📦 Generation Text Generator — Generation Text 生成器

v1.0.0

获取 text-driven videos ready to post, without touching a single slider. 上传 your text prompts (TXT, DOCX, PDF, MP4, up to 200MB), say something like "gene...

0· 7·0 当前·0 累计

by @dsewell-583h0

开发工具代码生成文档工具文件处理系统工具

下载技能包

安全扫描

VirusTotal

无害

查看报告

OpenClaw

可疑

medium confidence

The 技能 mostly matches its 状态d purpose (上传 text/files to a remote video generation API) but the 运行time instructions ask the 代理 to inspect local 安装/config paths that weren’t declared and to 上传 user files to an external 服务 — these mismatches and file系统访问 deserve clarification before 安装ing.

评估建议

What to consider before 安装ing: - This 技能 will 上传 user files (documents, videos) and prompts to a remote 服务 at mega-API-prod.nemovideo.AI for processing. Only use it with content you are comfortable 发送ing to an external server. - It prefers a NEMO_令牌 but can mint an anonymous 令牌 by calling the 服务; consider using a short-lived or throwaway 令牌 if you don't want to store persistent 凭证s. - The 技能.md asks the 代理 to 检测安装 paths and references a local config directory (~/.config/nemovideo/). The registr...

详细分析 ▾

ℹ 用途与能力

The 技能's name and description (生成 text-driven video content) align with the API 端点s and flows described (会话 creation, SSE text generation, 上传, render/导出). 请求ing a NEMO_令牌 is proportionate for an 认证d remote 服务. However, the 技能.md frontmatter also 列出s a config path (~/.config/nemovideo/) and the 运行time text instructs 检测ing 安装 paths (~/.ClawHub/, ~/.cursor/技能s/) to 设置 X-技能-平台 — file系统 inspection of those paths is outside the 状态d purpose and is not reflected in the registry metadata (registry 报告ed no required config paths). This mismatch is unexpected.

⚠ 指令范围

The 技能.md instructs connecting to an external API, 上传ing user files (TXT, DOCX, PDF, MP4 up to 200MB), generating anonymous 令牌s if NEMO_令牌 is absent, and saving 会话_id for further calls — these are consistent with the feature. Concern: the instructions explicitly direct the 代理 to 检测 the 代理's 安装 path and to use/inspect local config paths to populate headers (X-技能-平台), which implies reading file系统 paths/config not declared elsewhere. The 技能 also instructs polling 状态 and persistent 会话 storage; the 代理 will therefore transmit user content and metadata to an external host (mega-API-prod.nemovideo.AI). That is expected for this feature but is a notable 隐私/security surface; users should confirm the trustworthiness and retention policy of that 端点.

✓ 安装机制

This is an instruction-only 技能 with no 安装 spec and no code files, so nothing is written to disk by an 安装er. That reduces 安装ation risk. 运行time behavior still performs network calls and may read local paths as described above.

⚠ 凭证需求

The declared primaryEnv is NEMO_令牌, which is 应用ropriate for authenticating with the described API. However, the 技能.md frontmatter and 运行time text imply reading a local config directory (~/.config/nemovideo/) and 安装 paths to 设置 headers — those file系统访问es were not declared in the registry metadata summary. Requiring 访问 to local config paths or arbitrary file系统 locations would be disproportionate for a pure API 命令行工具ent unless used to reuse an existing NEMO_令牌; the 技能 should explicitly declare any config paths it will read.

✓ 持久化与权限

always:false and normal 代理 invocation are used. The 技能 saves 会话_id/状态 for interacting with the remote API, which is reasonable for this 工作流. There is no instruction to modify other 技能s or 系统-wide 设置tings. No forced always-on privilege is 请求ed.

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 generation-text-generator

镜像加速npx clawhub@latest install generation-text-generator --registry https://cn.longxiaskill.com

技能文档

获取ting 启动ed

Ready when you are. Drop your text prompts here or describe what you want to make.

Try saying:

"生成 a short description of a product launch video into a 1080p MP4" "生成 a script for a 30-second explAIner video about our new 应用" "generating video scripts and on-screen text from written prompts for content 创建器s" Automatic 设置up

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

令牌: If NEMO_令牌环境 variable is already 设置, use it and skip to 会话 below.

Free 令牌: 生成 a UUID as 命令行工具ent identifier, then POST to https://mega-API-prod.nemovideo.AI/API/auth/anonymous-令牌 with header X-命令行工具ent-Id: . The 响应 field data.令牌 becomes your NEMO_令牌 (100 credits, 7-day expiry).

会话: POST to https://mega-API-prod.nemovideo.AI/API/tasks/me/with-会话/nemo_代理 with Bearer auth and body {"task_name":"project"}. Save 会话_id from the 响应.

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

Generation Text 生成器 — 生成 Text for Video Content

发送 me your text prompts and describe the 结果 you want. The AI text generation 运行s on remote GPU nodes — nothing to 安装 on your machine.

A quick example: 上传 a short description of a product launch video, type "生成 a script for a 30-second explAIner video about our new 应用", and you'll 获取 a 1080p MP4 back in roughly 20-40 seconds. All rendering h应用ens server-side.

Worth noting: shorter, specific prompts produce more accurate and usable text 输出.

Matching 输入 to Actions

User prompts referencing generation text 生成器, 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.

Headers are derived from this file's YAML frontmatter. X-技能-Source is generation-text-生成器, 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).

Include Authorization: Bearer and all attribution headers on every 请求 — omitting them triggers a 402 on 导出.

API base: https://mega-API-prod.nemovideo.AI

创建会话: POST /API/tasks/me/with-会话/nemo_代理 — body {"task_name":"project","language":""} — returns task_id, 会话_id.

发送 message (SSE): POST /运行_sse — body {"应用_name":"nemo_代理","user_id":"me","会话_id":"","new_message":{"parts":[{"text":""}]}} with Accept: text/event-流. Max timeout: 15 minutes.

上传: POST /API/上传-video/nemo_代理/me/ — file: multipart -F "files=@/path", or URL: {"urls":[""],"source_type":"url"}

Credits: 获取 /API/credits/balance/simple — returns avAIlable, frozen, total

会话状态: 获取 /API/状态/nemo_代理/me//latest — key fields: data.状态.draft, data.状态.video_信息s, data.状态.生成d_media

导出 (free, no credits): POST /API/render/proxy/lambda — body {"id":"render_","会话Id":"","draft":,"输出":{"格式化":"mp4","质量":"high"}}. Poll 获取 /API/render/proxy/lambda/ every 30s until 状态 = completed. 下载 URL at 输出.url.

Supported 格式化s: mp4, mov, avi, 网页m, mkv, jpg, png, gif, 网页p, mp3, wav, m4a, aac.

Reading the SSE 流

Text 事件 go strAIght to the user (after 图形界面 translation). 工具 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 流 without any text. When that h应用ens, poll /API/状态 to confirm the timeline changed, then tell the user what was 更新d.

Translating 图形界面 Instructions

The backend 响应s as if there's a visual interface. Map its instructions to API calls:

"命令行工具ck" or "点击" → 执行 the action via the relevant 端点 "open" or "打开" → 查询会话状态 to 获取 the data "drag/drop" or "拖拽" → 发送 the edit command through SSE "preview in timeline" → show a text summary of current 追踪s "导出" or "导出" → 运行 the 导出工作流

Draft field m应用ing: t=追踪s, tt=追踪 type (0=video, 1=audio, 7=text), sg=segments, d=duration(ms), m=metadata.

Timeline (3 追踪s): 1. Video: city timelapse (0-10s) 2. BGM: Lo-fi (0-10s, 35%) 3. Title: "Urban Dreams" (0-3s)

Error Codes 0 — 成功, continue nor

数据来源：ClawHub ↗ · 中文优化：龙虾技能库