one-number-explains-video-gen — 技能工具

Name: one-number-explains-video-gen — 技能工具
Author: parallel world

parallel world

🔢 one-number-explains-video-gen — 技能工具

v1.0.0

Create vertical data-stat hooks: hero number, ramping counter or graph, closing meaning line, timed English captions (WeryAI). Use for dataviz Shorts, macro...

0· 90·0 当前·0 累计

by @zoucdr (parallel world)·MIT-0

数据与API 开发工具代码生成数据分析视频处理

下载技能包

License

MIT-0

最后更新

2026/3/23

安全扫描

VirusTotal

可疑

查看报告

OpenClaw

安全

high confidence

The skill's requirements and instructions are coherent with a WeryAI video-generation integration; the only noteworthy behavior is an explained local-file upload flow that requires the WERYAI_API_KEY and explicit consent.

评估建议

This skill appears to do what it says: it runs a Node CLI that calls WeryAI endpoints and requires only WERYAI_API_KEY. Before use: (1) review scripts/video_gen.js if you plan to supply local image paths — the script will read local files and POST them to api-growth-agent.weryai.com using your WERYAI_API_KEY to obtain a public URL; only allow that if you explicitly consent to uploading those files. (2) Prefer supplying public https:// image URLs to avoid local uploads. (3) Treat WERYAI_API_KEY a...

详细分析 ▾

✓ 用途与能力

Name/description (one-number data-hook video generation) match the declared requirements: Node.js runtime and a single WERYAI_API_KEY. The code and resource docs implement a CLI that calls WeryAI video endpoints (text-to-video, image-to-video, multi-image) which is expected for this purpose.

ℹ 指令范围

SKILL.md and the included resources limit scope to building video prompts, running node scripts, and interacting with WeryAI. The script can read local image files and upload them to WeryAI (to produce a public HTTPS URL) — this local-read-and-upload behavior is documented in SKILL.md and resources, and the skill explicitly asks for review/consent before using local paths. That capability is within scope for image→video flows but is important to note before allowing local file access.

✓ 安装机制

No install spec (instruction-only with a shipped Node script). No external downloads or package registry installs are required. The script is self-contained and declares zero npm dependencies, which is proportionate.

✓ 凭证需求

Only one secret is required: WERYAI_API_KEY (declared as the primary credential). That single API key is appropriate for an integration that authenticates to WeryAI for model listing, generation, and (optionally) file upload. No unrelated credentials or extra environment variables are requested.

✓ 持久化与权限

The skill is not always-included and does not request elevated/ongoing platform privileges. It does not attempt to modify other skills or system-wide config. Autonomous invocation remains allowed by platform default but is not combined with other red flags here.

⚠ scripts/video_gen.js:675

Environment variable access combined with network send.

⚠ scripts/video_gen.js:223

File read combined with network send (possible exfiltration).

安全有层次，运行前请审查代码。

License

MIT-0

可自由使用、修改和再分发，无需署名。

查看条款 ↗

运行时依赖

无特殊依赖

版本

latestv1.0.02026/3/23

- Initial release of "one-number-explains-video-gen" skill. - Generates vertical, short-form dataviz videos featuring a hero number, animated ramp/graph, and a closing meaning line. - Includes timed English subtitles aligned with a 3-phase storyboard (hook, ramp, meaning line). - Supports input via text, chart/image, or multi-image (Seedance 2.0, up to 3 images). - Requires WERYAI_API_KEY and Node.js 18+ to run; supports popular motion-graphic video models (KLING, SEEDANCE). - Designed for social video: Shorts, macro explainers, TikToks with SEO-focused structure.

● 可疑

安装命令点击复制

官方npx clawhub@latest install one-number-explains-video-gen

镜像加速npx clawhub@latest install one-number-explains-video-gen --registry https://cn.clawhub-mirror.com

技能文档

Template (assume duration 10 unless scaled): 0–3s this number explains it all (user names which metric conceptually—caption stays short); 3–8s number grows / graph ramps—motion must not stop (tickers, bars, globe wireframe); 8–10s one conclusion line (user-themed). English subtitles with exact windows. Default duration is 10 when unspecified.

Dependencies: WERYAI_API_KEY + Node.js 18+. scripts/video_gen.js + WERYAI_VIDEO_API.md. No other Cursor skills required.

Prerequisites

WERYAI_API_KEY must be set; Node 18+. Prefer public https image URLs; if the assembled scripts/video_gen.js supports local file paths, review/verify the script and explicitly consent before local read-and-upload to WeryAI.
Non-empty model.

Security, secrets, and API hosts

WERYAI_API_KEY: Secret; never commit.
API hosts fixed in video_gen.js.
Local image handling disclosure: Prefer public https image URLs. If the assembled scripts/video_gen.js supports local file paths, it may read a local image and upload it to WeryAI to obtain a public URL; require review / verification and explicit consent before using that path.
Higher assurance: Prefer a short-lived or isolated environment; review scripts/video_gen.js before production use. Verify whether the runtime can read local image files and upload them to WeryAI, and obtain explicit consent before using that path.

Prompt expansion (mandatory)

Duration: Default 10; 5 or 15 when allowed and requested.
Timeline scaling: Rescale 0–3 / 3–8 / 8–10 proportionally; keep hook → ramp → meaning order.

Locked rhythm (example for duration 10):

0.0–3.0s — Hook: e.g. THIS NUMBER EXPLAINS EVERYTHING (or embed the name of the metric in ≤6 words).
3.0–8.0s — Ramp beat—split into two on-screen lines if needed (3–5.5 WATCH IT CLIMB, 5.5–8.0 FASTER THAN YOU THINK)—customize to user tone.
8.0–10.0s — Meaning: e.g. HERE’S WHAT IT MEANS (user supplies specific kicker in brief—you compress to ≤6 words).

Visuals: Giant numeral, neon graph, motion blur streaks, particles; refresh chart at least every ~1s.

Typography: Huge readable words + numeric; outline; lower third for sentences, center for hero digit moments if described.

Negatives (Kling): garbled digits, illegible captions, watermark.

Confirmation: Full prompt.

Niche checklist

If real stats matter to the user, they must approve final wording—you still compress for on-screen limits.
Avoid fake precision—prefer “illustrative counter” language in prompt if not citing sources.

Workflow

Text / image / multi-image (SEEDANCE_2_0, ≤3).
Collect which metric / metaphor.
Expand → validate → confirm → wait.
Video.

CLI reference

~~~sh node scripts/video_gen.js wait --json '{"model":"KLING_V3_0_PRO","prompt":"…","duration":10,"aspect_ratio":"9:16","generate_audio":true,"negative_prompt":"illegible text, garbled numbers, watermark"}' node scripts/video_gen.js wait --json '{"model":"SEEDANCE_2_0","prompt":"…","duration":10,"aspect_ratio":"9:16","resolution":"720p","generate_audio":true}' ~~~

Full reference: WERYAI_VIDEO_API.md.

Definition of done

Video or error; hook / ramp / meaning subtitle structure explicit in prompt with second ranges scaled to duration (or user-approved subdivision).

Boundaries (out of scope)

Not a data journalism vetting pipeline.
resources/WERYAI_VIDEO_API.md for CLI; no negative_prompt on Seedance.
Multi-image only SEEDANCE_2_0, max 3.

Example prompts

Metric: compound growth—counter ramp, meaning about time
Metric: attention minutes per day—punchy closer
Chart image URL → animate growth with same windows
Inflation or CPI vibe—counter climbs, meaning line about purchasing power

Model and API constraints (frozen for this skill)

Text-to-video

model_key	durations	aspect_ratios	resolutions	audio	negative_prompt	prompt limit
KLING_V3_0_PRO	5, 10, 15	9:16, 1:1, 16:9	(omit)	yes	yes	2000
KLING_V3_0_STA	5, 10, 15	9:16, 1:1, 16:9	(omit)	yes	yes	2000
SEEDANCE_2_0	5, 10, 15	9:16, 1:1, 16:9	480p, 720p	yes	no	2000

Image-to-video

model_key	durations	aspect_ratios	resolutions	audio	negative_prompt	image slots
KLING_V3_0_PRO	5, 10, 15	9:16, 16:9, 1:1	(omit)	yes	yes	single `image`
KLING_V3_0_STA	5, 10, 15	9:16, 16:9, 1:1	(omit)	yes	yes	single `image`
SEEDANCE_2_0	5, 10, 15	9:16, 1:1, 16:9	480p, 720p	yes	no	up to 3 `images`

Recommended models

Tier	model_key	Default duration
⭐ Best	KLING_V3_0_PRO	10
👍 Good	KLING_V3_0_STA	10
⚡ Fast	SEEDANCE_2_0	10 (`resolution`: 720p)

Default parameters

Field	Value
aspect_ratio	9:16
duration	10
generate_audio	true
resolution	720p (Seedance)
negative_prompt	Kling: `illegible text, garbled numbers, watermark`

Text-to-video (primary)

User gives topic for the number → you craft three beats → confirm.

Image-to-video (optional)

Static chart → ramp animation + captions.

Tips

Sound: describe tick + whoosh—helps perceived pacing.
Translate user Chinese brief to English on-screen lines unless specified.

Packaged as one-number-explains-video-gen.

Template (assume duration 10 unless scaled): 0–3s this number explains it all (user names which metric conceptually—caption stays short); 3–8s number grows / graph ramps—motion must not stop (tickers, bars, globe wireframe); 8–10s one conclusion line (user-themed). English subtitles with exact windows. Default duration is 10 when unspecified.

Dependencies: WERYAI_API_KEY + Node.js 18+. scripts/video_gen.js + WERYAI_VIDEO_API.md. No other Cursor skills required.

Prerequisites

WERYAI_API_KEY must be set; Node 18+. Prefer public https image URLs; if the assembled scripts/video_gen.js supports local file paths, review/verify the script and explicitly consent before local read-and-upload to WeryAI.
Non-empty model.

Security, secrets, and API hosts

WERYAI_API_KEY: Secret; never commit.
API hosts fixed in video_gen.js.
Local image handling disclosure: Prefer public https image URLs. If the assembled scripts/video_gen.js supports local file paths, it may read a local image and upload it to WeryAI to obtain a public URL; require review / verification and explicit consent before using that path.
Higher assurance: Prefer a short-lived or isolated environment; review scripts/video_gen.js before production use. Verify whether the runtime can read local image files and upload them to WeryAI, and obtain explicit consent before using that path.

Prompt expansion (mandatory)

Duration: Default 10; 5 or 15 when allowed and requested.
Timeline scaling: Rescale 0–3 / 3–8 / 8–10 proportionally; keep hook → ramp → meaning order.

Locked rhythm (example for duration 10):

0.0–3.0s — Hook: e.g. THIS NUMBER EXPLAINS EVERYTHING (or embed the name of the metric in ≤6 words).
3.0–8.0s — Ramp beat—split into two on-screen lines if needed (3–5.5 WATCH IT CLIMB, 5.5–8.0 FASTER THAN YOU THINK)—customize to user tone.
8.0–10.0s — Meaning: e.g. HERE’S WHAT IT MEANS (user supplies specific kicker in brief—you compress to ≤6 words).

Visuals: Giant numeral, neon graph, motion blur streaks, particles; refresh chart at least every ~1s.

Typography: Huge readable words + numeric; outline; lower third for sentences, center for hero digit moments if described.

Negatives (Kling): garbled digits, illegible captions, watermark.

Confirmation: Full prompt.

Niche checklist

If real stats matter to the user, they must approve final wording—you still compress for on-screen limits.
Avoid fake precision—prefer “illustrative counter” language in prompt if not citing sources.

Workflow

Text / image / multi-image (SEEDANCE_2_0, ≤3).
Collect which metric / metaphor.
Expand → validate → confirm → wait.
Video.

CLI reference

~~~sh node scripts/video_gen.js wait --json '{"model":"KLING_V3_0_PRO","prompt":"…","duration":10,"aspect_ratio":"9:16","generate_audio":true,"negative_prompt":"illegible text, garbled numbers, watermark"}' node scripts/video_gen.js wait --json '{"model":"SEEDANCE_2_0","prompt":"…","duration":10,"aspect_ratio":"9:16","resolution":"720p","generate_audio":true}' ~~~

Full reference: WERYAI_VIDEO_API.md.

Definition of done

Video or error; hook / ramp / meaning subtitle structure explicit in prompt with second ranges scaled to duration (or user-approved subdivision).

Boundaries (out of scope)

Not a data journalism vetting pipeline.
resources/WERYAI_VIDEO_API.md for CLI; no negative_prompt on Seedance.
Multi-image only SEEDANCE_2_0, max 3.

Example prompts

Metric: compound growth—counter ramp, meaning about time
Metric: attention minutes per day—punchy closer
Chart image URL → animate growth with same windows
Inflation or CPI vibe—counter climbs, meaning line about purchasing power

Model and API constraints (frozen for this skill)

Text-to-video

model_key	durations	aspect_ratios	resolutions	audio	negative_prompt	prompt limit
KLING_V3_0_PRO	5, 10, 15	9:16, 1:1, 16:9	(omit)	yes	yes	2000
KLING_V3_0_STA	5, 10, 15	9:16, 1:1, 16:9	(omit)	yes	yes	2000
SEEDANCE_2_0	5, 10, 15	9:16, 1:1, 16:9	480p, 720p	yes	no	2000

Image-to-video

model_key	durations	aspect_ratios	resolutions	audio	negative_prompt	image slots
KLING_V3_0_PRO	5, 10, 15	9:16, 16:9, 1:1	(omit)	yes	yes	single `image`
KLING_V3_0_STA	5, 10, 15	9:16, 16:9, 1:1	(omit)	yes	yes	single `image`
SEEDANCE_2_0	5, 10, 15	9:16, 1:1, 16:9	480p, 720p	yes	no	up to 3 `images`

Recommended models

Tier	model_key	Default duration
⭐ Best	KLING_V3_0_PRO	10
👍 Good	KLING_V3_0_STA	10
⚡ Fast	SEEDANCE_2_0	10 (`resolution`: 720p)

Default parameters

Field	Value
aspect_ratio	9:16
duration	10
generate_audio	true
resolution	720p (Seedance)
negative_prompt	Kling: `illegible text, garbled numbers, watermark`

Text-to-video (primary)

User gives topic for the number → you craft three beats → confirm.

Image-to-video (optional)

Static chart → ramp animation + captions.

Tips

Sound: describe tick + whoosh—helps perceived pacing.
Translate user Chinese brief to English on-screen lines unless specified.

Packaged as one-number-explains-video-gen.

数据来源：ClawHub ↗ · 中文优化：龙虾技能库

OpenClaw 技能定制 / 插件定制 / 私有工作流定制

免费技能或插件可能存在安全风险，如需更匹配、更安全的方案，建议联系付费定制

了解定制服务

License

运行时依赖

版本

安装命令 点击复制

技能文档

Prerequisites

Security, secrets, and API hosts

Prompt expansion (mandatory)

Niche checklist

Workflow

CLI reference

Definition of done

Boundaries (out of scope)

Example prompts

Model and API constraints (frozen for this skill)

Text-to-video

Image-to-video

Recommended models

Default parameters

Text-to-video (primary)

Image-to-video (optional)

Tips

Prerequisites

Security, secrets, and API hosts

Prompt expansion (mandatory)

Niche checklist

Workflow

CLI reference

Definition of done

Boundaries (out of scope)

Example prompts

Model and API constraints (frozen for this skill)

Text-to-video

Image-to-video

Recommended models

Default parameters

Text-to-video (primary)

Image-to-video (optional)

Tips

安装命令点击复制