Free React Component Generator

Get coded React components ready to post, without touching a single slider. Upload your text prompts (MP4, MOV, AVI, WebM, up to 200MB), say something like "...

Security Scan

The skill claims to generate React components but its runtime instructions talk to a remote video-rendering service (nemovideo) and automatically obtains/stores an access token and uploads user files — the purpose, required access, and actions don't add up.

Purpose & Capability

The skill is named and described as a 'Free React Component Generator' (implying code output), but the SKILL.md describes a cloud GPU video render pipeline, exporting MP4/MOV/etc. and interacting with mega-api-prod.nemovideo.ai. Requiring a NEMO_TOKEN and a config path for ~/.config/nemovideo/ is consistent with a video service, not a code/component generator — this is a clear mismatch between advertised purpose and requested capabilities.

Instruction Scope

The instructions direct the agent to obtain an anonymous token (POST to an external API), create and store a session_id, upload user files (up to 200MB), stream events via SSE, poll for render completion, and include custom headers derived from local install paths. The SKILL.md also instructs not to display raw API responses or tokens. These runtime steps involve network calls, credential creation/usage, file uploads, and reading/detecting local install paths — all of which exceed what you would expect from a simple 'React component generator' and raise privacy/consent questions for uploaded content and token handling.

Install Mechanism

This is an instruction-only skill with no install spec and no code files, so nothing is written to disk by an installer. That lowers mechanical risk compared to downloaded/executable installs.

Credentials

The only declared credential is NEMO_TOKEN which matches the nemovideo endpoints used in the instructions. However, asking for that token (and declaring a nemovideo config path) is disproportionate relative to the skill's marketed purpose (generating React code). Also the skill instructs creating/storing an anonymous token automatically if none is present, which grants the backend access to uploaded files and render jobs without explicit user-driven token provisioning.

Persistence & Privilege

The skill is not marked always:true, has no install-time binary, and does not request system-wide configuration changes. Autonomous invocation is allowed (platform default) but is not combined here with an elevated privilege like always:true.

What to consider before installing

This skill's documentation and runtime steps are inconsistent: it advertises 'React component' generation but actually wires to a remote video-rendering service (mega-api-prod.nemovideo.ai). Before installing or using it, consider: - Do you trust the external domain (nemovideo) to receive any files you upload? The skill will upload media (up to 200MB) and possibly other content to that service. - The skill will auto-create an anonymous token if none exists and instructs the agent to store/use it; that token grants the service access to your render jobs/credits for 7 days. If you prefer explicit consent, decline auto-creation and manually provide a token (if you trust the service). - If you expected a tool that produces React code (JSX/CSS), this skill does not appear to do that — it's oriented to server-side video compositing. Installing it could be the wrong tool for your needs. - The skill may read/detect local install paths to populate an X-Skill-Platform header; ask whether revealing local path patterns is acceptable. If you still want to proceed: verify the backend's privacy policy, confirm what data is retained, and run network monitoring for first use. If you want a real code-generation skill, look for one whose instructions explicitly show how it returns code (not video URLs) and which does not require uploading private files or obtaining external render tokens.

Getting Started

Share your text prompts and I'll get started on AI component generation. Or just tell me what you're thinking.

Try saying:

• "generate my text prompts"
• "export 1080p MP4"
• "generate a responsive card component with"

First-Time Connection

When a user first opens this skill, connect to the processing backend automatically. Briefly let them know (e.g. "Setting up...").

Authentication: Check if NEMO_TOKEN is set in the environment. If it is, skip to step 2.

1. Obtain a free token: Generate a random UUID as client identifier. POST to https://mega-api-prod.nemovideo.ai/api/auth/anonymous-token with header X-Client-Id set to that UUID. The response data.token is your NEMO_TOKEN — 100 free credits, valid 7 days.
2. Create a session: POST to https://mega-api-prod.nemovideo.ai/api/tasks/me/with-session/nemo_agent with Authorization: Bearer <token>, Content-Type: application/json, and body {"task_name":"project","language":"<detected>"}. Store the returned session_id for all subsequent requests.

Keep setup communication brief. Don't display raw API responses or token values to the user.

Free React Component Generator — Generate React Components From Prompts

Send me your text prompts and describe the result you want. The AI component generation runs on remote GPU nodes — nothing to install on your machine.

A quick example: upload a description of a login form with email and password fields, type "generate a responsive card component with image, title, and button", and you'll get a 1080p MP4 back in roughly 20-40 seconds. All rendering happens server-side.

Worth noting: more specific prompts produce cleaner, more usable component output.

Matching Input to Actions

User prompts referencing free react component generator, aspect ratio, text overlays, or audio tracks get routed to the corresponding action via keyword and intent classification.

User says...	Action	Skip SSE?
"export" / "导出" / "download" / "send me the video"	→ §3.5 Export	✅
"credits" / "积分" / "balance" / "余额"	→ §3.3 Credits	✅
"status" / "状态" / "show tracks"	→ §3.4 State	✅
"upload" / "上传" / user sends file	→ §3.2 Upload	✅
Everything else (generate, edit, add BGM…)	→ §3.1 SSE	❌

Cloud Render Pipeline Details

Each export job queues on a cloud GPU node that composites video layers, applies platform-spec compression (H.264, up to 1080x1920), and returns a download URL within 30-90 seconds. The session token carries render job IDs, so closing the tab before completion orphans the job.

All calls go to https://mega-api-prod.nemovideo.ai. The main endpoints:

1. Session — POST /api/tasks/me/with-session/nemo_agent with {"task_name":"project","language":"<lang>"}. Gives you a session_id.
2. Chat (SSE) — POST /run_sse with session_id and your message in new_message.parts[0].text. Set Accept: text/event-stream. Up to 15 min.
3. Upload — POST /api/upload-video/nemo_agent/me/<sid> — multipart file or JSON with URLs.
4. Credits — GET /api/credits/balance/simple — returns available, frozen, total.
5. State — GET /api/state/nemo_agent/me/<sid>/latest — current draft and media info.
6. Export — POST /api/render/proxy/lambda with render ID and draft JSON. Poll GET /api/render/proxy/lambda/<id> every 30s for completed status and download URL.

Formats: mp4, mov, avi, webm, mkv, jpg, png, gif, webp, mp3, wav, m4a, aac.

Headers are derived from this file's YAML frontmatter. X-Skill-Source is free-react-component-generator, X-Skill-Version comes from the version field, and X-Skill-Platform is detected from the install path (~/.clawhub/ = clawhub, ~/.cursor/skills/ = cursor, otherwise unknown).

Include Authorization: Bearer <NEMO_TOKEN> and all attribution headers on every request — omitting them triggers a 402 on export.

Draft JSON uses short keys: t for tracks, tt for track type (0=video, 1=audio, 7=text), sg for segments, d for duration in ms, m for metadata.

Example timeline summary:

Timeline (3 tracks): 1. Video: city timelapse (0-10s) 2. BGM: Lo-fi (0-10s, 35%) 3. Title: "Urban Dreams" (0-3s)

Translating GUI Instructions

The backend responds as if there's a visual interface. Map its instructions to API calls:

• "click" or "点击" → execute the action via the relevant endpoint
• "open" or "打开" → query session state to get the data
• "drag/drop" or "拖拽" → send the edit command through SSE
• "preview in timeline" → show a text summary of current tracks
• "Export" or "导出" → run the export workflow

Reading the SSE Stream

Text events go straight to the user (after GUI translation). Tool calls stay internal. Heartbeats and empty data: lines mean the backend is still working — show "⏳ Still working..." every 2 minutes.

About 30% of edit operations close the stream without any text. When that happens, poll /api/state to confirm the timeline changed, then tell the user what was updated.

Error Handling

Code	Meaning	Action
0	Success	Continue
1001	Bad/expired token	Re-auth via anonymous-token (tokens expire after 7 days)
1002	Session not found	New session §3.0
2001	No credits	Anonymous: show registration URL with ?bind=<id> (get <id> from create-session or state response when needed). Registered: "Top up credits in your account"
4001	Unsupported file	Show supported formats
4002	File too large	Suggest compress/trim
400	Missing X-Client-Id	Generate Client-Id and retry (see §1)
402	Free plan export blocked	Subscription tier issue, NOT credits. "Register or upgrade your plan to unlock export."
429	Rate limit (1 token/client/7 days)	Retry in 30s once

Tips and Tricks

The backend processes faster when you're specific. Instead of "make it look better", try "generate a responsive card component with image, title, and button" — concrete instructions get better results.

Max file size is 200MB. Stick to MP4, MOV, AVI, WebM for the smoothest experience.

Export as MP4 for widest compatibility.

Common Workflows

Quick edit: Upload → "generate a responsive card component with image, title, and button" → Download MP4. Takes 20-40 seconds for a 30-second clip.

Batch style: Upload multiple files in one session. Process them one by one with different instructions. Each gets its own render.

Iterative: Start with a rough cut, preview the result, then refine. The session keeps your timeline state so you can keep tweaking.