-focused posts via belt CLI, but lacks substantive guidance on structure, code examples, audience depth, and editorial conventions beyond installation steps. |
| 3.8 | skills.sh | qwen-image-2 qwen-image-2 wraps alibaba's image generation models through the inference.sh cli, supporting generation and editing workflows via a minimal json interface. |
| 3.8 | skills.sh | talking-head-production talking-head-production creates synthetic videos with AI avatars and lipsync using the belt CLI. covers p-video-avatar, omnihuman, and related vendors but documentation is severely incomplete. |
| 3.8 | skills.sh | og-image-design og-image-design provides a cli wrapper for converting html to social sharing images via inference.sh, with minimal guidance on og meta tags, platform specs, or branding strategy. |
| 3.8 | skills.sh | newsletter-curation newsletter-curation provides a starting point for using the belt CLI to run content search via tavily, but lacks executable guidance for actual curation, formatting, or subscriber workflows. |
| 3.8 | skills.sh | social-media-carousel social-media-carousel provides a single html-to-image conversion example for carousel slides. no layout rules, swipe psychology, or multi-slide orchestration implemented despite the description claiming coverage. |
| 3.7 | skills.sh | nano-banana nano-banana wraps google gemini image generation models (gemini 3 pro image, gemini 2.5 flash image) through the inference.sh cli, enabling text-to-image synthesis via the belt command. |
| 3.5 | skills.sh | pitch-deck-visuals pitch-deck-visuals documents how to generate slide backgrounds via inference.sh cli, with one example of html-to-image conversion but no systematic coverage of the 12-slide framework or design principles claimed in metadata. |
| 3.5 | skills.sh | speech-to-text speech-to-text transcribes audio files to text using inference.sh cli and whisper models, requiring belt login and accepting remote audio urls as input. |
| 3.5 | skills.sh | p-image p-image wraps pruna's optimized text-to-image models via inference.sh cli, supporting p-image, p-image-lora, p-image-edit and variants. execution is minimal: authenticate with belt login, then invoke via belt app run with a prompt json input. |
| 3.4 | skills.sh | video-prompting-guide video-prompting-guide advertises best practices for ai video generation but provides only installation commands and a stub. core guidance content is missing entirely. |
| 3.4 | skills.sh | agent-ui agent-ui bundles a react component with agent runtime, tooling, and streaming, but lacks actionable implementation detail, decision logic, and failure guidance needed for production use. |
| 3.2 | skills.sh | widgets-ui widgets-ui exposes a json-driven component renderer for react, but lacks actionable guidance on schema construction, error handling, or realistic use cases beyond import statements. |
| 3.2 | skills.sh | p-video p-video wraps pruna's optimized video generation models (p-video, wan-t2v, wan-i2v) via inference.sh cli for text-to-video and image-to-video synthesis. incomplete documentation limits practical adoption. |
| 3.2 | skills.sh | related-skill related-skill surfaces available skills from the inference.sh registry via npm cli commands and provides install recipes for common workflows like content creation and research agents, but lacks actual discovery logic or filtering capability. |
| 3.2 | skills.sh | ai-avatar-video generates talking head videos from text or audio using inference.sh cli, supporting multiple avatar backends including p-video-avatar with bundled tts. |
| 3.2 | skills.sh | ai-social-media-content ai-social-media-content provides a minimal wrapper around inference.sh CLI for generating social media assets across platforms, but lacks actionable procedure, specific trigger context, and substantive documentation beyond login instructions. |
| 3.2 | skills.sh | agent-tools agent-tools documents a cli installation and usage guide for inference.sh, a cloud platform running 250+ ai apps. lacks skill structure, decision logic, and failure handling. |
| 3.2 | skills.sh | tools-ui tools-ui provides react component scaffolding for tool lifecycle ui states (pending, progress, approval, results) but lacks actionable procedures, trigger examples, and substantive failure handling. |
| 3.2 | skills.sh | background-removal background-removal invokes the birefnet model via inference.sh cli to strip backgrounds from images. minimal procedural detail, no failure handling, sparse trigger guidance. |
| 3.1 | skills.sh | chat-ui chat-ui provides react/next.js chat components (container, messages, input, typing indicators, avatars) via shadcn installer, but lacks procedural depth, trigger specificity, and failure mode documentation. |
| 2.5 | skills.sh | prompt-engineering prompt-engineering covers techniques for effective ai model interaction, but the skill.md is incomplete stub content with no actual procedure, examples, or actionable guidance. |
| 2.4 | skills.sh | app-store-screenshots app-store-screenshots provides a placeholder for creating ios and android screenshots via belt cli, but lacks actionable procedure, platform specifications, and decision logic. |
| — | skills.sh | ai-video-generation ai-video-generation — an installable skill for AI agents, published by inference-sh/skills. |
| — | skills.sh | ai-podcast-creation Create AI-powered podcasts with text-to-speech, music, and audio editing. Tools: Kokoro TTS, DIA TTS, Chatterbox, AI music generation, media merger.… |
| — | skills.sh | storyboard-creation Film and video storyboarding with shot vocabulary, continuity rules, and panel layout. Covers shot types, camera angles, movement, 180-degree rule, and… |
| — | skills.sh | explainer-video-guide Explainer video production guide: scripting, voiceover, visuals, and assembly. Covers script formulas, pacing rules, scene planning, and multi-tool pipelines.… |
| — | skills.sh | nano-banana-2 Generate images with Google Gemini 3.1 Flash Image Preview (Nano Banana 2) via inference.sh CLI. Capabilities: text-to-image, image editing, multi-image input… |
| — | skills.sh | seo-content-brief SEO content brief creation with keyword research, search intent analysis, and content structure. Covers SERP analysis, heading hierarchy, word count targets,… |
| — | skills.sh | python-executor Execute Python code in a safe sandboxed environment via [inference.sh](https://inference.sh). Pre-installed: NumPy, Pandas, Matplotlib, requests,… |
| — | skills.sh | character-design-sheet Character consistency across AI-generated images with reference sheets and LoRA techniques. Covers turnaround views, expression sheets, color palettes, and… |
| — | skills.sh | flux-image Generate images with FLUX models (Black Forest Labs) via inference.sh CLI. Models: FLUX Dev LoRA, FLUX.2 Klein LoRA with custom style adaptation. Capabilities:… |
| — | skills.sh | product-photography AI product photography with studio lighting, lifestyle shots, and packshot conventions. Covers angles, backgrounds, shadow types, hero shots, and e-commerce… |
| — | skills.sh | ai-voice-cloning AI voice generation, text-to-speech, and voice synthesis via inference.sh CLI. Models: Inworld TTS-2 (100+ languages, emotion/non-verbal steering), Inworld TTS… |
| — | skills.sh | text-to-speech Convert text to natural speech with Inworld TTS, ElevenLabs, DIA TTS, Kokoro, Chatterbox, and more via inference.sh CLI. Models: Inworld TTS-2 (100+ languages,… |
| — | skills.sh | llm-models Access Claude, Gemini, Kimi, GLM and 100+ LLMs via inference.sh CLI using OpenRouter. Models: Claude Opus 4.5, Claude Sonnet 4.5, Claude Haiku 4.5, Gemini 3… |
| — | skills.sh | logo-design-guide Logo design principles and AI image generation best practices for creating logos. Covers logo types, prompting techniques, scalability rules, and iteration… |
| — | skills.sh | ai-product-photography Generate professional AI product photography and commercial images. Models: FLUX, Imagen 3, Grok, Seedream for product shots, lifestyle images, mockups.… |
| — | skills.sh | javascript-sdk JavaScript/TypeScript SDK for inference.sh - run AI apps, build agents, integrate 250+ models. Package: @inferencesh/sdk (npm install). Full TypeScript… |
| — | skills.sh | ai-automation-workflows Build automated AI workflows combining multiple models and services. Patterns: batch processing, scheduled tasks, event-driven pipelines, agent loops. Tools:… |
| — | skills.sh | video-ad-specs Video ad creation with exact platform-specific specs for TikTok, Instagram, YouTube, Facebook, LinkedIn. Covers dimensions, duration limits, AIDA framework,… |
| — | skills.sh | python-sdk Python SDK for inference.sh - run AI apps, build agents, and integrate with 250+ models. Package: inferencesh (pip install inferencesh). Supports sync/async,… |
| — | skills.sh | ai-music-generation Generate AI music and songs with ElevenLabs, Diffrythm, Tencent Song Generation via inference.sh CLI. Models: ElevenLabs Music (up to 10 min, commercial… |
| — | skills.sh | infsh-cli Run 250+ AI apps via inference.sh CLI - image generation, video creation, LLMs, search, 3D, Twitter automation. Models: FLUX, Veo, Gemini, Grok, Claude,… |
| — | skills.sh | customer-persona Research-backed customer persona creation with market data and avatar generation. Covers demographics, psychographics, jobs-to-be-done, journey mapping, and… |
| — | skills.sh | youtube-thumbnail-design YouTube thumbnail design with specific dimensions, contrast rules, and mobile preview optimization. Covers safe zones, text placement, face expression… |
| — | skills.sh | product-hunt-launch Product Hunt launch optimization with specific specs, timing, and gallery strategy. Covers taglines, gallery images, maker comments, and launch day tactics.… |
| — | skills.sh | ai-marketing-videos Create AI marketing videos for ads, promos, product launches, and brand content. Models: Veo, Seedance, Wan, FLUX for visuals, Kokoro for voiceover. Types:… |
| — | skills.sh | case-study-writing B2B case study writing with STAR framework, data visualization, and research. Covers structure, customer quotes, metrics presentation, and distribution… |
| — | skills.sh | ai-content-pipeline Build multi-step AI content creation pipelines combining image, video, audio, and text. Workflow examples: generate image -> animate -> add voiceover -> merge… |
| — | skills.sh | qwen-image-2-pro Generate images with Alibaba Qwen-Image-2.0-Pro via inference.sh CLI. Professional text rendering, fine-grained realism, enhanced semantic adherence. Ideal for… |
| — | skills.sh | content-repurposing Content atomization — turn one piece of content into many formats. Covers blog-to-thread, blog-to-carousel, podcast-to-blog, video-to-quotes, and more. Use… |
| — | skills.sh | twitter-thread-creation Twitter/X thread writing with hook tweets, thread structure, and engagement optimization. Covers tweet formatting, character limits, media attachments, and… |
| — | skills.sh | ai-rag-pipeline Build RAG (Retrieval Augmented Generation) pipelines with web search and LLMs. Tools: Tavily Search, Exa Search, Exa Answer, Claude, GPT-4, Gemini via… |
| — | skills.sh | landing-page-design Landing page conversion optimization with layout rules, hero section design, and CTA psychology. Covers above-the-fold formula, social proof placement, mobile… |
| — | skills.sh | linkedin-content LinkedIn post writing with hook formulas, formatting rules, and engagement patterns. Covers post types, algorithm signals, character limits, and content… |
| — | skills.sh | competitor-teardown Structured competitive analysis with feature matrices, SWOT, positioning maps, and UX review. Covers research frameworks, pricing comparison, review mining,… |
| — | skills.sh | book-cover-design Book cover design with genre-specific conventions, typography rules, and AI image generation. Covers fiction and non-fiction genres, sizing, thumbnail testing,… |
| — | skills.sh | remotion-render Render videos from React/Remotion component code via inference.sh. Pass TSX code, get MP4. Supports all Remotion APIs: useCurrentFrame, useVideoConfig, spring,… |
| — | skills.sh | image-upscaling Upscale and enhance images with Real-ESRGAN, Thera, Topaz, FLUX Upscaler via inference.sh CLI. Models: Real-ESRGAN, Thera (any size), FLUX Dev Upscaler, Topaz… |
| — | skills.sh | email-design Email marketing design with layout patterns, subject line formulas, and deliverability rules. Covers welcome sequences, promotional emails, transactional… |
| — | skills.sh | data-visualization Data visualization with chart selection, color theory, and annotation best practices. Covers chart types (bar, line, scatter, heatmap), axes rules, and… |
| — | skills.sh | google-veo Generate videos with Google Veo models via inference.sh CLI. Models: Veo 3.1, Veo 3.1 Fast, Veo 3, Veo 3 Fast, Veo 2. Capabilities: text-to-video, cinematic… |
| — | skills.sh | twitter-automation Automate Twitter/X with posting, engagement, and user management via inference.sh CLI. Apps: x/post-tweet, x/post-create (with media), x/post-like,… |
