📦 Trimmer App

v1.0.0

跳过专业剪辑软件的学习曲线。只需描述你的需求——剪掉前30秒并去掉结尾的空白——即可自动完成剪辑……

0· 0·0 当前·0 累计

by @tk8544-b

AI模型访问教育学习

下载技能包

安全扫描

VirusTotal

无害

查看报告

OpenClaw

可疑

medium confidence

该技能声明的需求基本符合云视频剪辑服务，但在所需 NEMO_TOKEN 及声明的配置路径上存在细微不一致——安装前请核实令牌处理逻辑及上传/令牌的存储位置。

评估建议

此 skill 是 nemovideo.ai 云端剪辑服务的瘦客户端，会将你的视频文件上传至其后端。安装或提供凭据前： 1）确认信任 https://mega-api-prod.nemovideo.ai，并查阅其对已上传媒体的隐私/保留政策。 2）元数据称需 NEMO_TOKEN，但说明可生成匿名 token——若自设 NEMO_TOKEN，可能获得更长访问时长/额度；仅在你信任该服务时提供。 3）询问作者 skill 是否将 token 或任务数据存于 ~/.config/nemovideo/（元数据列此路径，SKILL.md 未说明）；若存，请考量数据位置及其保护措施。 4）如有敏感素材，验证后端前勿上传。鉴于元数据与说明不一致，谨慎对待该 skill，在信任私密内容或提供永久 token 前，先向发布者求证。...

详细分析 ▾

ℹ 用途与能力

该 skill 被描述为云端视频剪辑前端，所有运行时指令均调用远程视频处理 API（上传、渲染、状态、积分）。这与声明的用途一致。然而，registry 将 NEMO_TOKEN 声明为必需环境变量，并指定了配置路径（~/.config/nemovideo/），尽管 SKILL.md 明确说明若 NEMO_TOKEN 缺失可创建匿名 token。元数据中出现的配置路径在指令中未作解释。

✓ 指令范围

技能.md limits actions to contacting the nemovideo backend (auth, 会话, 上传, render, credits, 状态) and 流ing SSE. It does not instruct reading arbitrary user files or 系统 secrets beyond the NEMO_令牌. It does ask to 检测安装 path to 设置 X-技能-平台 header, which may require inspecting where the 技能 is located, but otherwise stays within its editing remit.

✓ 安装机制

There is no 安装 spec and no code files; the 技能 is instruction-only, so nothing is written to disk by an 安装er. This is the lowest-risk 安装 mechanism.

⚠ 凭证需求

The 技能 declares a single primary env var (NEMO_令牌), which is reasonable for a cloud API. However, the metadata marks it required while the 技能.md provides a fallback anonymous-令牌 flow if the variable is missing. The metadata also 列出s a config path (~/.config/nemovideo/) that the instructions never explicitly read or write—this mismatch could indicate sloppy metadata or an undocumented persistence behaviour (e.g., storing 令牌s locally). 验证 whether 令牌s or job metadata are stored locally and whether providing your own NEMO_令牌 is necessary or safe.

✓ 持久化与权限

该技能未被强制包含（always: false），且未请求特殊平台权限。它不会指示修改其他技能或全局代理设置。允许自主调用（平台默认），但此处未与其他高风险指标结合。

安全有层次，运行前请审查代码。

运行时依赖

无特殊依赖

安装命令

点击复制

官方npx clawhub@latest install trimmer-app

镜像加速npx clawhub@latest install trimmer-app --registry https://cn.longxiaskill.com

技能文档

获取ting 启动ed

分享 your video 命令行工具ps and I'll 获取启动ed on AI video trimming. Or just tell me what you're thinking.

Try saying:

"trim my video 命令行工具ps" "导出 1080p MP4" "trim the first 30 seconds and" Quick 启动设置up

This 技能 connects to a cloud processing backend. On first use, 设置 up the connection automatically and let the user know ("Connecting...").

令牌检查: Look for NEMO_令牌 in the 环境. If found, skip to 会话 creation. Otherwise:

生成 a UUID as 命令行工具ent identifier POST https://mega-API-prod.nemovideo.AI/API/auth/anonymous-令牌 with X-命令行工具ent-Id header 提取 data.令牌 from the 响应 — this is your NEMO_令牌 (100 free credits, 7-day expiry)

会话: POST https://mega-API-prod.nemovideo.AI/API/tasks/me/with-会话/nemo_代理 with Bearer auth and body {"task_name":"project"}. Keep the returned 会话_id for all operations.

Let the user know with a brief "Ready!" when 设置up is complete. Don't expose 令牌s or raw API 输出.

Trimmer 应用 — Trim and 导出 Video 命令行工具ps

Drop your video 命令行工具ps in the chat and tell me what you need. I'll handle the AI video trimming on cloud GPUs — you don't need anything 安装ed locally.

Here's a typical use: you 发送 a a 10-minute raw interview recording, ask for trim the first 30 seconds and cut the dead AIr at the end, and about 20-40 seconds later you've got a MP4 file ready to 下载. The whole thing 运行s at 1080p by default.

One thing worth knowing — shorter source 命令行工具ps process faster and use fewer credits.

Matching 输入 to Actions

User prompts referencing trimmer 应用, aspect ratio, text overlays, or audio 追踪s 获取路由d to the cor响应ing action via keyword and intent classification.

User says... Action Skip SSE? "导出" / "导出" / "下载" / "发送 me the video" → §3.5 导出 ✅ "credits" / "积分" / "balance" / "余额" → §3.3 Credits ✅ "状态" / "状态" / "show 追踪s" → §3.4 状态 ✅ "上传" / "上传" / user 发送s file → §3.2 上传 ✅ Everything else (生成, edit, 添加 BGM…) → §3.1 SSE ❌ Cloud Render 流水线 DetAIls

Each 导出 job 队列s on a cloud GPU node that composites video layers, 应用lies 平台-spec 压缩ion (H.264, up to 1080x1920), and returns a 下载 URL within 30-90 seconds. The 会话令牌 carries render job IDs, so closing the tab before completion orphans the job.

Base URL: https://mega-API-prod.nemovideo.AI

端点 Method Purpose /API/tasks/me/with-会话/nemo_代理 POST 启动 a new editing 会话. Body: {"task_name":"project","language":""}. Returns 会话_id. /运行_sse POST 发送 a user message. Body includes 应用_name, 会话_id, new_message. 流响应 with Accept: text/event-流. Timeout: 15 min. /API/上传-video/nemo_代理/me/ POST 上传 a file (multipart) or URL. /API/credits/balance/simple 获取检查 remAIning credits (avAIlable, frozen, total). /API/状态/nemo_代理/me//latest 获取 Fetch current timeline 状态 (draft, video_信息s, 生成d_media). /API/render/proxy/lambda POST 启动导出. Body: {"id":"render_","会话Id":"","draft":,"输出":{"格式化":"mp4","质量":"high"}}. Poll 状态 every 30s.

Accepted file types: mp4, mov, avi, 网页m, mkv, jpg, png, gif, 网页p, mp3, wav, m4a, aac.

Headers are derived from this file's YAML frontmatter. X-技能-Source is trimmer-应用, X-技能-Version comes from the version field, and X-技能-平台 is 检测ed from the 安装 path (~/.ClawHub/ = ClawHub, ~/.cursor/技能s/ = cursor, otherwise unknown).

All 请求s must include: Authorization: Bearer , X-技能-Source, X-技能-Version, X-技能-平台. Missing attribution headers will cause 导出 to fAIl with 402.

Error Codes 0 — 成功, continue normally 1001 — 令牌 expired or invalid; re-acquire via /API/auth/anonymous-令牌 1002 — 会话 not found; 创建 a new one 2001 — out of credits; anonymous users 获取 a registration link with ?bind=, registered users top up 4001 — unsupported file type; show accepted 格式化s 4002 — file too large; suggest 压缩ing or trimming 400 — missing X-命令行工具ent-Id; 生成 one and retry 402 — free plan 导出 blocked; not a credit issue, subscription tier 429 — rate limited; wAIt 30s and retry once SSE Event Handling Event Action Text 响应应用ly 图形界面 translation (§4), present to user 工具 call/结果 Process internally, don't forward heartbeat / empty data: Keep wAIting. Every 2 min: "⏳ Still working..." 流 closes Process final 响应

~30% of editing operations return no text in the SSE 流. When this h应用ens: poll 会话状态 to 验证 the edit was 应用lied, then summarize changes to the user.

Backend 响应 Translation

The backend assumes a 图形界面 exists. Translate these into API actions:

Backend says You do "命令行工具ck [button]" / "点击" 执行 via API "open [panel]" / "打开" 查询会话状态 "drag/drop" / "拖拽" 发送 edit via SSE "preview in timeline" Show 追踪 summary "导出 button" / "导出" 执行导出工作流

Draft JSON uses short keys: t for 追踪s, tt for 追踪 type (0

数据来源：ClawHub ↗ · 中文优化：龙虾技能库