Best Wechat Video

Skip the learning curve of professional editing software. Describe what you want — trim the clip, add subtitles in Chinese and English, and export for WeChat...

Security Scan

The skill's stated purpose (remote video editing for WeChat) is plausible, but the runtime instructions and metadata contain inconsistencies and mild scope creep (filesystem checks, unstated config storage) that you should understand before installing or using it.

Purpose & Capability

The skill's need for an API token (NEMO_TOKEN) and network access to a remote video-processing backend fits its claimed purpose. However, the SKILL.md metadata includes a config path (~/.config/nemovideo/) and runtime steps that try to detect the agent install path (~/.clawhub/, ~/.cursor/skills/), while the registry metadata provided earlier listed no required config paths. This mismatch is unexplained and suggests extra filesystem access beyond simple upload/use.

Instruction Scope

Instructions tell the agent to automatically connect to an external API, obtain an anonymous token if none is present, store a session_id for subsequent requests, and detect install paths and skill frontmatter at runtime. Reading install paths and config directories (to set X-Skill-Platform) and storing session tokens are not necessary for basic upload/edit/export functionality and expand the skill's scope into local filesystem access and persistent state without specifying where/how data is stored.

Install Mechanism

There is no install spec and no code files — this is instruction-only. That minimizes installation risk (nothing is downloaded or written by an installer). The primary runtime risk comes from the network calls and filesystem access described in SKILL.md, not from an installer.

Credentials

The skill only declares one required environment variable (NEMO_TOKEN), which is reasonable for an API-backed service. But the SKILL.md also references a config directory (~/.config/nemovideo/) and implies storing session state there; those filesystem access requirements were not reflected in the registry metadata and are not justified in the description. That asymmetry increases privacy risk.

Persistence & Privilege

The skill is not force-enabled (always:false) and can be invoked by the user. It does instruct the agent to generate and persist a short-lived anonymous token and to store session_id for ongoing jobs. Persisting credentials/session state is common for remote services, but the instructions do not specify storage location or retention policy, which is an information governance concern rather than an immediate technical exploit.

What to consider before installing

Before installing or using this skill, consider the following: - Network & privacy: The skill uploads your raw video to a third-party service (mega-api-prod.nemovideo.ai). Don't send sensitive footage you wouldn't want uploaded to an external GPU backend. - Token & storage: The skill will look for NEMO_TOKEN and — if absent — request an anonymous token from the backend and store session IDs. Ask the maintainer where tokens/session state are stored (local file path, encryption, retention) and whether you can opt out of persistent storage. - Filesystem access: SKILL.md instructs the agent to detect install paths and a config directory. If you prefer minimal local probing, do not grant the skill access to your home config directories or ask for a version that omits those checks. - Metadata mismatch: Registry metadata did not list config paths but SKILL.md did. Treat this as a caution: verify the final manifest (as delivered by the registry) matches what's in SKILL.md. - Domain verification: If you plan to use it, verify the backend domain and service (nemovideo) and confirm their privacy/terms. Consider getting an account-based API key rather than relying on anonymous tokens if you need auditability. If you need strong guarantees (no uploads, no persistent tokens, no filesystem probing), do not install this skill until the author clarifies storage behavior and removes unnecessary filesystem checks.

Getting Started

Got raw video footage to work with? Send it over and tell me what you need — I'll take care of the AI video optimization.

Try saying:

• "create a 30-second phone-recorded clip for WeChat Moments into a 1080p MP4"
• "trim the clip, add subtitles in Chinese and English, and export for WeChat sharing"
• "creating optimized short videos for WeChat Moments and chats for WeChat content 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.

Best WeChat Video — Create and Export WeChat Videos

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

A quick example: upload a 30-second phone-recorded clip for WeChat Moments, type "trim the clip, add subtitles in Chinese and English, and export for WeChat sharing", and you'll get a 1080p MP4 back in roughly 30-60 seconds. All rendering happens server-side.

Worth noting: keep clips under 30 seconds to stay within WeChat Moments upload limits.

Matching Input to Actions

User prompts referencing best wechat 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.

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

• X-Skill-Source: best-wechat-video
• 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.

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.

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

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 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 → "trim the clip, add subtitles in Chinese and English, and export for WeChat sharing" → Download MP4. Takes 30-60 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.

Tips and Tricks

The backend processes faster when you're specific. Instead of "make it look better", try "trim the clip, add subtitles in Chinese and English, and export for WeChat sharing" — concrete instructions get better results.

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

Export as MP4 with H.264 codec for best compatibility with WeChat.