🏆 Vibe Ranking Top 500

Helper skill for README-first AI paper reproduction that scans a repository, extracts documented commands, and returns the smallest trustworthy inference, evaluation, and training plan.

Executes and audits the selected smoke test, documented inference, or evaluation command during README-first AI paper reproduction, writing standardized `repro_outputs/` evidence and patch notes.

Sub-skill for README-first AI paper reproduction that prepares a conservative conda-first environment plus checkpoint, dataset, and cache path assumptions before any run attempt.

🎨 Local-first, open-source Claude Design alternative. 🖥️ Native desktop app. ⚡ 259+ Skills · ✨ 142+ Design Systems 🖼️ Web · desktop · mobile prototypes · slides · images · videos · HyperFrames 📦 Sandboxed preview · HTML/PDF/PPTX/MP4 export 🤖 Claude Code / OpenClaw / Codex / Cursor / OpenCode / Qwen / Copilot / Hermes / Kimi & 17+ CLIs.

Converts arbitrary text (articles, notes, topics, briefs) into faceless explainer videos with auto-generated TTS narration and LLM-designed visuals including typography, abstract graphics, diagrams, and data visualizations.

Creates product launch, SaaS promo, feature reveal, and marketing videos using HyperFrames. Takes a product URL for brand capture or a brief/script, then produces a professionally structured promotional video.

A sentry automation plugin from Awesome Claude Skills by Composio, a curated list of practical Claude Code skills for development productivity.

Orchestrator skill for creating short, design-led motion graphics with HyperFrames, covering kinetic typography, data visualizations, logo reveals, lower-thirds, social overlays, and animated headlines without narration.

Portable agent skill that upgrades AI-built frontend interfaces with stronger layout, typography, motion, and spacing to avoid boilerplate-looking UIs. The original v1 of Taste Skill, preserved for projects depending on its stable behavior.

A Claude Code skill that transforms GitHub pull requests into polished code-change explainer videos, ingesting PR diffs, commits, and file stats via the gh CLI and rendering them as before-after, diff-highlight, and impact scenes.

skills-collective/skills

skills-collective/skills

Adds cinematic captions to talking-head videos using a catalog of 17+ visual identities. Supports column-flow compositing (captions behind the subject via matting and occlusion) and themed constitutions with effects like neon sign reveals and glyph-decode climaxes.

A Composio-powered Claude plugin that automates Zendesk workflows including ticket management, user administration, organization handling, search operations, and macro execution.

Generates images through the inference.sh `infsh` CLI using 50+ models including FLUX, Gemini, and Reve.

Generates videos through the inference.sh `infsh` CLI using 40+ models including Veo, Seedance, and Wan.

Bundle of inference.sh agent skills giving coding agents unified access to image, video, LLM, web-search, and social-automation tools across 150+ models.

Sets up and operates the inference.sh `infsh` CLI for agents — login, app discovery, and running inference against the inference.sh platform.

A Claude Code skill that guides the creation of seek-safe 2D/3D keyframe animations for HyperFrames compositions, supporting GSAP timelines, CSS keyframes, Anime.js, WAAPI, FLIP transitions, SVG morph/draw, motion paths, and 3D depth effects with built-in verification diagnostics.

Automates Twitter/X operations through Composio's Rube MCP, including posting, searching, user management, bookmarks, lists, and media handling.