Explore
MCP servers and skills: search, filter by where they run, and compare.
MCP servers and skills: search, filter by where they run, and compare.
Core package for defining schemas, catalogs, and AI prompt generation for json-render. Use when working with @json-render/core, defining schemas, creating catalogs, or building JSON specs for UI/video
OfficialSkillApache-2.0★ 19k in collectionNo key
Remotion renderer for json-render that turns JSON timeline specs into videos. Use when working with @json-render/remotion, building video compositions from JSON, creating video catalogs, or rendering
OfficialSkillApache-2.0★ 19k in collectionNo key
React Three Fiber 3D renderer for json-render. Use when working with @json-render/react-three-fiber, building 3D scenes from JSON specs, rendering meshes/lights/models/environments, or integrating Thr
OfficialSkillApache-2.0★ 19k in collectionNo key
Code generation utilities for json-render. Use when generating code from UI specs, building custom code exporters, traversing specs, or serializing props for @json-render/codegen.
OfficialSkillApache-2.0★ 19k in collectionNo key
Inspect an agent repository and optional traces, interview the user, write reviewed Task Specs, build and audit Harbor tasks, and bootstrap reusable project World Knowledge Skills. Use for agent evals
OfficialSkillMIT★ 1.3k in collectionNo key
InternVideo2-CLIP L14 (TAO video_clip) for video-text retrieval, zero-shot classification, embedding extraction, LoRA fine-tuning, ONNX export, and TensorRT deployment. Use when the user asks to "fine
in the skill textCLIP L14**. The PyTorch image provides `train`, `evaluate`, `inference`, `export`, and `default_specs`. TAO Deploy provides `gen_trt_engine`, TensorRT `evaluate`, and TensorRT `inference`. Container images
OfficialSkillApache-2.0★ 3.6k in collectionNo key
Cosmos-Embed1 video-text embedding for text-to-video retrieval, video-to-video search, semantic deduplication, and fine-tuning. Use when the user asks to "fine-tune Cosmos-Embed1", "run cosmos-embed i
in the skill textexport`. Container image and per-action commands are in `references/skill_info.yaml`. Compact starting specs are in `references/spec_template_*.yaml`. ## Train Action Policy AutoML is not packaged for this
OfficialSkillApache-2.0★ 3.6k in collectionNo key
Visual ChangeNet for binary image classification and segmentation in AOI defect detection. Use when training, evaluating, exporting, or running inference for PCB defect detection or visual inspection,
in the skill textRADIO, use the bundled `scripts/stage_backbone.py` and the mount in `references/local-docker.md`. Segment specs use `model.backbone.type: vit_large_nvdinov2` and the NVDINOv2 checkpoint family. Keep the checkpoint architecture
OfficialSkillApache-2.0★ 3.6k in collectionNo key
Generate industry-standard specifications — PRD, SRS, Technical Design, and Test Plan — each usable standalone or as part of a full traceability chain
in the skill textspecifications — from early-stage brainstorming to Technical Design with auto-generated feature specs — each usable standalone or as part of a streamlined auto chain. ## Overview Software
SkillMIT★ 10No key
Claude AI skill for cinematic Higgsfield AI prompts — 32 sub-skills covering Seedance 2.5 (omni-reference, video edit + extend) and 2.0, the Hell Grind feature-film pipeline, an acting system, Cinema
in the skill textVersion ](   . Deterministic anti-AI-slop linter with 152 rules, 160 brand specs, a 7-axis synthesizer, an MCP server (18 tools), 25 co
SkillMIT★ 78No key
A lightweight, zero-dependency CLI tool to manage and activate capabilities for AI coding assistants (such as Claude Code, Cursor, Trae, etc.).
in the skill textexpert Agents (agent-*.md) ├── commands/ # Agent runtime Slash Commands (*.md) ├── docs/ # Technical specs and user guidelines ├── scripts/ # CLI manager source code (hub.js) ├── skills/ # Modular capability skills
SkillMIT★ 978No key
Design minimal AI agent packs for Codex and Claude from project descriptions.
in the skill textpacks for Codex and Claude Code from project descriptions, README files, technical specs, or existing repository evidence. `agent-pack-designer` is a portable Codex skill for
SkillMIT★ 11No key
Reusable UI/UX design skills for AI coding agents — Codex, Claude Code, ZCode, and more.
in the skill textcomplete UI/UX methodology: brand-driven visual direction, design tokens, component recipes, motion specs, and a strict anti-pattern guardrail that keeps output from looking like slop
SkillMIT★ 162No key
Claude skill that analyzes images, websites, and Figma files and generates a structured design.md with token system, component inventory, and reconstruction notes.
in the skill textthat turns **images, websites, and Figma files** into structured, machine-readable design specs — and copies **single elements** (navbars to 3D art) as rebuild prompts any
SkillMIT★ 218No key
Lead with PSL examples in design docs; TS authoring surface mirrors or extends PSL
in the skill textfrom Prisma 1.x/2.x); the TS contract builder is secondary. Design docs (specs, ADRs, architecture docs, READMEs) should reflect that ordering. - **Lead with PSL** when illustrating
OfficialRuleApache-2.0★ 415 in collectionNo key
🖼️ AI agent skill for Claude Code & Codex — turns raw app screenshots into store-ready App Store & Google Play marketing images: device frames (iPhone·iPad·Galaxy·Fold·Flip), app-matched backgrounds,
in the skill textStore & Google Play sizes.   **English** · 한국어 --- Making App Store and Google Play screenshots by hand
SkillMIT★ 89No key
Spec-driven development MCP server for AI coding agents — 8 phases, bi-directional traceability, and 7 quality gates, 15 tools over Streamable HTTP (MIT)
in the skill texthuman vision statement. The AI autonomously researches, audits your codebase, generates specs and plans, implements, and validates — with **bi-directional verification** at every junction to ensure
SkillMIT★ 1Few starsNo key
Five Claude skills that turn a brief into an on-brand storyboard, prompts for ten image and video generators, and checked frames with a hash-pinned audit trail.
in the skill textproduction-grade storyboard with model-specific image prompts, on-screen text specs, an HTML preview, and a versioned audit trail, plus a brand-lock extractor that
SkillApache-2.0★ 21No key
Agent skill: make short videos with code — the agent asks what you want, writes a seven-block prompt (role / context / task / specs / style / avoid / check), draws every frame in Canvas, WebGL or Thre
SkillMIT★ 12No key
Plan first, then let your coding agent build. 25+ planning, design, review and delivery skills for Claude Code, Codex and Cursor, plus the openplanr CLI. Specs, stories and tasks live in your repo und
SkillMIT★ 5No key
Claude skill that goes past word-list humanizers: strips the full catalog of AI tells, refits the text to its channel (LinkedIn, X, cold email, Slack, exec memo, blog), and learns your voice from your
in the skill textfor the move, not just the string. 2. **Channel fit.** Per-channel specs for length, structure, opening convention, formatting, and sign-off across LinkedIn posts and
SkillMIT★ 13No key
Agentic KiCad PCB design workflow for SKiDL — architect, source, code, and verify circuits with AI agents.
in the skill textstock parts from suppliers and retrieves KiCad footprints 5. **Datasheet Librarian** - Gathers specs and datasheets for significant parts and stores them locally 6. **SKiDL Coder** - Writes
SkillMIT★ 22No key
12 agent skills for AI-driven software development — a gated idea-to-ship pipeline: 7w3 design, build-ready specs, executable architecture, honest review loops, a parallel worker-fleet lane, QA, safe
SkillMIT★ 19No key
An assembly line for AI software development. 35 skills, 11 agent personas, 29 commands. From raw idea to shipped code.
in the skill textskills > An Agentic Engineering toolkit for AI coding agents. The human writes specs and architecture. Agents implement in parallel with contracts. Review gates enforce correctness. Structured
SkillMIT★ 3Few starsNo key
The Generative UI framework
in the skill textprops.value, props.format)} ), Button: ({ props, emit }) => ( emit("press")}>{props.label} ), }, }); ``` ### 3. Render AI-Generated Specs ```tsx function Dashboard({ spec }) { return ; } ``` **That's it.** AI generates JSON, you render
OfficialSkillApache-2.0★ 19kNo key
Comprehensive guide for creating professional UI/UX designs in Penpot using MCP tools. Use this skill when: (1) Creating new UI/UX designs for web, mobile, or desktop applications, (2) Building design
in the skill textQuick Reference | Task | Reference File | | ---- | -------------- | | MCP server installation & troubleshooting | setup-troubleshooting.md | | Component specs (buttons, forms, nav) | component-patterns.md | | Accessibility (contrast, touch targets) | accessibility.md | | Screen sizes & platform ⟦s
OfficialSkillMIT★ 40k in collectionNo key
Run the mining-based DEFT improvement workflow for ITS Cosmos-Reason binary video questions, focused on the non-reasoning classification/evaluation path. Use when the user asks for a DEFT CR ITS minin
in the skill textthe DEFT workspace should be as follows: ```text / ├── data/ ├── hf_cache/ ├── model/ ├── specs/ └── results/ ``` | Path | Purpose | | --- | --- | | ` /data/` | User-provided KPI and training datasets, including LLaVA annotations
OfficialSkillApache-2.0★ 3.6k in collectionNo key
OneFormer for universal image segmentation. Unifies panoptic, instance, and semantic segmentation with a single architecture using task-conditioned queries. Use when training, evaluating, exporting, q
in the skill textdefault with this model's `skill_dir`. Preserve workflow/application overrides for datasets, specs, output directories, GPU/platform settings, parent checkpoints, and `automl_policy`. Use direct model training
OfficialSkillApache-2.0★ 3.6k in collectionNo key
Run the disk-backed DEFT AOI improvement loop for NVIDIA Cosmos Reason 3 / Cosmos3 models, using Nano by default and Edge or Super when explicitly requested: evaluate the base model on Proxy and froze
in the skill textContract ```text workspace/ ├── annotations/ # user-supplied │ ├── benchmark_kpi.json │ ├── proxy_kpi.json │ └── mining_pool.json ├── images/ # user-supplied └── specs/ # produced by this workflow, after approval ├── train_spec.toml ├── evaluate_spec_proxy.toml └── evaluate_spec_benchmark.toml ```
OfficialSkillApache-2.0 AND CC-BY-4.0★ 3.6k in collectionNo key
Run the full DEFT AOI improvement loop for NVIDIA TAO VisualChangeNet / ChangeNet PCB inspection models: baseline evaluate, RCA, Cosmos AnomalyGen / AMP synthetic defects, k-NN mining, retraining, and
in the skill texteither end-to-end C-RADIOv2-B or a frozen DINOv3 backbone. `specs/baseline_spec.yaml` defines the architecture. Backbone variants, staging, `HF_TOKEN`, and mount rules are owned
OfficialSkillApache-2.0 AND CC-BY-4.0★ 3.6k in collectionNo key
PyTorch-based TAO image classification. Supports a wide range of backbones (FAN, EfficientNet, ResNet, etc.) with distillation and quantization for deployment. Use when training, evaluating, distillin
in the skill textdefault with this model's `skill_dir`. Preserve workflow/application overrides for datasets, specs, output directories, GPU/platform settings, parent checkpoints, and `automl_policy`. Use direct model training
OfficialSkillApache-2.0★ 3.6k in collectionNo key
Architecture diagrams and checkable docs from your codebase — ERD, C4, API and lifecycle — generated from Prisma, OpenAPI or GraphQL. One HTML file, no server.
in the skill textdisposable.** Documentation and changes are two more views over the same specs, all in one dashboard file. Every diagram also exports as Mermaid (`vibex mermaid
SkillMIT★ 390No key
106 social media skills for AI agents - strategy, writing, video, design, platform growth, publishing, and analytics. Works with Claude, Cursor, OpenClaw, Hermes & 40+ agents.
in the skill textcaption-writer short-form-video-script cross-platform-repurposing \ engagement-routine platform-specs-and-validation scheduling-and-queue ~/.claude/skills/ ``` **Keep it updated** — plugin installs update themselves
SkillMIT★ 155No key
90 specialist AI agents + 3 project-local extensions for Claude Code / Codex CLI / Antigravity CLI (agy). Anthropic Agent Skills spec-aligned, hub-spoke orchestration via Nexus with 49 Recipes and 11
in the skill textknow they needed."_ - Feature proposals. Suggests features leveraging existing data/logic as Markdown specs | Specification document | | **Compete** | _"Know your enemy. Know the market. Know yourself."_ - Competitive research
SkillMIT★ 92No key
Claude Skills for every role: 164 Claude Code skills (Agent Skills) for PM, QA, engineering, design, DevOps, sales, marketing and more. Install as a plugin.
in the skill textobservations into structured debrief reports | Lean Startup - Ries | | `compliance-auditor` | Audit feature specs against India's DPDP Act 2023 — consent, children's data, retention, rights | DPDP
SkillMIT★ 20No key
An architecture-level AI harness that compiles constraints and NFRs into explicit, reviewable architecture decisions. Combines a deterministic compiler, curated pattern registry, and agent workflow sk
in the skill textand add constraints progressively as your understanding grows. **Visual walkthroughs:** see `test-specs-demo/index.html` for HTML demos showing compile → review → edit → recompile loops on real
SkillMIT★ 10No key
Spec-Driven Development Plugins For ClaudeCode/Codex
in the skill textGenerate Tasks with explicit status, wiring, verification, and dependencies ### Spec Files Location Specs are stored in `.claude/specs/ /` by default. Existing `.codex/specs/ /` directories are supported
SkillMIT★ 10No key
Opt-in UI/UX skill for AI coding agents. One trigger activates a Senior Designer + UX Researcher + Frontend Lead workflow — discovery, design systems, WCAG accessibility, 20+ UI styles, industry reaso
in the skill textsearch/filter models - User flows, task flows, journey maps, service blueprints - Wireframes, layout specs, visual direction, interaction design **Accessibility** - WCAG 2.2 AA audits and remediation guidance - Advanced
SkillMIT★ 1Few starsNo key
Who stands behind it
Who stands behind it
