Video Script Yijia

Get ready-to-use scripts ready to post, without touching a single slider. Upload your text or brief (MP4, MOV, TXT, DOCX, up to 200MB), say something like "w...

Security Scan

The skill appears to do what it says — it talks to a nemovideo cloud API using a NEMO_TOKEN and uploads user files for cloud rendering — but there are a few small metadata/instruction mismatches you should be aware of before installing.

Purpose & Capability

The skill's name/description (video script + render) aligns with its runtime actions: it requires a NEMO_TOKEN, creates sessions, uploads files, and requests renders from mega-api-prod.nemovideo.ai. One inconsistency: the registry metadata in the skill manifest reported no required config paths, but the SKILL.md frontmatter lists a config path (~/.config/nemovideo/). This mismatch should be clarified (does the skill read/write that config directory?).

Instruction Scope

SKILL.md gives concrete API calls for auth, session creation, SSE messaging, uploads, and export polling — all within the stated purpose. It instructs the agent to: use NEMO_TOKEN if present, generate an anonymous token if not, save session_id and (implicitly) tokens, read the SKILL.md frontmatter, and detect install path to set an attribution header. These instructions legitimately touch local files you choose to upload and may read the skill file or install path; they do not instruct arbitrary system-wide data collection. Still, the agent will transmit uploaded files and session tokens to the external nemovideo API, so uploaded content and tokens are exfiltrated to that service by design.

Install Mechanism

No install spec or code files are present (instruction-only). That minimizes on-disk install risk — nothing is downloaded or executed beyond the agent following the written instructions at runtime.

Credentials

The only required environment credential is NEMO_TOKEN (declared as primaryEnv), which is appropriate for a third-party rendering API. The SKILL.md also references a local config path (~/.config/nemovideo/) which was not listed in the registry metadata; this is a minor inconsistency and should be confirmed because the skill may read/write session tokens or cached credentials there.

Persistence & Privilege

The skill is not force-included (always:false) and uses normal autonomous invocation settings. It instructs saving session state/tokens (expected for session continuity) but does not request elevated platform privileges or modification of other skills. Verify where session tokens are stored (e.g., the referenced config path) if you want to control persistence.

Assessment

This skill is coherent with its stated purpose but will send any uploaded files and session tokens to mega-api-prod.nemovideo.ai. Before installing: (1) Confirm whether the skill will read/write ~/.config/nemovideo/ (manifest mismatch). (2) Only upload non-sensitive media/content you consent to send to the external service. (3) If you already have a NEMO_TOKEN in your environment, recognize the skill will use it — ensure that token's scope is appropriate. (4) If you prefer not to expose a permanent token, let the skill use the anonymous-token flow and revoke or delete any stored session tokens after use. (5) Verify the API domain and consider network-level controls or review of outgoing requests if you need to limit exposure.

Getting Started

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

Try saying:

• "generate my text or brief"
• "export 1080p MP4"
• "write a video script for a"

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.

Video Script Yijia — Generate Video Scripts with AI

Drop your text or brief in the chat and tell me what you need. I'll handle the AI script generation on cloud GPUs — you don't need anything installed locally.

Here's a typical use: you send a a product description or topic brief for a 60-second video, ask for write a video script for a 90-second explainer about our new fitness app, and about 20-40 seconds later you've got a MP4 file ready to download. The whole thing runs at 1080p by default.

One thing worth knowing — providing a clear target audience in your brief produces tighter, more relevant scripts.

Matching Input to Actions

User prompts referencing video script yijia, 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.

Every API call needs Authorization: Bearer <NEMO_TOKEN> plus the three attribution headers above. If any header is missing, exports return 402.

Skill attribution — read from this file's YAML frontmatter at runtime:

• X-Skill-Source: video-script-yijia
• X-Skill-Version: from frontmatter version
• X-Skill-Platform: detect from install path (~/.clawhub/ → clawhub, ~/.cursor/skills/ → cursor, else 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 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

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)

Tips and Tricks

The backend processes faster when you're specific. Instead of "make it look better", try "write a video script for a 90-second explainer about our new fitness app" — concrete instructions get better results.

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

Export your final video as MP4 for widest platform compatibility.

Common Workflows

Quick edit: Upload → "write a video script for a 90-second explainer about our new fitness app" → 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.