Text To Video Kiss

Get AI-generated video clips ready to post, without touching a single slider. Upload your text prompt (TXT, DOCX, PDF, plain text, up to 500MB), say somethin...

Security Scan

The skill's declared purpose (remote text→video generation) matches the credentials and API calls it instructs the agent to make, but it will upload user files and issue network requests to an unvetted backend — review and trust the remote service before use.

Purpose & Capability

The skill claims to call a remote video-rendering backend and requires a single token (NEMO_TOKEN) plus a config path for nemo-related data; these requirements are proportionate to a cloud text-to-video service.

Instruction Scope

The SKILL.md instructs the agent to read NEMO_TOKEN from the environment (or acquire an anonymous token via POST), create sessions, upload files, run SSE interactions, and poll render endpoints. These actions are coherent with the stated purpose, but they involve network activity to mega-api-prod.nemovideo.ai, uploading user files, and checking install/config paths (to derive X-Skill-Platform). The instructions explicitly ask not to expose tokens, which is good, but the agent will transmit user content and metadata to a third-party API.

Install Mechanism

No install steps or third-party downloads are present (instruction-only). Nothing is written to disk by an installer; risk is limited to runtime behavior.

Credentials

Only a single token (NEMO_TOKEN) and a nemo config path are required, which matches a remote API client. There are no unrelated credential requests or broad environment access declared.

Persistence & Privilege

The skill does not request always:true and does not ask to modify other skills or system-wide config. It will create session tokens and use them for API calls, which is expected for a remote service.

Assessment

This skill is internally consistent for a cloud text→video tool, but it relies entirely on a remote backend (mega-api-prod.nemovideo.ai) that has no visible homepage or reputation in the package metadata. Before installing or using it: (1) Decide whether you trust that backend — the skill will upload files and prompts (potentially sensitive) for remote processing. (2) Prefer setting your own NEMO_TOKEN (if you have an account) rather than letting the skill obtain an anonymous token for you. (3) Avoid uploading private or regulated content (PII, secrets, or minors) unless you have reviewed the service's privacy/TOS. (4) Note the skill reads environment and install/config paths to derive headers — this is used for attribution but could reveal platform info. If you need higher assurance, ask the publisher for a homepage or privacy policy and an explicit security/privacy statement before proceeding.

Getting Started

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

Try saying:

• "generate my text prompt"
• "export 1080p MP4"
• "generate a romantic kiss scene from"

Quick Start Setup

This skill connects to a cloud processing backend. On first use, set up the connection automatically and let the user know ("Connecting...").

Token check: Look for NEMO_TOKEN in the environment. If found, skip to session creation. Otherwise:

• Generate a UUID as client identifier
• POST https://mega-api-prod.nemovideo.ai/api/auth/anonymous-token with X-Client-Id header
• Extract data.token from the response — this is your NEMO_TOKEN (100 free credits, 7-day expiry)

Session: POST https://mega-api-prod.nemovideo.ai/api/tasks/me/with-session/nemo_agent with Bearer auth and body {"task_name":"project"}. Keep the returned session_id for all operations.

Let the user know with a brief "Ready!" when setup is complete. Don't expose tokens or raw API output.

Text to Video Kiss — Generate Kiss Scenes from Text

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

A quick example: upload a short description like 'two people sharing a kiss at sunset on a beach', type "generate a romantic kiss scene from a written description", and you'll get a 1080p MP4 back in roughly 1-2 minutes. All rendering happens server-side.

Worth noting: shorter, more specific prompts produce more accurate and consistent results.

Matching Input to Actions

User prompts referencing text to video kiss, 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 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.

Headers are derived from this file's YAML frontmatter. X-Skill-Source is text-to-video-kiss, 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

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

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 "generate a romantic kiss scene from a written description" — concrete instructions get better results.

Max file size is 500MB. Stick to TXT, DOCX, PDF, plain text for the smoothest experience.

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

Common Workflows

Quick edit: Upload → "generate a romantic kiss scene from a written description" → 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.