Weixin Video

Get WeChat-ready videos ready to post, without touching a single slider. Upload your video clips (MP4, MOV, AVI, WebM, up to 200MB), say something like "form...

Security Scan

The skill's stated purpose (cloud video formatting for WeChat) matches its runtime network actions, but there are inconsistencies around required credentials and filesystem/config access that merit caution before installing.

Purpose & Capability

The skill claims to format videos via a cloud rendering backend (mega-api-prod.nemovideo.ai) and its instructions describe exactly the session, upload, SSE, and export endpoints needed for that. Requiring a token for that backend (NEMO_TOKEN) is reasonable for the described functionality. However, the SKILL.md also lists a config path (~/.config/nemovideo/) in its metadata while the registry metadata declares no config paths — this mismatch is unexplained.

Instruction Scope

Most instructions stay within the backend API (session creation, upload, render, poll). But the skill instructs detecting install path to set X-Skill-Platform (reading ~/.* paths) and includes configPaths in its YAML metadata, which implies reading filesystem locations not declared in the registry. Also, although NEMO_TOKEN is declared required, the SKILL.md explicitly instructs the agent to create an anonymous token by calling the backend if no environment token exists — meaning the skill will proceed (and upload user media) even without a user-provided credential. These behaviors expand scope beyond a simple formatting helper.

Install Mechanism

Instruction-only skill with no install spec and no code files — nothing is written to disk by an installer. This is lower risk from an installation perspective.

Credentials

The only declared environment variable is NEMO_TOKEN, which is appropriate for the backend. But SKILL.md will obtain an anonymous token automatically if NEMO_TOKEN is missing, contradicting the 'required' designation. The metadata also references a config path (~/.config/nemovideo/) not declared elsewhere. Requesting a single service token is proportionate to the purpose; the inconsistency about whether the token is required and the implicit filesystem access are concerning.

Persistence & Privilege

always is false and the skill is user-invocable; it does not demand permanent inclusion or elevated platform privileges. It does instruct keeping a session_id for operations, which is normal for a service client.

Scan Findings in Context

[no-findings] expected: The regex-based scanner found nothing to analyze; this is expected because the skill is instruction-only (only SKILL.md present). The lack of findings is not evidence of safety — review the instructions themselves.

What to consider before installing

This skill uses a third‑party cloud service (mega-api-prod.nemovideo.ai) to process and host your uploaded videos — expect your media to be sent off‑device. The SKILL.md says it requires NEMO_TOKEN but will auto‑request an anonymous token if none is present, so it can operate (and upload data) without you supplying credentials. There is also an unexplained reference to a local config path and to detecting install paths, which implies reading some filesystem locations. Before installing, consider: (1) do you trust the external domain to handle and store your videos? (2) ask the publisher for a homepage or privacy/terms link (none is provided), and prefer providing your own token if you want control; (3) test with non‑sensitive sample videos first; (4) if you need assurance the skill won't read local files or config, request clarification about the configPath and install-path detection. If you are processing private or sensitive footage, avoid installing until you confirm data handling and retention policies.

Getting Started

Send me your video clips and I'll handle the WeChat video formatting. Or just describe what you're after.

Try saying:

• "convert a 30-second MP4 recorded on a smartphone into a 1080p MP4"
• "format and compress this video for sharing on WeChat"
• "formatting and compressing videos for WeChat sharing for WeChat users"

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.

Weixin Video — Format Videos for WeChat Sharing

This tool takes your video clips and runs WeChat video formatting through a cloud rendering pipeline. You upload, describe what you want, and download the result.

Say you have a 30-second MP4 recorded on a smartphone and want to format and compress this video for sharing on WeChat — the backend processes it in about 20-40 seconds and hands you a 1080p MP4.

Tip: keeping clips under 60 seconds ensures smooth WeChat sharing without compression artifacts.

Matching Input to Actions

User prompts referencing weixin video, 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 weixin-video, 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).

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.

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)

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

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.

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 "format and compress this video for sharing on WeChat" — concrete instructions get better results.

Max file size is 200MB. Stick to MP4, MOV, AVI, WebM for the smoothest experience.

H.264 codec gives the best balance of quality and size for WeChat playback.

Common Workflows

Quick edit: Upload → "format and compress this video for sharing on WeChat" → Download MP4. Takes 20-40 seconds 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.