Topic · Development
Best prototyping skills for Claude Code, Codex and other agents.
- skills
- 113
- official
- 4
Prototyping skills, ranked
Ranked by score. Sort bymost stars,trending,newest,recently updated
| # | Skill | Repository | Stars | Used in | Tokens | Auto-check | Licence | Updated |
|---|---|---|---|---|---|---|---|---|
| 1 | Builds single-file interactive HTML prototypes rendered with the real LobeHub UI components and written as production-style React, so they can later be split into files. | lobehub/ | 83k | — | ~1.6k | Automated safety check: Pass | Unknown | today |
| 2 | Maintains the Vuetify repo's local Playground.vue so contributors get a realistic reproduction and a short demo they can paste into a pull request description. | vuetifyjs/ | 41k | — | ~730 | Automated safety check: Pass | Unknown | yesterday |
| 3 | A skill your agent uses when the user is designing, prototyping, or rewriting a desktop app that must run on multiple OSes (macOS + Windows, optionally Linux) AND feel indistinguishable from a… | yetone/ | 1.9k | 1 repo | ~1.5k | Automated safety check: Pass | MIT | 4 mo ago |
| 4 | Create videos from a text prompt using HeyGen's Video Agent. | calesthio/ | 65k | — | ~1.3k | Automated safety check: Pass | AGPL-3.0 | 4 days ago |
| 5 | Builds a throwaway prototype at just the fidelity needed to settle a specific how-it-should-work-or-feel question, before committing to an approach other work will treat as fixed. | EveryInc/ | 25k | — | ~1.9k | Automated safety check: Pass | MIT | today |
| 6 | Delegates coding tasks to Codex CLI for prototyping, debugging, and code review. | GuDaStudio/ | 132 | 1 repo | ~712 | Automated safety check: Pass | MIT | 9 mo ago |
| 7 | Use the Claude Code CLI to consult Claude and delegate coding tasks for prototyping, debugging, and code review. | appautomaton/ | 457 | 1 repo | ~1.5k | Automated safety check: Pass | MIT | 24 days ago |
| 8 | Guided workflow for authorized penetration testing, vulnerability validation, security reporting, CTF/local sandbox reverse engineering, and user-directed vulnerability research. | lingbol088-spec/ | 222 | — | ~1.8k | Automated safety check: Pass | MIT | 2 mo ago |
| 9 | Puts four real design variations of one project file on your localhost behind a small card you flip with the arrow keys, then acts on your verdict. | Nutlope/ | 211 | — | ~3.5k | Automated safety check: Pass | MIT | 1 mo ago |
| 10 | Use with the dstack skill for model-serving work when the image, serving command, resources, backend/fleet choice, or service behavior is not proven. | dstackai/ | 2.3k | — | ~1.6k | Automated safety check: Pass | MPL-2.0 | today |
| 11 | 11.HTML Create or redesign self-contained single-file HTML artifacts with a visual direction shaped by the user's brief, project, and subject. | plannotator/ | 3.6k | — | ~1.6k | Automated safety check: Pass | MIT | 23 days ago |
| 12 | Use the Gemini CLI to consult Gemini and delegate coding tasks for prototyping, debugging, and code review. | appautomaton/ | 457 | 1 repo | ~1.1k | Automated safety check: Pass | MIT | 24 days ago |
| 13 | 13.Digikey Search DigiKey for electronic components and download datasheets — primary source for prototype orders and the preferred API method for fetching datasheets. | aklofas/ | 1.3k | 1 repo | ~4.5k | Automated safety check: Pass | MIT | yesterday |
| 14 | A skill your agent uses to generate well-branded interfaces and assets for fast-agent, either for production or throwaway prototypes/mocks/etc. | evalstate/ | 3.9k | — | ~220 | Automated safety check: Pass | Apache-2.0 | 2 days ago |
| 15 | Generates parametric, print-ready 3D models in Python and exports them as STL files sized to real connectors, devices and mounting hardware. | flowful-ai/ | 655 | — | ~5.3k | Automated safety check: Pass | CC-BY-NC-4.0 | 2 mo ago |
| 16 | Builds a website page by page with Stitch in an autonomous loop, passing a baton file from one iteration to the next that names the next page and prompt. | google-labs-code/ | 8.4k | 5 repos | ~2.6k | Automated safety check: Notes | Apache-2.0 | 1 mo ago |
| 17 | Delegates coding tasks to Gemini CLI for prototyping, debugging, and code review. | haoyu-haoyu/ | 109 | — | ~521 | Automated safety check: Pass | MIT | 5 mo ago |
| 18 | Builds a risk-matched whitebox or an approved production game candidate from a game design for its target runtime, with replayable evidence. | zenstory-ai/ | 832 | — | ~661 | Automated safety check: Pass | MIT | 4 days ago |
| 19 | 19.S2 Docs Look up Spectrum 2 (S2) component documentation, design guidelines, and usage patterns when building with React Spectrum or Spectrum Web Components. | adobe/ | 155 | — | ~868 | Automated safety check: Pass | Apache-2.0 | 5 days ago |
| 20 | A skill your agent uses to generate well-branded interfaces and assets for Baby Menu, either for production or throwaway prototypes/mocks/etc. | kunchenguid/ | 233 | — | ~1.1k | Automated safety check: Pass | MIT | 12 days ago |
| 21 | Explores a feature idea through HTML mocks that match the project's existing UI, keeping every earlier version and logging each requested tweak in a context file. | imbue-ai/ | 400 | — | ~677 | Automated safety check: Pass | AGPL-3.0 | today |
| 22 | Converts a working code prototype into a structured Figma file with one frame per interaction state, mapped to your design system and annotated with transitions. | alima-max/ | 140 | — | ~7.8k | Automated safety check: Pass | MIT | 2 mo ago |
| 23 | Direct-invocation specialist for polished, responsive, self-contained HTML mockups and interactive prototypes grounded in the user's conversation, product context, and design language. | plannotator/ | 3.6k | — | ~1.5k | Automated safety check: Pass | MIT | 23 days ago |
| 24 | Delegate tasks to Google's Antigravity CLI (agy) for prototyping, debugging, code review, and research. | appautomaton/ | 131 | — | ~2.4k | Automated safety check: Pass | No licence | 24 days ago |
| 25 | 25.Prototype Build a throwaway prototype to flesh out a design — a runnable terminal app for state/business-logic questions, or several radically different UI variations toggleable from one route. | fossasia/ | 1.6k | 34 repos | ~755 | Automated safety check: Pass | Apache-2.0 | 2 days ago |
| 26 | 26.Vibes Self-contained app generator — invoke this skill directly, do not decompose into sub-steps. | popmechanic/ | 135 | — | ~2.6k | Automated safety check: Notes | MIT | 2 mo ago |
| 27 | Expert patterns for simplifying 3D games to 2D including dimension reduction strategies, 2.5D fake-depth, isometric ports, camera flattening, physics conversion, 3D-to-sprite art pipeline, and… | thedivergentai/ | 803 | — | ~4.5k | Automated safety check: Pass | LGPL-3.0 | 28 days ago |
| 28 | Builds a clickable low-fidelity prototype of one flow from a product brief during discovery, with simulated data and browser checks, before detailed design. | open-mercato/ | 221 | — | ~1.9k | Automated safety check: Pass | MIT | 2 days ago |
| 29 | Delegate tasks to Claude Code CLI for prototyping, debugging, and code review. | appautomaton/ | 131 | — | ~2.5k | Automated safety check: Pass | No licence | 24 days ago |
| 30 | Guides building Gradio web UIs and ML demos in Python, covering Interface, Blocks, ChatInterface, event listeners, layouts and chatbots. | huggingface/ | 11k | 4 repos | ~6.2k | Automated safety check: Pass | Apache-2.0 | 6 days ago |
| 31 | 31.PRP Spike Settles a feasibility question with the smallest throwaway build that could disprove it, in an isolated worktree, ending in a verdict backed by evidence instead of a PR. | Wirasm/ | 2.3k | — | ~3.8k | Automated safety check: Pass | MIT | 5 days ago |
| 32 | Builds a single-file HTML explorer with visual controls, a live preview and a copyable prompt, using one of six templates chosen to fit the topic. | anthropics/ | 37k | 1 repo | ~949 | Automated safety check: Pass | Apache-2.0 | today |
| 33 | 33.Andrew Ng Applies the reasoning, principles, and frameworks of Andrew Ng (machine learning pioneer, co-founder of Coursera and DeepLearning.AI, Stanford University, and former Google Brain lead). | K-Dense-AI/ | 282 | — | ~1.5k | Automated safety check: Pass | MIT | 1 mo ago |
| 34 | Delegate tasks to Codex CLI for prototyping, debugging, code review, implementation handoff, cross-model second opinions, and multi-turn Codex sessions via SESSIONID. | appautomaton/ | 131 | — | ~3.4k | Automated safety check: Pass | No licence | 24 days ago |
| 35 | Activate this skill when authoring DataJunction (DJ) nodes via the REST API directly (curl, HTTP clients) — typically for exploration, ad-hoc prototyping, or namespaces that aren't repo-backed. | DataJunction/ | 161 | — | ~1.8k | Automated safety check: Pass | MIT | yesterday |
| 36 | A skill your agent uses to generate well-branded interfaces and assets for Honeycomb (shared AI agent memory, a Legion Code × Activeloop product), either for production or throwaway… | legioncodeinc/ | 110 | — | ~571 | Automated safety check: Pass | AGPL-3.0 | 3 days ago |
| 37 | Asks one clarifying question at a time, then builds two or three single-file HTML prototypes checked across phone, tablet, and desktop widths. | huiliyi37/ | 1.1k | — | ~415 | Automated safety check: Pass | Apache-2.0 | 2 days ago |
| 38 | 38.Langchain Framework for building LLM-powered applications with agents, chains, and RAG. | Orchestra-Research/ | 13k | 2 repos | ~3.2k | Automated safety check: Pass | MIT | 3 mo ago |
| 39 | 39.PRP Spike Settles a feasibility or fit question by building the smallest throwaway artifact that could prove it wrong, in an isolated worktree, ending in a PROVEN, DISPROVEN or CONDITIONAL verdict. | Wirasm/ | 2.3k | — | ~3.8k | Automated safety check: Pass | MIT | 5 days ago |
| 40 | Run a structured 5-day process to prototype, test, and validate product ideas with real users. | wondelai/ | 2.4k | — | ~3.8k | Automated safety check: Pass | MIT | 26 days ago |
| 41 | 41.Writing Spec Collaboratively write a feature spec with the developer. An agent skill from bartstc/vite-ts-react-template. | bartstc/ | 122 | — | ~3.4k | Automated safety check: Pass | MIT | yesterday |
| 42 | 42.Beava Design A skill your agent uses to generate well-branded interfaces and assets for beava (beava.dev, an open-source single-binary feature server for stream processing), either for production or throwaway… | beava-dev/ | 138 | — | ~443 | Automated safety check: Pass | Apache-2.0 | 4 mo ago |
| 43 | Idea to AI-generated prototype to customer validation to engineering handoff. | borghei/ | 874 | — | ~3.6k | Automated safety check: Pass | MIT | today |
| 44 | Delegate tasks to Grok CLI (xAI) for prototyping, debugging, code review, research, and cross-model second opinions. | appautomaton/ | 131 | — | ~2.4k | Automated safety check: Pass | No licence | 24 days ago |
| 45 | 45.Nxv Design A skill your agent uses to generate well-branded interfaces and assets for nxv (Nix Version Index) — either for production or throwaway prototypes/mocks. | utensils/ | 136 | — | ~607 | Automated safety check: Pass | MIT | 1 mo ago |
| 46 | Provision instant temporary Postgres databases via Claimable Postgres by Neon (pg.new). | henryalouf/ | 155 | — | ~2.4k | Automated safety check: Notes | MIT | 4 mo ago |
| 47 | Help users build functional product prototypes from natural language or visual mocks using AI coding tools. | RefoundAI/ | 1.4k | — | ~1.2k | Automated safety check: Pass | MIT | 2 mo ago |
| 48 | Settles stalled design questions by building a throwaway artifact: either a pure logic module in a clickable shell, or three structurally different UI variants. | Yeachan-Heo/ | 40k | — | ~1.4k | Automated safety check: Pass | MIT | today |
Questions, answered from the data.
What is the best prototyping skill?
LobeHub Interactive Prototype from lobehub/lobehub ranks first of the 113 prototyping skills listed here, with the highest score: its repository has 83k GitHub stars, its SKILL.md loads about 1.6k tokens and it passes the automated safety check with no findings. Next come Vuetify Playground and Native Feel Cross Platform Desktop.
Which prototyping skills are official?
4 of the 113 prototyping skills are official, published by the vendor's own GitHub organization: Stitch Build Loop, Gradio App Builder, Interactive HTML Playground Builder and Create Technical Spike.
How are these skills ranked?
By Skill Navigator score, which combines the GitHub stars of the skill's repository (shared across that repo's skills and discounted for large collections), how many other GitHub owners carry a copy of the skill, and automated SKILL.md quality checks, minus penalties for safety-check warnings and for each further skill from the same repository. Skills that fail the safety check are not listed.
Explore related skills
Category
More topics in Development
- Pull requests1,927
- Refactoring1,154
- Debugging1,154
- Changelog and release notes1,147
- Code review1,053
- Technical documentation998
- Linting and formatting830
- Git workflow809
- Diagrams801
- Project scaffolding742
- Root cause analysis610
- Code quality579
- Architecture decision records562
- Commit messages556
- Git worktrees528
- Performance optimization440
- Design patterns408
- Error handling317
- Type safety301
- Dependency management285
- Software architecture280
- Monorepo tooling267
- Async programming243
- Issue triage234