Prompt Generator Skill Online

Get AI-generated prompts ready to post, without touching a single slider. Upload your text description (MP4, MOV, TXT, WebM, up to 200MB), say something like...

Security Scan

The skill's claims and runtime instructions are internally consistent: it needs a single NEMO_TOKEN and talks to a single external API to upload user media and request renders — but it will send user files to a third‑party service and there are a few small metadata inconsistencies to be aware of.

Purpose & Capability

Name and description (generate video prompts / render pipeline) align with the declared runtime actions: the SKILL.md exclusively describes authenticating with nemo (NEMO_TOKEN or anonymous token), creating sessions, uploading files, SSE interactions, and exporting rendered media. Requiring a NEMO_TOKEN is appropriate for this purpose.

Instruction Scope

Instructions direct the agent to obtain or reuse a NEMO_TOKEN, create sessions, upload user files (up to 200MB), stream SSE messages, poll render status, and return download URLs — all consistent with a cloud rendering prompt tool. The skill will POST user media and metadata to https://mega-api-prod.nemovideo.ai; that is expected but a privacy consideration. The SKILL.md also describes detecting the agent's install path for an X-Skill-Platform header, which implies reading environment/paths; this is plausible for attribution but expands the agent’s filesystem awareness slightly.

Install Mechanism

Instruction-only skill with no install spec or code files; nothing is written to disk by an install step. This is low-risk from an installation standpoint.

Credentials

Only one credential is required (NEMO_TOKEN) which is proportional to the described cloud API usage. Minor inconsistency: the SKILL.md frontmatter declares a config path (~/.config/nemovideo/) while the registry metadata earlier listed no required config paths — this discrepancy should be clarified. Otherwise no unrelated secrets or broad credential access are requested.

Persistence & Privilege

The skill does not request persistent 'always' inclusion and does not modify other skills or system-wide settings. Autonomous invocation is allowed by default on the platform but that is normal and not a unique concern here.

Assessment

This skill sends any uploaded media and prompts to a third‑party API at mega-api-prod.nemovideo.ai and requires a NEMO_TOKEN (or will obtain a short‑lived anonymous token). If you care about privacy or proprietary content, do not upload sensitive media. Note the SKILL.md mentions reading an install path (used to set an attribution header) and a config directory (~/.config/nemovideo/) in its frontmatter — registry metadata did not list that path, so ask the publisher to clarify what local files the skill will access. Because the skill’s source is unknown, verify the provider and privacy policy before using it with private or confidential content. Finally, avoid pasting other secrets into prompts; the skill only needs NEMO_TOKEN for operation.

Getting Started

Send me your text description and I'll handle the AI prompt generation. Or just describe what you're after.

Try saying:

• "generate a short description of a sunset beach scene into a 1080p MP4"
• "generate a detailed video prompt for a cinematic ocean sunset with slow camera movement"
• "generating detailed video prompts from simple text ideas for content creators"

Automatic Setup

On first interaction, connect to the processing API before doing anything else. Show a brief status like "Setting things up...".

Token: If NEMO_TOKEN environment variable is already set, use it and skip to Session below.

Free token: Generate a UUID as client identifier, then POST to https://mega-api-prod.nemovideo.ai/api/auth/anonymous-token with header X-Client-Id: <uuid>. The response field data.token becomes your NEMO_TOKEN (100 credits, 7-day expiry).

Session: POST to https://mega-api-prod.nemovideo.ai/api/tasks/me/with-session/nemo_agent with Bearer auth and body {"task_name":"project"}. Save session_id from the response.

Confirm to the user you're connected and ready. Don't print tokens or raw JSON.

Prompt Generator Skill Online — Generate Video Prompts Instantly

This tool takes your text description and runs AI prompt generation through a cloud rendering pipeline. You upload, describe what you want, and download the result.

Say you have a short description of a sunset beach scene and want to generate a detailed video prompt for a cinematic ocean sunset with slow camera movement — the backend processes it in about 10-30 seconds and hands you a 1080p MP4.

Tip: more specific input descriptions produce more usable and detailed prompts.

Matching Input to Actions

User prompts referencing prompt generator skill online, 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.

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

Headers are derived from this file's YAML frontmatter. X-Skill-Source is prompt-generator-skill-online, 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).

API base: https://mega-api-prod.nemovideo.ai

Create session: POST /api/tasks/me/with-session/nemo_agent — body {"task_name":"project","language":"<lang>"} — returns task_id, session_id.

Send message (SSE): POST /run_sse — body {"app_name":"nemo_agent","user_id":"me","session_id":"<sid>","new_message":{"parts":[{"text":"<msg>"}]}} with Accept: text/event-stream. Max timeout: 15 minutes.

Upload: POST /api/upload-video/nemo_agent/me/<sid> — file: multipart -F "files=@/path", or URL: {"urls":["<url>"],"source_type":"url"}

Credits: GET /api/credits/balance/simple — returns available, frozen, total

Session state: GET /api/state/nemo_agent/me/<sid>/latest — key fields: data.state.draft, data.state.video_infos, data.state.generated_media

Export (free, no credits): POST /api/render/proxy/lambda — body {"id":"render_<ts>","sessionId":"<sid>","draft":<json>,"output":{"format":"mp4","quality":"high"}}. Poll GET /api/render/proxy/lambda/<id> every 30s until status = completed. Download URL at output.url.

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

Error Codes

• 0 — success, continue normally
• 1001 — token expired or invalid; re-acquire via /api/auth/anonymous-token
• 1002 — session not found; create a new one
• 2001 — out of credits; anonymous users get a registration link with ?bind=<id>, registered users top up
• 4001 — unsupported file type; show accepted formats
• 4002 — file too large; suggest compressing or trimming
• 400 — missing X-Client-Id; generate one and retry
• 402 — free plan export blocked; not a credit issue, subscription tier
• 429 — rate limited; wait 30s and retry once

Backend Response Translation

The backend assumes a GUI exists. Translate these into API actions:

Backend says	You do
"click [button]" / "点击"	Execute via API
"open [panel]" / "打开"	Query session state
"drag/drop" / "拖拽"	Send edit via SSE
"preview in timeline"	Show track summary
"Export button" / "导出"	Execute export workflow

SSE Event Handling

Event	Action
Text response	Apply GUI translation (§4), present to user
Tool call/result	Process internally, don't forward
heartbeat / empty data:	Keep waiting. Every 2 min: "⏳ Still working..."
Stream closes	Process final response

~30% of editing operations return no text in the SSE stream. When this happens: poll session state to verify the edit was applied, then summarize changes to the user.

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)

Common Workflows

Quick edit: Upload → "generate a detailed video prompt for a cinematic ocean sunset with slow camera movement" → Download MP4. Takes 10-30 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.

Tips and Tricks

The backend processes faster when you're specific. Instead of "make it look better", try "generate a detailed video prompt for a cinematic ocean sunset with slow camera movement" — concrete instructions get better results.

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

Export as MP4 for widest compatibility.