← Back to Skills Marketplace
caoyacheng

Ai News Poster

by 小曹学AI · GitHub ↗ · v1.0.0
cross-platform ⚠ suspicious
372
Downloads
0
Stars
0
Active Installs
1
Versions
Install in OpenClaw
/install ai-news-poster
Description
Generate fixed-template daily AI news posters from five news items. Use when the user asks to create a poster, social card, or image summary for "today's AI...
README (SKILL.md)

AI News Poster

Create one fixed-style poster from exactly 5 AI news items.

When to use this skill

Use this skill when the user wants:

  • A daily AI news poster
  • A fixed template visual for 5 AI headlines
  • A Chinese or bilingual social poster summarizing AI updates

If the user asks for a long-form report, article, PPT, or spreadsheet, do not use this skill.

Input contract

Before generating the poster, normalize input into this structure:

{
  "date": "YYYY-MM-DD",
  "title": "今日AI资讯速览",
  "news": [
    {"headline": "新闻1标题", "summary": "一句话摘要(18-32字)", "source": "来源", "tag": "模型/产品/融资/政策/研究"},
    {"headline": "新闻2标题", "summary": "一句话摘要(18-32字)", "source": "来源", "tag": "模型/产品/融资/政策/研究"},
    {"headline": "新闻3标题", "summary": "一句话摘要(18-32字)", "source": "来源", "tag": "模型/产品/融资/政策/研究"},
    {"headline": "新闻4标题", "summary": "一句话摘要(18-32字)", "source": "来源", "tag": "模型/产品/融资/政策/研究"},
    {"headline": "新闻5标题", "summary": "一句话摘要(18-32字)", "source": "来源", "tag": "模型/产品/融资/政策/研究"}
  ],
  "footer": "数据来源: 公开新闻整理",
  "brand": "你的品牌名"
}

Rules:

  • Always use exactly 5 news items.
  • If more than 5 are provided, keep the most important 5 and explain filtering in one sentence.
  • If fewer than 5 are provided, ask for missing items.
  • Remove hype and keep each summary factual.

Fixed poster template (must follow)

Canvas

  • Size: 1080 x 1350 (4:5)
  • Background: deep navy gradient (#0B1020 to #121A33)
  • Safe margin: 64px on all sides

Typography

  • Main title: 72px bold, white
  • Date subtitle: 32px medium, #A9B4D0
  • News headline: 38px semibold, white
  • News summary: 28px regular, #D6DEFF
  • Meta line (tag + source): 24px medium, #8FA2D8
  • Footer: 22px regular, #93A0C3

Layout

  1. Top block:
    • Main title (今日AI资讯速览)
    • Date line (YYYY-MM-DD)
  2. Body block:
    • 5 cards in a single vertical column, evenly spaced
    • Each card includes:
      • Index badge (01 to 05)
      • Headline (single line preferred, max 24 Chinese chars)
      • Summary (1 line, max 32 Chinese chars)
      • Meta line: #tag | source
  3. Bottom block:
    • Left: footer text
    • Right: brand mark text

Visual style

  • Card background: translucent white 8%-10%
  • Card border: 1px #2B3C73
  • Corner radius: 18px
  • Use one accent color for badges: #6AA8FF
  • Keep high contrast; avoid decorative clutter

Generation workflow

  1. Validate and normalize 5 news items.
  2. Rewrite each summary to one concise sentence (18-32 Chinese chars).
  3. Build poster JSON following the input contract.
  4. Generate one final poster image using:
    • python scripts/render.py \x3Cinput.json> \x3Coutput.png>
  5. If needed, install dependency once:
    • python -m pip install pillow
  6. Self-check before final output:
    • Exactly 5 items
    • No overflow/cropping
    • Typography hierarchy is clear
    • Source shown for all items

Utility scripts

  • Renderer: scripts/render.py
  • Sample input: examples/input.sample.json

Quick start:

  • python scripts/render.py examples/input.sample.json output/today-ai-news.png

Manual copy flow (fallback when script is unavailable):

  • Build poster copy using the exact order:
    • Title -> Date -> News01..News05 -> Footer -> Brand
  • Render one final poster image in 1080x1350.

Poster text template

Use this content skeleton before rendering:

[TITLE] 今日AI资讯速览
[DATE] 2026-02-28

[01] {headline}
{summary}
#{tag} | {source}

[02] {headline}
{summary}
#{tag} | {source}

[03] {headline}
{summary}
#{tag} | {source}

[04] {headline}
{summary}
#{tag} | {source}

[05] {headline}
{summary}
#{tag} | {source}

[FOOTER] 数据来源: 公开新闻整理
[BRAND] {brand}

Output requirements

  • Primary output: one poster image file (.png)
  • Optional companion output: the normalized JSON used for rendering
  • Keep output deterministic: same input should produce same layout structure

Example trigger prompts

  • "把今天 5 条 AI 新闻做成固定模版海报"
  • "按我们日更样式生成一张 AI 资讯图,给小红书发"
  • "Use today's five AI headlines and make a poster card"
Usage Guidance
This skill is not obviously malicious, but it is inconsistent: SKILL.md promises automatic summary rewriting and filtering when >5 items, while the shipped script will error unless exactly 5 items are provided and will render the headlines/summaries as-is. The script also uses hardcoded top title text and different colors than the markdown spec. Before installing or using it in production: 1) review/modify scripts/render.py if you need the skill to accept >5 items, perform selection/filtering, or rewrite summaries; 2) test the renderer locally with examples/input.sample.json to confirm the visual output matches your brand; 3) ensure Pillow and desired fonts are available on your host (the script tries macOS font paths and falls back to defaults); 4) if you require the poster title to come from input.title, change the hardcoded strings in render.py. If you need stronger assurance (no hidden behavior), open the full script and run it in a sandbox or have a developer audit the small mismatches noted above.
Capability Analysis
Type: OpenClaw Skill Name: ai-news-poster Version: 1.0.0 The ai-news-poster skill is a legitimate utility designed to generate image-based news summaries. The core logic in `scripts/render.py` uses the Pillow library to render text from a validated JSON input onto a templated PNG background, with no evidence of network exfiltration, unauthorized file access, or malicious command execution. The instructions in `SKILL.md` and the manual are consistent with the tool's stated purpose and follow standard OpenClaw skill patterns.
Capability Assessment
Purpose & Capability
Name/description (generate a 5-item AI news poster) aligns with the provided renderer script that reads JSON and writes a PNG. However the SKILL.md visual/typography spec (colors, exact title text) and some behavioral expectations (automatic filtering when >5 items, rewriting summaries) are not fully reflected in scripts/render.py. The renderer uses hardcoded top titles ('科创中心' / 'AI热点速报') instead of data.title and uses different color/gradient constants than the hex values in SKILL.md.
Instruction Scope
SKILL.md instructs the agent to 'rewrite each summary' and to 'keep the most important 5 and explain filtering' when >5 are provided. The included Python renderer enforces exactly 5 items (raises an error otherwise) and simply draws the provided headlines/summaries — it does not perform summarization, sanitization, or selection/filtering. The SKILL.md and actual runtime behavior therefore disagree about preprocessing and automatic content changes. Otherwise, runtime instructions only reference local files and a local Pillow install; there are no network calls or exfiltration instructions.
Install Mechanism
No install spec; this is instruction + local script only. The only external dependency is Pillow (pip install), which is declared in SKILL.md. No downloads from arbitrary URLs, no package installs beyond pip for a well-known library.
Credentials
The skill requests no environment variables, no credentials, and no config paths. The renderer reads only the provided input JSON and writes a local PNG; there is no access to unrelated secrets or system configuration.
Persistence & Privilege
always is false and the skill does not request permanent presence or modify other skills or global agent configuration. It only writes its output file and creates output directories as expected for a renderer.
How to Use
  1. Make sure OpenClaw is installed (local or Docker)
  2. Run the install command in chat: /install ai-news-poster
  3. After installation, invoke the skill by name or use /ai-news-poster
  4. Provide required inputs per the skill's parameter spec and get structured output
Version History
v1.0.0
Initial release of ai-news-poster skill. - Generate daily AI news posters from exactly 5 news items using a fixed Chinese/English template. - Strict poster style: layout, typography, and content contract provided. - Validates input: always normalizes news to 5 items, rewrites summaries, ensures factuality. - Poster output: 1080x1350 PNG image, ready for social sharing; outputs normalized JSON if needed. - Includes sample prompts, rendering script usage, and manual fallback instructions.
Metadata
Slug ai-news-poster
Version 1.0.0
License
All-time Installs 0
Active Installs 0
Total Versions 1
Frequently Asked Questions

What is Ai News Poster?

Generate fixed-template daily AI news posters from five news items. Use when the user asks to create a poster, social card, or image summary for "today's AI... It is an AI Agent Skill for Claude Code / OpenClaw, with 372 downloads so far.

How do I install Ai News Poster?

Run "/install ai-news-poster" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.

Is Ai News Poster free?

Yes, Ai News Poster is completely free (open-source). You can download, install and use it at no cost.

Which platforms does Ai News Poster support?

Ai News Poster is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).

Who created Ai News Poster?

It is built and maintained by 小曹学AI (@caoyacheng); the current version is v1.0.0.

💬 Comments