Getting Started

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.

Turn Shelter Footage Into Adoption-Ready Stories

Every animal in a shelter deserves a video that shows their real personality — not just a shaky clip with no context. The pet-adoption-video skill helps you build videos that tell a pet's story in a way that resonates with potential adopters scrolling through social media or a rescue organization's website.

Whether you're working with raw footage from a phone, a set of photos, or just a written description of the pet, this skill helps you shape it into a structured, emotionally engaging video concept. You'll get scene-by-scene outlines, caption suggestions, voiceover scripts, and on-screen text ideas tailored to the specific animal — their breed, age, quirks, and adoption needs.

This is especially useful for small rescues and foster networks that don't have a dedicated media team. Instead of spending hours figuring out what to say or how to sequence clips, you can focus on the animals while this skill handles the storytelling framework that drives real adoption outcomes.

How Your Video Requests Flow

When you describe a pet's personality, story, or shelter details, the skill routes your request to the appropriate video template engine — whether that's a tearjerker rescue narrative, an upbeat playful profile, or a senior pet spotlight.

Cloud Backend API Reference

Pet adoption video processing runs through ClawHub's media rendering pipeline, which stitches together shelter-provided footage, AI-generated captions, and adoption call-to-action overlays in the cloud — no local rendering required. Heavy tasks like b-roll sequencing and voiceover sync are handled server-side so your final shareable video is ready in seconds.

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

• X-Skill-Source: pet-adoption-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.

SSE Event Handling

~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:

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

Common Workflows

Most users come to this skill with one of three starting points: raw footage they need to structure, a pet profile they want to turn into a video concept, or a finished video that needs better captions and on-screen text.

For footage-based projects, share a description of what clips you have — length, what the pet is doing, the setting — and the skill will suggest a scene order, transition cues, and a voiceover or text overlay script that fits the footage you've already captured.

For profile-to-video workflows, paste in the pet's shelter bio or foster notes and specify the platform (TikTok, Instagram, Facebook, rescue website). You'll get a tailored script with an emotional opening hook, a middle section showcasing personality, and a clear call-to-action that tells viewers exactly how to adopt.

For caption and overlay work, share your existing video concept or rough cut description and the skill will generate platform-optimized captions, hashtag suggestions, and on-screen text timed to key moments in the video.

Quick Start Guide

Getting your first pet adoption video script takes less than two minutes. Start by telling the skill three things: the pet's basic info (name, species, breed, age), their standout personality traits or backstory, and where the video will be posted.

From there, specify the video length you're targeting. A 15-30 second TikTok needs a very different structure than a 2-minute Facebook feature video. If you're unsure, ask the skill to recommend a format based on the platform and the pet's story.

Once you have a script or outline, you can ask for variations — a more upbeat tone for a playful puppy, a gentler and slower-paced version for a timid or special-needs animal. You can also request separate versions for different platforms from the same core content, so one session can produce assets for Instagram, TikTok, and your rescue's website all at once.