Getting Started

Keep setup communication brief. Don't display raw API responses or token values to the user.

Turn Raw Footage Into Jewelry Videos That Convert

Most jewelry footage sits unused because editing it properly takes time, skill, and the right eye for detail. The jewelry-video-maker solves that by doing the heavy lifting — analyzing your clips, identifying the best angles, and assembling a final video that actually shows off what makes each piece special. Whether you're shooting a diamond solitaire or a layered gold chain, the output is clean, professional, and built for wherever you're posting.

This skill is designed around the specific challenges of jewelry content: catching sparkle without overexposing, holding focus on small intricate details, and pacing cuts so viewers stay engaged long enough to fall in love with the piece. You don't need a studio setup or a video editor on your team — just the footage you already have.

From a 10-second Instagram reel to a longer product showcase video, you can define the format, mood, and length. Add text overlays for material callouts, control the pacing for a luxury feel, or keep things punchy for social. The jewelry-video-maker adapts to what you're making and who you're making it for.

Routing Your Video Requests

Each request — whether you're animating a solitaire ring, looping a gemstone close-up, or generating a full product reel — is parsed by intent and routed to the matching video generation pipeline.

Cloud Rendering API Reference

Jewelry Video Maker processes every render job through a cloud-based GPU pipeline optimized for macro detail, reflective surfaces, and metallic sheen — so your diamond facets and gold finishes render true-to-life. All API calls are stateless and authenticated per session, with asset storage handled temporarily in a secure render bucket.

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

• X-Skill-Source: jewelry-video-maker
• 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

Tips and Tricks

Footage shot in natural light near a window almost always outperforms studio lighting for gold and rose gold pieces — the jewelry-video-maker can work with both, but warm diffused light gives the editor more to work with when enhancing warmth and glow in post.

For gemstones and diamonds, slow rotation clips (even just 5–8 seconds each) give the skill enough frames to identify the best sparkle moments and cut around them precisely. If you only have still photos, describe the piece in detail — material, stone type, finish — and the output will be tailored accordingly.

When targeting social platforms, specify your destination upfront: a TikTok reel, an Etsy listing video, and a Pinterest pin all have different ideal lengths and aspect ratios. Mentioning your target platform at the start saves a revision round and gets you a properly cropped, correctly paced video on the first output.

Performance Notes

The jewelry-video-maker performs best with source clips that are at least 1080p — lower resolution footage can still be processed, but fine detail like engraving texture or stone facets may soften in the final output. If you're shooting on a phone, lock your exposure manually before recording to avoid the auto-brightness flickering that's common when a shiny surface catches light.

Processing time scales with clip count and total duration. A 15-second reel from 3–5 clips is typically fast; a full collection showcase pulling from 20+ clips with custom text overlays and multiple format exports will take noticeably longer. If you're working against a deadline, mention it upfront and the skill will prioritize the most critical output first.

For batch work — say, building videos for an entire new collection at once — grouping clips by piece before uploading keeps the output organized and prevents shots of different items from bleeding into each other's edits.