功能描述

Skip the learning curve of professional editing software. Describe what you want — turn these images into a 30-second promo video with music and text overlay...

使用说明 (SKILL.md)

Getting Started

Share your images or clips and I'll get started on AI video creation. Or just tell me what you're thinking.

Try saying:

"generate my images or clips"
"export 1080p MP4"
"turn these images into a 30-second"

Automatic Setup

On first interaction, connect to the processing API before doing anything else. Show a brief status like "Setting things up...".

Token: If NEMO_TOKEN environment variable is already set, use it and skip to Session below.

Free token: Generate a UUID as client identifier, then POST to https://mega-api-prod.nemovideo.ai/api/auth/anonymous-token with header X-Client-Id: \x3Cuuid>. The response field data.token becomes your NEMO_TOKEN (100 credits, 7-day expiry).

Session: POST to https://mega-api-prod.nemovideo.ai/api/tasks/me/with-session/nemo_agent with Bearer auth and body {"task_name":"project"}. Save session_id from the response.

Confirm to the user you're connected and ready. Don't print tokens or raw JSON.

Free Video Generator Canva — Create Videos from Images Free

Name: Free Video Generator Canva
Author: tk8544-b

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

Here's a typical use: you send a five product photos and a logo file, ask for turn these images into a 30-second promo video with music and text overlays, 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 — using fewer than 10 images keeps processing fast and the video focused.

Matching Input to Actions

User prompts referencing free video generator canva, 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.

Base URL: https://mega-api-prod.nemovideo.ai

Endpoint	Method	Purpose
`/api/tasks/me/with-session/nemo_agent`	POST	Start a new editing session. Body: `{"task_name":"project","language":"\x3Clang>"}`. Returns `session_id`.
`/run_sse`	POST	Send a user message. Body includes `app_name`, `session_id`, `new_message`. Stream response with `Accept: text/event-stream`. Timeout: 15 min.
`/api/upload-video/nemo_agent/me/\x3Csid>`	POST	Upload a file (multipart) or URL.
`/api/credits/balance/simple`	GET	Check remaining credits (`available`, `frozen`, `total`).
`/api/state/nemo_agent/me/\x3Csid>/latest`	GET	Fetch current timeline state (`draft`, `video_infos`, `generated_media`).
`/api/render/proxy/lambda`	POST	Start export. Body: `{"id":"render_\x3Cts>","sessionId":"\x3Csid>","draft":\x3Cjson>,"output":{"format":"mp4","quality":"high"}}`. Poll status every 30s.

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

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

X-Skill-Source: free-video-generator-canva
X-Skill-Version: from frontmatter version
X-Skill-Platform: detect from install path (~/.clawhub/ → clawhub, ~/.cursor/skills/ → cursor, else unknown)

Include Authorization: Bearer \x3CNEMO_TOKEN> and all attribution headers on every request — omitting them triggers a 402 on export.

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=\x3Cid>` (get `\x3Cid>` 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

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 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)

Common Workflows

Quick edit: Upload → "turn these images into a 30-second promo video with music and text overlays" → 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 "turn these images into a 30-second promo video with music and text overlays" — concrete instructions get better results.

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

Export as MP4 for widest compatibility across social platforms.

安全使用建议

This skill appears to be a legitimate wrapper for a 3rd-party video-rendering API (nemovideo.ai), but its name uses 'Canva' which is likely misleading — it is not an official Canva integration. Before installing or using it: (1) Confirm you are comfortable uploading the files you provide (images/videos/audio) to https://mega-api-prod.nemovideo.ai — do not upload sensitive or private material if you are unsure of their privacy/retention. (2) Check how and where tokens and session IDs are stored: SKILL.md implies saving session_id and may use ~/.config/nemovideo/ to persist state; decide if you accept tokens being written to disk. (3) If you prefer not to provide a persistent credential, use the anonymous-token flow but note it grants limited, time-bound credits. (4) Be aware the skill will read its own frontmatter and detect install paths to set attribution headers — that requires filesystem access to the agent environment. (5) If you need an actual Canva integration, do not assume this skill provides one; ask the publisher for clarification or use an official Canva connector. If any of the above concerns are unacceptable, do not install or invoke the skill.

功能分析

Type: OpenClaw Skill Name: free-video-generator-canva Version: 1.0.0 The skill bundle provides a functional integration for a video generation service hosted at nemovideo.ai. It contains standard instructions for an AI agent to handle authentication via anonymous tokens, manage user sessions, upload media files, and poll for video rendering status. No evidence of data exfiltration, malicious execution, or harmful prompt injection was found; the requested environment variables and configuration paths are specific to the service's operation.

能力评估

⚠ Purpose & Capability

The skill's stated purpose is to turn images/clips into short promo videos — the runtime instructions match that (upload files, create sessions, request renders). However the name and marketing use 'Canva' whereas all endpoints point to mega-api-prod.nemovideo.ai (no Canva API). This is misleading and could cause users to assume an official Canva integration when none exists. Also SKILL.md frontmatter includes a required config path (~/.config/nemovideo/) while the registry metadata reported no required config paths — a mismatch that should be resolved.

ℹ Instruction Scope

Runtime instructions are specific to video creation: generate/refresh tokens, start sessions, upload files, handle SSE, poll render status. That scope is appropriate. The instructions also ask the agent to read the skill's YAML frontmatter and detect install path to populate attribution headers, which requires filesystem/agent-environment access. They also instruct to 'save session_id' and persist tokens (ambiguous whether in-memory or on-disk). These steps are within the functional scope but do give the skill access to local state and may cause tokens/ids to be written to disk.

✓ Install Mechanism

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

ℹ Credentials

Only one credential is declared (NEMO_TOKEN), which is consistent with a hosted rendering API. However the SKILL.md frontmatter adds a configPaths requirement (~/.config/nemovideo/), which is not reflected in the registry metadata; that suggests the skill expects to read/write a local config directory to store tokens or session state. Confirm whether the skill will persist tokens/config to disk before installing. Requesting a single API token is proportional to the stated task, but persistent storage of that token is important to understand.

ℹ Persistence & Privilege

The skill is not always-enabled and does not request elevated platform privileges. It can be invoked autonomously (normal default). The instructions imply saving session tokens/ids and detecting the agent install path (to set attribution headers), which could result in persistent local state (~/.config/nemovideo/) — the spec is ambiguous about where session/token data is stored.

版本历史

v1.0.0

Initial release of Free Video Generator Canva — Create Videos from Images Free: - Instantly create promo videos from uploaded images or clips with AI-powered editing, music, and text overlays. - Simple onboarding: automatic token and session management, ready in seconds without setup. - Supports direct upload (MP4, MOV, PNG, JPG, and others), 200MB max per file. - Exports high-quality 1080p MP4 videos, optimized for social sharing. - Tracks session state, credits, and export/download progress. - Clear error messages and guided troubleshooting for unsupported files, token expiry, and credit issues.

元数据

Slug free-video-generator-canva

版本 1.0.0

许可证 MIT-0

累计安装 1

当前安装数 1

历史版本数 1

常见问题

Free Video Generator Canva 是什么？

Skip the learning curve of professional editing software. Describe what you want — turn these images into a 30-second promo video with music and text overlay... 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件，目前累计下载 75 次。

如何安装 Free Video Generator Canva？

在 OpenClaw 或 Claude Code 对话框中运行命令「/install free-video-generator-canva」即可一键安装，无需额外配置。

Free Video Generator Canva 是免费的吗？

是的，Free Video Generator Canva 完全免费，采用 MIT-0 许可证，可自由下载、安装和使用。

Free Video Generator Canva 支持哪些平台？

Free Video Generator Canva 跨平台运行，可在任意部署了 OpenClaw / Claude Code 的环境中使用（cross-platform）。

谁开发了 Free Video Generator Canva？

由 tk8544-b（@tk8544-b）开发并维护，当前版本 v1.0.0。

Free Video Generator Canva