Ai Copywriter Video

Get script-overlaid videos ready to post, without touching a single slider. Upload your raw video footage (MP4, MOV, AVI, WebM, up to 500MB), say something l...

Security Scan

The skill's declared purpose (generating and overlaying captions/scripts on uploaded videos) matches its runtime instructions and required credential (NEMO_TOKEN); nothing requested is disproportionate, though there is a small metadata mismatch to review and you should be aware that uploads and tokens are sent to an external Nemo backend.

Purpose & Capability

Name/description (AI copywriting + overlaying captions on video) align with the API endpoints and actions described in SKILL.md (upload, SSE-based generation, render/export). The single required credential (NEMO_TOKEN) is appropriate for a cloud video service.

Instruction Scope

Instructions are scoped to the Nemo backend: create/use session, upload files or URLs, stream SSE messages, poll render status, return download URL. The skill tells the agent to read its own YAML frontmatter and detect install path to populate X-Skill-Platform headers, and it will POST to an anonymous-token endpoint if no NEMO_TOKEN is present. These behaviors are explainable for attribution and fallback auth, but they do mean user video data and generated tokens are sent to the external API.

Install Mechanism

No install spec and no code files — instruction-only skill. No binaries or archives are downloaded or written to disk by an installer, which minimizes install-time risk.

Credentials

The skill only requires one credential (NEMO_TOKEN), which is appropriate. Metadata also lists a config path (~/.config/nemovideo/) that the SKILL.md does not actually reference; this mismatch is minor but should be clarified by the author. The runtime also requires access to any files the user uploads (video paths) — expected for this purpose.

Persistence & Privilege

always:false and normal model invocation. The skill does not request elevated/persistent system privileges or modification of other skills. It only asks to read its own frontmatter/paths for attribution.

Assessment

This skill appears to do what it says: it sends your uploaded video to Nemo's cloud rendering service and uses a NEMO_TOKEN to authenticate. Before installing or using it, consider: 1) Any video you upload will be transmitted to an external service (mega-api-prod.nemovideo.ai) — do not upload sensitive footage you wouldn't want processed off‑site. 2) Prefer supplying your own NEMO_TOKEN rather than relying on the anonymous-token fallback if you want account-level auditing or control. 3) Ask the developer to explain why metadata lists ~/.config/nemovideo/ when the runtime docs don't reference that path. 4) Check Nemo's privacy/retention policy if you care about how long uploaded media or generated text is stored. If those items are acceptable, the skill's requests and instructions are proportionate to its stated purpose.

Getting Started

Share your raw video footage and I'll get started on AI script and caption generation. Or just tell me what you're thinking.

Try saying:

• "generate my raw video footage"
• "export 1080p MP4"
• "write and overlay a sales script"

Getting Connected

Before handling any user request, establish a connection to the backend API. Show a brief status like "Connecting...".

If NEMO_TOKEN is in the environment, use it directly and create a session. Otherwise, acquire a free starter token:

• Generate a UUID as client identifier
• POST to https://mega-api-prod.nemovideo.ai/api/auth/anonymous-token with the X-Client-Id header
• The response includes a token with 100 free credits valid for 7 days — use it as NEMO_TOKEN

Then create a session by POSTing to https://mega-api-prod.nemovideo.ai/api/tasks/me/with-session/nemo_agent with Bearer authorization and body {"task_name":"project","language":"en"}. The session_id in the response is needed for all following requests.

Tell the user you're ready. Keep the technical details out of the chat.

AI Copywriter Video — Generate Copy and Captions for Videos

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

Here's a typical use: you send a a 60-second product demo video, ask for write and overlay a sales script as captions for my product video, and about 30-60 seconds later you've got a MP4 file ready to download. The whole thing runs at 1080p by default.

One thing worth knowing — shorter videos under 90 seconds produce tighter, more focused AI copy.

Matching Input to Actions

User prompts referencing ai copywriter video, 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.

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

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

All requests must include: Authorization: Bearer <NEMO_TOKEN>, X-Skill-Source, X-Skill-Version, X-Skill-Platform. Missing attribution headers will cause export to fail with 402.

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.

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.

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

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)

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

Common Workflows

Quick edit: Upload → "write and overlay a sales script as captions for my product video" → Download MP4. Takes 30-60 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 "write and overlay a sales script as captions for my product video" — concrete instructions get better results.

Max file size is 500MB. Stick to MP4, MOV, AVI, WebM for the smoothest experience.

Export as MP4 for widest compatibility across social and ad platforms.