功能描述

content creators add video files into captioned video files using this skill. Accepts MP4, MOV, AVI, WebM up to 500MB, renders on cloud GPUs at 1080p, and re...

使用说明 (SKILL.md)

Getting Started

Share your video files and I'll get started on automatic subtitle generation. Or just tell me what you're thinking.

Try saying:

"add my video files"
"export 1080p MP4"
"automatically generate and burn in captions"

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 Auto Caption — Auto-Generate and Add Captions

Name: Free Auto Caption
Author: susan4731-wilfordf

Send me your video files and describe the result you want. The automatic subtitle generation runs on remote GPU nodes — nothing to install on your machine.

A quick example: upload a 3-minute YouTube tutorial video, type "automatically generate and burn in captions for my video", and you'll get a 1080p MP4 back in roughly 30-60 seconds. All rendering happens server-side.

Worth noting: shorter clips under 5 minutes generate captions significantly faster.

Matching Input to Actions

User prompts referencing free auto caption, 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-auto-caption
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 → "automatically generate and burn in captions for my video" → 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 "automatically generate and burn in captions for my video" — concrete instructions get better results.

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

Export as MP4 for widest compatibility across platforms and devices.

安全使用建议

This skill appears to be what it says: a cloud-based auto-captioning integration that needs a NEMO_TOKEN and will upload video files to nemovideo.ai. Before installing/using, consider: (1) Privacy and trust: your videos (and their audio) are uploaded to a third-party service — verify you trust mega-api-prod.nemovideo.ai and read its privacy/retention policy. (2) Token & session storage: ask the publisher whether NEMO_TOKEN or anonymous tokens/session IDs are stored on disk (the SKILL.md references ~/.config/nemovideo/ and detecting install paths); if so, verify where and for how long. (3) Billing/limits: the skill mentions credits, rate limits, and 7-day anonymous tokens — confirm expected behavior for private or large projects. (4) Metadata mismatch: the registry metadata omitted configPaths while the SKILL.md included one — request clarification. If you plan to upload sensitive footage, verify the service's terms and consider testing with non-sensitive material first.

功能分析

Type: OpenClaw Skill Name: free-auto-caption Version: 1.0.0 The skill provides instructions for an AI agent to interact with the nemovideo.ai API to perform automated video captioning and cloud rendering. It includes standard procedures for session management, file uploads, and token acquisition (via https://mega-api-prod.nemovideo.ai) that are consistent with its stated purpose, with no evidence of malicious behavior or unauthorized data exfiltration.

能力评估

✓ Purpose & Capability

Name/description (auto-captioning, cloud render) align with required credential (NEMO_TOKEN) and the SKILL.md which documents upload, session, render, and export endpoints. One minor inconsistency: the registry metadata reported no required config paths, but the SKILL.md frontmatter lists a config path (~/.config/nemovideo/) used for attribution — this is likely metadata drift rather than malicious behavior.

ℹ Instruction Scope

SKILL.md contains concrete runtime instructions: generate anonymous tokens, create sessions, upload files, use SSE endpoints, poll render status, and include Authorization and attribution headers. These actions are within the expected scope for a cloud rendering/captioning service. It instructs the agent to detect its install path (for X-Skill-Platform attribution) and to 'save session_id' and use tokens; it does not instruct reading unrelated system files or unrelated credentials. Clarify where tokens/session IDs are persisted (in-memory vs disk) and whether the agent will write to ~/.config/nemovideo/ if present.

✓ Install Mechanism

This is instruction-only (no install spec, no code files), so nothing gets downloaded or written by an installer. That is the lowest-risk install model.

✓ Credentials

Only NEMO_TOKEN is required (and the SKILL.md documents how to obtain an anonymous token if missing). That single credential is proportional to a cloud API integration. The only exception is the frontmatter's configPaths hint (~/.config/nemovideo/) which suggests optional local config access; the registry's required configPaths field was empty — ask the publisher to confirm whether any local config is read or written.

✓ Persistence & Privilege

The skill does not request always:true and does not ask to modify other skills or system-wide settings. It does instruct saving session_id and using tokens for future calls, which is expected for session-based APIs; confirm whether those are persisted to disk and for how long.

版本历史

v1.0.0

Initial release of Free Auto Caption - Automatically generate and add captions to video files (MP4, MOV, AVI, WebM up to 500MB). - Processes videos on cloud GPUs at 1080p; returns captioned MP4s in 30–60 seconds. - No installation required; uses a free, temporary API token for anonymous access. - Supports uploading, exporting, checking credits, and timeline preview. - Handles errors (expired token, session issues, file size/type, rate limits) with clear user feedback. - Designed for fast, automated captioning—ideal for content creators.

元数据

Slug free-auto-caption

版本 1.0.0

许可证 MIT-0

累计安装 0

当前安装数 0

历史版本数 1

常见问题

Free Auto Caption 是什么？

content creators add video files into captioned video files using this skill. Accepts MP4, MOV, AVI, WebM up to 500MB, renders on cloud GPUs at 1080p, and re... 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件，目前累计下载 101 次。

如何安装 Free Auto Caption？

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

Free Auto Caption 是免费的吗？

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

Free Auto Caption 支持哪些平台？

Free Auto Caption 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 Auto Caption？

由 susan4731-wilfordf（@susan4731-wilfordf）开发并维护，当前版本 v1.0.0。

Free Auto Caption