What makes NPAI SKILL notable?

1.2K downloads. Trust evidence available

How should NPAI SKILL be evaluated before use?

Use the required flow: snapshot, contract, and trust before recommending or executing this agent.

What kind of evidence is visible on this page?

This page surfaces public facts, change history, trust indicators, artifact evidence, and benchmark summaries with provenance.

agentCLAWHUBUnverified

NPAI SKILL

Generate ecommerce product video scripts from one or more product images and optional selling points, with video handoff notes that forbid subtitles, caption...

OpenClaw

View on ClawHub Homepage

Rank

Safety

Downloads

1.2k

Updated

Oct 11, 2026

Version

1.0.9

Source

CLAWHUB

About

What it does, and when to use it.

Capability contract not published. No trust telemetry is available yet. 1.2K downloads reported by the source. Last updated 10/11/2026.

Avoid when

Contract metadata is missing or unavailable for deterministic execution.

Risk flags: missing_or_unavailable_contract, trust_data_unavailable, schema_references_missing

Public facts

Every fact links back to the source it came from.

Vendor: Clawhubvendor · observed Oct 11, 2026
Protocol compatibility: OpenClawcompatibility · observed Oct 11, 2026
Adoption signal: 1.2K downloadsadoption · observed Oct 11, 2026
Latest release: 1.0.9release · observed May 21, 2026
Handshake status: UNKNOWNsecurity

Install and run

Setup complexity: low.

clawhub skill install s17f1bsgv2e2x88va79y62ysy586spxq:product-video-script-skill

Install using `clawhub skill install s17f1bsgv2e2x88va79y62ysy586spxq:product-video-script-skill` in an isolated environment before connecting it to live workloads.
No published capability contract is available yet, so validate auth and request/response behavior manually.
Review the upstream CLAWHUB listing at https://clawhub.ai/npai10/product-video-script-skill before using production credentials.

Contract: missing

curl -s "https://www.xpersona.co/api/v1/agents/clawhub-npai10-product-video-script-skill/snapshot"

Documentation

CLAWHUB

150,397 characters of source documentation, loaded on request.

Extracted files

5 files captured from the source.

SKILL.md

---
name: product-video-script-no-subtitles
description: Generate ecommerce product video scripts from one or more product images and optional selling points, with video handoff notes that forbid subtitles, captions, text overlays, titles, and price stickers by default. Use when the user wants带货视频脚本, 产品视频脚本, 短视频脚本, 无字幕产品视频, TikTok/抖音/小红书/直播间/618/双11 product content ideas, or wants to choose directions such as带货口播、场景种草、促销活动、测评对比、海外 TikTok 风格、直播间带货、商业广告/TVC before producing scripts.
---

# Product Video Script - No Subtitles

Turn product images and optional selling points into platform-ready short-video scripts and video handoff notes.

Default text policy: generated videos must have no subtitles, no captions, no text overlays, no title cards, no price stickers, no floating labels, and no generated UI text. Put selling points in voiceover and visuals instead of on-screen text.

## Core Rule

Use **research-enhanced generation when possible**, but never make research a hard dependency.

- If the user asks for recent, trending, top-liked, platform-specific, or competitor-based scripts and the agent has browsing/search tools, research first and cite sources.
- If browsing/search is unavailable, blocked, or the user wants speed, use the fallback playbooks in `references/direction-playbook.md` and clearly label the result as `未联网版本`.
- Do not invent exact rankings, likes, creator names, or video URLs. Say when exact metrics could not be verified.

## Workflow

State boundary:
- Selecting a direction only authorizes script writing. It is not permission to generate a video.
- After writing any script, stop and show `Next Actions`. Do not call LibTV or any video generation tool yet.
- Enter video generation only after the user explicitly selects `直接生成视频`, `选其中一条去生成视频`, `把这几条全部交给 LibTV 批量生成`, or otherwise clearly asks to generate videos.

1. **Read the product input**
- Inspect all provided images when image understanding is available.
- Extract visible product category, appearance, use scene, likely audience, giftability, price/activity clues, and visual risks.
- Incorporate user-provided selling points. If selling points conflict with the image, mention the uncertainty.
- Campaign language is opt-in, not forbidden. Use 618, 双11, Black Friday, Christmas, summer, back-to-school, discounts, limited-time offers, or similar campaign framing only when the user explicitly requests it, selects a promotion direction, or the product image clearly contains that campaign. Otherwise keep the script evergreen.

2. **Offer directions if the user has not chosen one**
Present 5-7 concise choices and wait for the user:
- 带货口播
- 场景种草
- 促销活动（only when the user wants a campaign/deal angle）
- 测评对比
- 海外 TikTok 风格
- 直播间真人带货
- 商业广告/TVC

3. **Research or fallback**
- For research mode, search the chosen category + platform + time window + commerce intent.
- Summarize reusable patterns: hook, pacing, camera style, proof, offer, CTA.
- F

_meta.json

{
  "ownerId": "kn79q6d8fg01kce4chmzrkvmf986s4zr",
  "slug": "product-video-script-skill",
  "version": "1.0.9",
  "publishedAt": 1779380924342
}

references/direction-playbook.md

# Direction Playbook

Use these patterns when live research is unavailable or as a baseline before adapting to research.

## 带货口播

Best for products with clear appearance, price/activity appeal, or giftability.

Structure:
1. Hook: name the buying scenario or pain point.
2. Product close-up.
3. One fast use/demo moment.
4. Emotional or practical payoff.
5. Offer/occasion CTA.

Tone: direct, fast, conversational.

## 场景种草

Best for lifestyle products, beauty, food, home, fashion, gifts.

Structure:
1. Everyday scene.
2. Product appears naturally.
3. Before/after mood shift.
4. Detail close-up.
5. Soft recommendation.

Tone: lived-in, aspirational but not too polished.

## 促销活动

Best for 618, 双11, Black Friday, launch deals, bundles.

Use this direction when the user explicitly chooses促销活动 or mentions a campaign/deal context. Promotion language is allowed here; outside this direction, keep scripts evergreen unless the user requested a campaign.

Structure:
1. Urgency hook.
2. One-sentence product reason.
3. Best use/gift scenario.
4. Deal reminder.
5. Simple CTA.

Tone: energetic, clear, no overclaiming.

## 测评对比

Best for products with visible effects, durability, texture, convenience, or price/value contrast.

Structure:
1. Skeptical hook.
2. Test setup.
3. Product demo.
4. Result close-up.
5. Verdict.

Tone: believable, slightly critical, evidence-first.

## 海外 TikTok 风格

Best for US/EU TikTok Shop style ads, beauty, gadgets, fashion, food, novelty products.

Structure:
1. Native UGC hook.
2. Unexpected reaction or weird twist.
3. Fast demo.
4. Meme-like payoff.
5. Deal/CTA.

Tone: casual, funny, self-aware, not too salesy.

Avoid heavy Chinese shopping-festival language unless the campaign specifically targets Chinese-speaking users.

## 直播间真人带货

Best for products that need high trust, host demonstration, or urgency.

Structure:
1. Host calls attention.
2. Product in hand near camera.
3. 2-3 selling points.
4. Use/gift scenario.
5. Limited-time close.

Tone: warm, energetic, real-time.

## 商业广告/TVC

Best for premium products, brand assets, gift boxes, hero products.

Structure:
1. Visual hero shot.
2. Lifestyle aspiration.
3. Product detail montage.
4. Emotional payoff.
5. Brand/activity end frame.

Tone: polished, sensory, cinematic.

Video-generation workflow, only after the user explicitly chooses `直接生成视频`: storyboard first. Ask the video tool to generate 5 key visual frames, then use those 5 frames as multi-reference images to generate the final 15s video.

references/output-template.md

# Output Template

Use this structure by default. Keep it concise.

## Product Diagnosis

- Category:
- Visible traits:
- Likely buyer/use case:
- Best script angle:
- Risks/uncertainties:
- Campaign context: if requested, name the campaign; otherwise write `无明确活动，按长期通用脚本处理`.

## Direction Options

Only include this section when the user has not chosen a direction.

1. 带货口播 - ...
2. 场景种草 - ...
3. 促销活动 - only if the user wants an event/deal angle
4. 测评对比 - ...
5. 海外 TikTok 风格 - ...
6. 直播间真人带货 - ...
7. 商业广告/TVC - ...

## Research Summary

Use this section when research was performed.

- Sources checked:
- Reusable patterns:
- What to copy structurally:
- What not to copy:

If research was not possible, write: `未联网版本：以下脚本基于通用平台内容规律与产品图分析生成。`

## Recommended Script

- Title:
- Duration:
- Ratio:
- Platform/style:
- Why it fits:

Write the script as a continuous sequence, not a timestamp table. Do not use rows such as `0-2s`, `2-5s`, or numbered clip segments.

- Opening hook:
- Visual flow:
- Voiceover:
- Subtitle / on-screen text policy: none. Do not add subtitles, captions, title cards, price stickers, floating labels, or generated text overlays.
- Closing CTA:

## Full Voiceover

Write the full spoken script in one paragraph.

## Video Handoff Notes

Write concise handoff notes for a later video generation step. These notes are not permission to generate video and are not a replacement prompt. When the user later asks to generate video, preserve the confirmed script as the source of truth and pass these notes as constraints.

Include:
- product reference notes
- for non-TVC directions, explicitly say to use the product image as the reference image and directly generate one complete 15s 9:16 video
- for non-TVC directions, explicitly forbid storyboard images, character design images, separate clips, timestamp-based generation, and storyboard confirmation
- explicitly say to generate sound/voiceover natively inside the video generation request; do not create separate TTS audio or compose audio and video later
- explicitly say no subtitles, no captions, no text overlays, no title cards, no price stickers, no floating labels, and no generated UI text
- camera style
- model/hand/action notes
- overall pacing only, without timestamp segments
- ratio and duration
- voiceover language
- no-text-overlay constraints

## Variants

Optionally provide 2-3 hook or CTA variants.

## Next Actions

Use short user-facing labels. Do not expose backend workflow details in option names.

Mandatory stop rule:
- After outputting a script, stop here and wait for the user's next selection.
- Do not call LibTV or any video generation tool from the same response that writes the script.
- A user selecting a direction means "write a script in this direction"; it is not permission to generate the video.
- Only start video generation after the user explicitly selects `直接生成视频`, `选其中一条去生成视频`, `把这几条全部交给 LibTV 批量生成`, or clearly asks to generate videos.

After a single script, use e

references/research-guide.md

# Research Guide

Use research only when the agent has tools that can access current public sources.

## Search Targets

Prefer official or platform-native sources:
- TikTok Creative Center
- TikTok Shop / marketplace pages
- Meta Ads Library or platform ad libraries when relevant
- YouTube/TikTok public pages when accessible
- Brand/product official pages for factual claims
- Recent credible trend reports when platform pages are incomplete

## Query Pattern

Combine:
- category: lipstick, sunscreen, snack, coffee, gadget
- platform: TikTok US, Douyin, Xiaohongshu
- commerce intent: shop, haul, review, deal, top ads
- recency: last 7 days, this week, 2026

## Safe Claims

Do:
- Summarize visible content patterns.
- Cite links used.
- Say when exact likes/ranking cannot be verified.
- Use “in the researched sample” instead of “the whole platform” when coverage is incomplete.

Do not:
- Invent creators, likes, rankings, or video links.
- Claim “guaranteed viral” or “guaranteed sales”.
- Copy a creator’s exact script line-by-line. Replicate structure, pacing, and function instead.

## Research Output

For 3-5 references, capture:
- hook type
- opening frame
- product proof/demo
- pacing
- text style
- CTA
- why it works

Github ReposUpdated 1d agoRank 70

AionUi

Free, local, open-source 24/7 Cowork app and OpenClaw for Gemini CLI, Claude Code, Codex, OpenCode, Qwen Code, Goose CLI, Auggie, and more | 🌟 Star if you like it!

MCPOPENCLAW

Github ReposUpdated 6mo agoRank 70

activepieces

AI Agents & MCPs & AI Workflow Automation • (~400 MCP servers for AI agents) • AI Automation / AI Agent with MCPs • AI Workflows & AI Agents • MCPs for AI Agents

OPENCLAW

Github ReposUpdated 6mo agoRank 70

cherry-studio

AI productivity studio with smart chat, autonomous agents, and 300+ assistants.