Video Editing With Gopro

Turn a 3-minute GoPro hiking clip in MP4 into 4K edited action clips just by typing what you need. Whether it's trimming and polishing GoPro action footage f...

Security Scan

The skill mostly matches a remote GoPro editing service but contains several inconsistencies and behaviors that warrant caution (automatic token generation, filesystem/install-path probing, and a 4K claim that conflicts with stated API limits).

Purpose & Capability

The skill's name and description match a remote video-editing service that would reasonably require an API token. However there are clear mismatches: the frontmatter/description promises "4K" outputs, while the Cloud Render Pipeline text limits outputs to H.264 up to 1080x1920. Registry metadata (earlier summary) lists no config paths, but the SKILL.md frontmatter references a config path (~/.config/nemovideo/). These inconsistencies reduce confidence that the declared capabilities and constraints are accurate.

Instruction Scope

The runtime instructions will (1) automatically request an anonymous token from an external endpoint if NEMO_TOKEN is absent, (2) create and store a session_id for subsequent API calls, and (3) require the agent to determine install path to set X-Skill-Platform header (which implies probing filesystem locations like ~/.clawhub/ or ~/.cursor/skills/). Auto-generating and storing API tokens and probing install paths go beyond simple editing and raise privacy and scope questions. The instructions also tell the agent to upload user video files (expected) and to avoid showing raw tokens to users (good practice).

Install Mechanism

This is an instruction-only skill with no install spec and no code files — lowest disk/installation risk.

Credentials

Only one environment variable (NEMO_TOKEN) is declared as required, which is proportionate for an API-backed service. But SKILL.md both references an on-disk config path (~/.config/nemovideo/) and instructs creating an anonymous token at runtime when NEMO_TOKEN is absent; it's unclear whether tokens/session IDs are persisted to disk or only kept in memory. The token generation behavior means the skill can obtain credentials without explicit user-provided keys, which is plausible but should be communicated to users.

Persistence & Privilege

The skill does not request always:true or other elevated platform privileges, and there is no install-time code writing to system locations. The only persistence implied is storing a session_id / token for session management; storage location and lifetime are unspecified.

What to consider before installing

This skill appears to be a wrapper around a remote video-processing API (nemovideo). Before installing: (1) Confirm you trust the external domain (https://mega-api-prod.nemovideo.ai) and its privacy/terms — your raw video will be uploaded to that service. (2) Ask the author or vendor to resolve contradictions: the skill advertises 4K output but the pipeline text says up to 1080x1920. (3) Clarify where and how tokens/session IDs are stored (in memory vs written to ~/.config/nemovideo/) and whether anonymous tokens created automatically will be persisted. (4) If you have sensitive footage, do not use the skill until you confirm retention, access controls, and deletion policies for uploaded videos. (5) If you want stronger assurance, request the skill author to remove install-path probing for X-Skill-Platform (or document exactly what is read) and to make token-creation explicit (ask for user consent) rather than automatic.

Getting Started

Ready when you are. Drop your raw GoPro footage here or describe what you want to make.

Try saying:

• "edit a 3-minute GoPro hiking clip in MP4 into a 4K MP4"
• "cut the shaky parts, stabilize the footage, and add background music"
• "trimming and polishing GoPro action footage for social media for action sports 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.

Video Editing with GoPro — Edit and Export GoPro Clips

Send me your raw GoPro footage and describe the result you want. The AI video editing runs on remote GPU nodes — nothing to install on your machine.

A quick example: upload a 3-minute GoPro hiking clip in MP4, type "cut the shaky parts, stabilize the footage, and add background music", and you'll get a 4K MP4 back in roughly 1-2 minutes. All rendering happens server-side.

Worth noting: shorter clips under 2 minutes process significantly faster and yield tighter edits.

Matching Input to Actions

User prompts referencing video editing with gopro, 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: video-editing-with-gopro
• X-Skill-Version: from frontmatter version
• X-Skill-Platform: detect from install path (~/.clawhub/ → clawhub, ~/.cursor/skills/ → cursor, else unknown)

Every API call needs Authorization: Bearer <NEMO_TOKEN> plus the three attribution headers above. If any header is missing, exports return 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 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

Common Workflows

Quick edit: Upload → "cut the shaky parts, stabilize the footage, and add background 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 "cut the shaky parts, stabilize the footage, and add background music" — concrete instructions get better results.

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

Export as MP4 with H.264 codec for widest compatibility across platforms.