Ai Video Editor Kapwing

Turn a 2-minute screen recording or phone video into 1080p edited captioned videos just by typing what you need. Whether it's adding subtitles and trimming c...

Security Scan

The skill mostly behaves like a cloud video editor and only requests one credential, but there are branding/source inconsistencies and ambiguous token storage that should be clarified before trusting uploads or providing your own token.

Purpose & Capability

The skill claims to be an 'AI Video Editor Kapwing' but its runtime instructions call a nemovideo backend (mega-api-prod.nemovideo.ai) and require NEMO_TOKEN — technically coherent for a Nemo-backed editor but inconsistent with the 'Kapwing' name and the registry metadata (registry said no config paths while the SKILL.md frontmatter lists ~/.config/nemovideo/). The single required env var (NEMO_TOKEN) is proportional to a cloud video service.

Instruction Scope

SKILL.md gives detailed runtime steps (anonymous-token acquisition, session creation, SSE streaming, uploads, polling exports). It instructs the agent to auto-create an anonymous token if NEMO_TOKEN is absent and to 'store' session_id / token for subsequent calls, and also references deriving headers from install paths and a config directory. The registry metadata did not declare a config path but the frontmatter does — storing tokens or session IDs on disk is implied but not specified. The instructions do not request unrelated system files or other credentials, but the automatic token creation + implicit storage and the mismatch about config paths are ambiguous and worth flagging.

Install Mechanism

Instruction-only skill with no install spec and no code files — lowest install risk (nothing is downloaded or written by an installer).

Credentials

Only NEMO_TOKEN is declared as required (primary credential), which is appropriate for an API-backed video editor. However, SKILL.md describes generating and storing a token when one is not present, and frontmatter references a config path (~/.config/nemovideo/). The registry metadata did not list config paths, so there is an inconsistency about where/if credentials will be persisted.

Persistence & Privilege

The skill is not always-enabled and does not request elevated platform privileges. It implies persistence of tokens/session IDs (possibly in a config path), but does not request to modify other skills or system settings. Autonomous invocation is allowed (default) but not unusually privileged here.

What to consider before installing

Things to consider before installing or using this skill: - Source & naming: The skill is named 'Kapwing' but its backend is mega-api-prod.nemovideo.ai. Confirm whether this skill is actually affiliated with Kapwing; the mismatch could be accidental or misleading. - Token behavior: If you don't supply NEMO_TOKEN the skill will auto-request an anonymous token from the nemovideo API and will store a session_id/token for future API calls. Ask where tokens/session data are stored (in-memory only vs written to ~/.config/nemovideo/) and how long they persist. - Privacy: All uploaded videos are sent to the nemovideo domain. Do not upload sensitive or private videos unless you trust that service and its privacy policy. - Provide your own token only if you trust the provider: supplying your own NEMO_TOKEN could allow the skill to act on your account/credits. Prefer using the anonymous token flow if you want limited exposure. - Ask the publisher: Because the skill's source/homepage is unknown and metadata mismatches exist, request the publisher identity, privacy policy, and confirmation about where tokens are stored and what data are logged. If you need, I can draft questions to ask the publisher or suggest safer alternatives.

Getting Started

Ready when you are. Drop your raw video clips here or describe what you want to make.

Try saying:

• "edit a 2-minute screen recording or phone video into a 1080p MP4"
• "trim the video, add subtitles, and resize for Instagram Reels"
• "adding subtitles and trimming clips for social media for content creators and marketers"

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.

AI Video Editor Kapwing — Edit and Export Videos Online

Drop your raw video clips in the chat and tell me what you need. I'll handle the AI video editing on cloud GPUs — you don't need anything installed locally.

Here's a typical use: you send a a 2-minute screen recording or phone video, ask for trim the video, add subtitles, and resize for Instagram Reels, and about 1-2 minutes later you've got a MP4 file ready to download. The whole thing runs at 1080p by default.

One thing worth knowing — shorter clips under 3 minutes process significantly faster and use fewer credits.

Matching Input to Actions

User prompts referencing ai video editor kapwing, 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 calls go to https://mega-api-prod.nemovideo.ai. The main endpoints:

1. Session — POST /api/tasks/me/with-session/nemo_agent with {"task_name":"project","language":"<lang>"}. Gives you a session_id.
2. Chat (SSE) — POST /run_sse with session_id and your message in new_message.parts[0].text. Set Accept: text/event-stream. Up to 15 min.
3. Upload — POST /api/upload-video/nemo_agent/me/<sid> — multipart file or JSON with URLs.
4. Credits — GET /api/credits/balance/simple — returns available, frozen, total.
5. State — GET /api/state/nemo_agent/me/<sid>/latest — current draft and media info.
6. Export — POST /api/render/proxy/lambda with render ID and draft JSON. Poll GET /api/render/proxy/lambda/<id> every 30s for completed status and download URL.

Formats: mp4, mov, avi, webm, mkv, jpg, png, gif, webp, mp3, wav, m4a, aac.

Headers are derived from this file's YAML frontmatter. X-Skill-Source is ai-video-editor-kapwing, 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).

Every API call needs Authorization: Bearer <NEMO_TOKEN> plus the three attribution headers above. If any header is missing, exports return 402.

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)

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

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.

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

Tips and Tricks

The backend processes faster when you're specific. Instead of "make it look better", try "trim the video, add subtitles, and resize for Instagram Reels" — concrete instructions get better results.

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

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

Common Workflows

Quick edit: Upload → "trim the video, add subtitles, and resize for Instagram Reels" → 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.