Ai Wechat Video

Turn a 60-second product demo video into 1080p WeChat-ready videos just by typing what you need. Whether it's converting and formatting videos for sharing on...

Security Scan

The skill's declared purpose (format WeChat videos) generally matches the API calls it describes, but there are internal inconsistencies and a few instruction-level details that don't add up and warrant caution before installing or providing credentials.

Purpose & Capability

The declared purpose (cloud-based video formatting for WeChat) aligns with the API endpoints and operations documented (upload, render, export). Requesting a single service token (NEMO_TOKEN) is proportional for a cloud backend. However, the SKILL.md frontmatter lists a required config path (~/.config/nemovideo/) while the registry metadata earlier listed no required config paths — this mismatch is inconsistent.

Instruction Scope

The runtime instructions direct the agent to obtain or reuse a bearer token, create sessions, upload videos (multipart or URL), stream SSE responses, and poll render status — all expected for this service. Concerns: (1) the file-upload examples explicitly show local file paths (files=@/path) which could imply reading arbitrary local paths if the agent has file access; the instructions don't clearly constrain uploads to user-supplied attachments. (2) The header 'X-Skill-Platform' is supposed to be auto-detected from install path — instruction-only skills often cannot reliably detect an install path, so this requirement is unrealistic. (3) The SKILL.md frontmatter requiring a config directory (contradicting registry metadata) suggests either sloppy packaging or an unexplained need to read local config.

Install Mechanism

No install spec and no code files (instruction-only) — lowest-risk delivery mechanism. Nothing is downloaded or written to disk by an installer.

Credentials

The skill only requests one credential: NEMO_TOKEN (primaryEnv). That is proportionate for a cloud render service. Important caveat: that single token can grant access to the user's account on the backend (jobs, uploads, credits), so it's sensitive — the SKILL.md also documents steps to obtain an anonymous token if not provided, which is safer for trial use. The apparent frontmatter request for a local config path is inconsistent with the declared requirements and should be clarified.

Persistence & Privilege

always is false and the skill is instruction-only; it does not request permanent inclusion or system-wide configuration changes. Autonomous invocation is allowed by default (normal) but does increase runtime scope; this is not combined with elevated privileges in this package.

What to consider before installing

This skill mostly does what it says — it talks to a Nemovideo-like backend to upload and render short videos — but a few things are inconsistent and worth checking before you install or hand over credentials: - Only provide a NEMO_TOKEN if you trust the backend/service. That token can be used to upload files, start renders, and consume credits on your account. If possible, test with an anonymous token (the SKILL.md shows how to obtain one) rather than your primary account token. - Ask the publisher to clarify the config path discrepancy: SKILL.md frontmatter references ~/.config/nemovideo/ while registry metadata did not declare any required config paths. If the skill will read local config files, you should know exactly what it will access. - Confirm how uploads are handled: the doc shows multipart uploads using local file paths (files=@/path). Ensure the agent will only upload files you explicitly attach in-chat, and will not attempt to read arbitrary filesystem paths. - The requirement to auto-detect an install path for X-Skill-Platform is unrealistic for an instruction-only skill; ask the author to switch to a fixed platform header or a safe default. - Because the source is unknown, prefer using anonymous/free tokens for initial testing, revoke tokens you provide if you stop using the skill, and monitor your account activity/credits on the backend service. If the publisher can resolve the config-path/metadata mismatch and confirm uploads are limited to user-provided files, the incoherences look like sloppy packaging rather than malicious behavior.

Getting Started

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

Try saying:

• "convert a 60-second product demo video into a 1080p MP4"
• "format this video for WeChat Moments with subtitles and a square crop"
• "converting and formatting videos for sharing on WeChat for WeChat content creators"

Getting Connected

Before handling any user request, establish a connection to the backend API. Show a brief status like "Connecting...".

If NEMO_TOKEN is in the environment, use it directly and create a session. Otherwise, acquire a free starter token:

• Generate a UUID as client identifier
• POST to https://mega-api-prod.nemovideo.ai/api/auth/anonymous-token with the X-Client-Id header
• The response includes a token with 100 free credits valid for 7 days — use it as NEMO_TOKEN

Then create a session by POSTing to https://mega-api-prod.nemovideo.ai/api/tasks/me/with-session/nemo_agent with Bearer authorization and body {"task_name":"project","language":"en"}. The session_id in the response is needed for all following requests.

Tell the user you're ready. Keep the technical details out of the chat.

AI WeChat Video — Format and Export WeChat Videos

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

Here's a typical use: you send a a 60-second product demo video, ask for format this video for WeChat Moments with subtitles and a square crop, and about 30-60 seconds later you've got a MP4 file ready to download. The whole thing runs at 1080p by default.

One thing worth knowing — keep videos under 1 minute to match WeChat Moments playback limits.

Matching Input to Actions

User prompts referencing ai 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.

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.

Three attribution headers are required on every request and must match this file's frontmatter:

Header	Value
X-Skill-Source	ai-wechat-video
X-Skill-Version	frontmatter version
X-Skill-Platform	auto-detect: clawhub / cursor / unknown from install path

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.

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

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

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.

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)

Tips and Tricks

The backend processes faster when you're specific. Instead of "make it look better", try "format this video for WeChat Moments with subtitles and a square crop" — 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 WeChat compatibility.

Common Workflows

Quick edit: Upload → "format this video for WeChat Moments with subtitles and a square crop" → 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.