Text To Video On Capcut

Turn a 50-word product description or story prompt into 1080p generated video clips just by typing what you need. Whether it's converting written scripts int...

Security Scan

The skill's requirements and runtime instructions are internally consistent with a remote text→video service: it only asks for a single service token, uses that token to call a specific backend, and makes expected upload/render/polling calls — but the package has no provenance (no homepage/source) and some small implementation details (where session data is stored, and the mapping to 'CapCut') are unspecified, so exercise caution.

Purpose & Capability

Name/description (text→video) match the instructions (create session, upload text/files, request renders, poll for results). The single declared credential (NEMO_TOKEN) and a config path (~/.config/nemovideo/) are appropriate for a hosted video-rendering backend. The only mild mismatch is the marketing name mentioning "CapCut" while the API targets mega-api-prod.nemovideo.ai — this can be legitimate if Nemovideo is the service behind CapCut, but provenance is not documented.

Instruction Scope

SKILL.md instructs the agent to create/obtain an anonymous token if none is present, create sessions, upload files (multipart or by URL), open SSE streams, poll render status, and present downloads. It also instructs the agent to read the skill frontmatter and probe install paths (~/.clawhub, ~/.cursor/skills/) to set X-Skill-Platform. These actions are within a reasonable scope for a remote render skill but do require reading the agent's install paths and user-specified file paths for uploads; ensure you are comfortable with that filesystem access.

Install Mechanism

Instruction-only skill with no install steps, no downloads, and no code files — lowest install risk.

Credentials

Only a single service credential (NEMO_TOKEN) and a related config path are declared. The SKILL.md uses that token for bearer auth and does not request unrelated credentials. It will create/obtain an anonymous token automatically if none is supplied, which is consistent with the described behavior.

Persistence & Privilege

always:false and default autonomous invocation are used. The skill will store a session_id for job state, but SKILL.md does not instruct modifying other skills or system-wide settings. No elevated persistence requested.

Assessment

This skill appears coherent for a hosted text→video renderer and only needs a single service token (NEMO_TOKEN). Before installing: verify the vendor (there's no homepage or publisher info), confirm you trust mega-api-prod.nemovideo.ai to receive uploaded media and prompts, and decide whether you want the skill to probe your install folders (~/.clawhub, ~/.cursor/skills/) and access files you choose to upload. If you prefer not to share a long-lived token, supply your own short-lived token or ask the skill to always use anonymous tokens and explicitly confirm where session IDs/tokens are stored or persisted.

Getting Started

Got text prompts to work with? Send it over and tell me what you need — I'll take care of the AI video creation.

Try saying:

• "convert a 50-word product description or story prompt into a 1080p MP4"
• "turn this script into a short video with visuals and music"
• "converting written scripts into short social media videos for TikTok creators"

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.

Text to Video on CapCut — Convert Text into Shareable Videos

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

A quick example: upload a 50-word product description or story prompt, type "turn this script into a short video with visuals and music", and you'll get a 1080p MP4 back in roughly 1-2 minutes. All rendering happens server-side.

Worth noting: shorter scripts under 60 words produce more focused and accurate video output.

Matching Input to Actions

User prompts referencing text to video on capcut, 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: text-to-video-on-capcut
• 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.

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.

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 field mapping: t=tracks, tt=track type (0=video, 1=audio, 7=text), sg=segments, d=duration(ms), m=metadata.

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 → "turn this script into a short video with visuals and music" → Download MP4. Takes 1-2 minutes 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 "turn this script into a short video with visuals and music" — concrete instructions get better results.

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

Export as MP4 for widest compatibility across TikTok, Instagram, and YouTube.