Pitch Video

Turn a 2-minute founder explanation recording into 1080p polished pitch video just by typing what you need. Whether it's creating investor or sales pitch vid...

Security Scan

The skill's runtime instructions and requested API token are coherent with a cloud video-rendering service, but there are provenance and metadata inconsistencies (no homepage/source, differing configPaths) and it will upload user media to an external API — verify the service and token handling before use.

Purpose & Capability

Name/description align with behavior: the SKILL.md describes uploading footage, remote GPU rendering, and returning downloadable video URLs. However, SKILL.md metadata lists a required configPath (~/.config/nemovideo/) while the registry metadata listed none, and there is no homepage or known source for the skill — these provenance gaps are unexplained and worth verifying.

Instruction Scope

Instructions stay within the expected scope (authenticate, create session, upload files, stream SSE edits, export/poll for download). They do instruct the agent to acquire an anonymous token automatically if NEMO_TOKEN is absent and to include attribution headers (including a platform value derived from local install paths). That automatic anonymous-token flow and install-path detection broaden what the agent may do without explicit user consent.

Install Mechanism

No install spec and no code files (instruction-only) — lowest-risk delivery mechanism. Nothing is downloaded or written by an install step in the skill bundle itself.

Credentials

Only a single API credential (NEMO_TOKEN) is requested which is appropriate for calling the described backend. Caveats: SKILL.md metadata indicates a config path (~/.config/nemovideo/) not declared in the registry metadata, and the skill will attempt to obtain an anonymous token if none is provided — this behavior should be considered before supplying media or letting the agent obtain credentials automatically.

Persistence & Privilege

Skill does not request always: true and does not modify other skills. Autonomous invocation is allowed (platform default) but not combined here with any elevated persistence or cross-skill configuration changes.

What to consider before installing

This skill appears to do what it claims (upload your footage to a remote renderer and return a video), but exercise caution before using it: there is no public homepage or known source, and the SKILL.md contains metadata that doesn't match the registry (a listed config path). The skill will upload your media to https://mega-api-prod.nemovideo.ai and may obtain an anonymous token on your behalf if you don't provide NEMO_TOKEN. Before installing or running: 1) verify the vendor/service (nemovideo) reputation and privacy/retention policy; 2) prefer supplying your own NEMO_TOKEN from a trusted account rather than letting the skill request an anonymous token; 3) avoid uploading sensitive or proprietary footage until you confirm where data is stored and who can access it; 4) ask the publisher for a homepage or contact details, or decline installing if provenance can't be verified. If you want higher assurance, request the skill author to provide a trusted repo/homepage and to remove unexplained configPath requirements.

Getting Started

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

Try saying:

• "create a 2-minute founder explanation recording into a 1080p MP4"
• "cut filler words, add slide overlays, and export a 90-second investor pitch"
• "creating investor or sales pitch videos from raw recordings for founders, marketers, sales teams"

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.

Pitch Video — Create and Export Pitch Videos

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

A quick example: upload a 2-minute founder explanation recording, type "cut filler words, add slide overlays, and export a 90-second investor pitch", and you'll get a 1080p MP4 back in roughly 1-2 minutes. All rendering happens server-side.

Worth noting: keep your pitch under 3 minutes for best investor engagement.

Matching Input to Actions

User prompts referencing pitch 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 pitch-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).

Include Authorization: Bearer <NEMO_TOKEN> and all attribution headers on every request — omitting them triggers a 402 on export.

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 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 filler words, add slide overlays, and export a 90-second investor pitch" → 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 filler words, add slide overlays, and export a 90-second investor pitch" — concrete instructions get better results.

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

Export as MP4 for widest compatibility across email, decks, and video platforms.