generate-word-clouds

generate-word-clouds is a skill for Codex from Lucas-Fong/html-report-stable-base. It costs 83 tokens per session (1,204 once invoked), scanned A, original, MIT.

A workflow for turning weighted keyword lists into compact PNG word-cloud images, where more important words appear larger.

In plain words
What is it for?
It is for creating one or several branded word clouds from Excel, CSV, JSON, tables, or pasted data, with options such as transparent backgrounds and horizontal text.
Why use it?
It removes the need to arrange the words by hand and checks that the generated images follow the selected colors, shape, background, spacing, and word count.

Skill for Codex

Written for Codex: agents/openai.yaml present.

Good fit It is for creating one or several branded word clouds from Excel, CSV, JSON, tables, or pasted data, with options such as transparent backgrounds and horizontal text.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/lucas-fong/html-report-stable-base/generate-word-clouds
Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Any agent
npx skills add Lucas-Fong/html-report-stable-base --skill generate-word-clouds
Clone the repo
git clone --depth 1 https://github.com/Lucas-Fong/html-report-stable-base

Made for: Codex.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for generate-word-clouds

README.md
[![agentmods](https://agentmods.dev/badge/skills/lucas-fong/html-report-stable-base/generate-word-clouds/github.svg)](https://agentmods.dev/skills/lucas-fong/html-report-stable-base/generate-word-clouds)
Your own site
<a href="https://agentmods.dev/skills/lucas-fong/html-report-stable-base/generate-word-clouds"><img src="https://agentmods.dev/badge/skills/lucas-fong/html-report-stable-base/generate-word-clouds/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for generate-word-clouds

Your own site · 80×15
<a href="https://agentmods.dev/skills/lucas-fong/html-report-stable-base/generate-word-clouds"><img src="https://agentmods.dev/badge/skills/lucas-fong/html-report-stable-base/generate-word-clouds.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 83 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,204 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00083 $0.01204
Opus 5 $0.00042 $0.00602
Sonnet 5 $0.00017 $0.00241
Haiku 4.5 $0.00008 $0.00120

Measured 12d ago against content hash 1b0ea8b8c142, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

generate-word-clouds scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 12d ago.

The scan reads SKILL.md. This mod also ships 2 executable files (scripts/extract_xlsx.py, scripts/generate_word_clouds.mjs), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

skills/generate-word-clouds/SKILL.md · 91 lines

How it starts

The opening of the file, as written. The whole thing — 91 lines — stays where its author put it; the contents beside it link to each section on GitHub.

品牌词云生成

将关键词及权重生成紧凑、可复用的 PNG 词云。默认输出横排文字、透明背景、椭圆形和四周 20px 边距。

工作流

  1. 读取关键词数据并识别每个列表的名称、关键词列和权重列。Excel 优先运行 scripts/extract_xlsx.py,不要临时编写转换脚本或用重量级工作簿渲染工具读取。
  2. 最多接受 10 个列表;超过时请用户拆分批次。
  3. 查询尚未缓存的品牌配色后,一次性确认最终配置:
请确认词云配置:
- 配色:品牌名、候选官方色值及来源 / 用户指定色值
- 关键词数量:Top 50
- 底色:透明
- 形状:椭圆
- 输出列表:列表名称(共 N 个)

若用户已明确其中部分配置,只确认尚未明确的项目并展示最终汇总。每个任务最多请求一次配置确认;用户明确说“按默认”“直接生成”或“无需确认”时可直接执行。

  1. 配色为品牌名时,先查 references/brand_palettes.json。存在已核验记录时直接复用并展示来源;没有记录时才联网查询品牌官网、官方品牌手册或官方媒体资料,只采用官方来源。将新结果写入缓存,记录来源、提取依据、日期和 3–6 个十六进制色值。若官方色值无法可靠取得,说明情况并请用户提供颜色;不得把第三方取色结果声称为官方配色。
  2. 按权重降序取 Top N。默认值:
    • Top N:50
    • 底色:透明
    • 形状:椭圆
    • 边距:20px
    • 文字方向:全部从左到右水平排列
  3. Excel 输入先运行快速提取器,再运行生成器:
python scripts/extract_xlsx.py input.xlsx config.json --top-n 50 \
  --palette-file references/brand_palettes.json
node scripts/generate_word_clouds.mjs config.json output-directory

提取器同时接受 {列表名: [色值...]} 映射或 brand_palettes.json 的缓存格式。作为 html-report 插件内置 skill 使用时,若依赖缺失,先在插件根目录运行 node scripts/bootstrap_html_report_deps.mjs,让 sharpopenpyxl 可用。CSV、JSON 或粘贴数据可直接整理成生成器配置。

  1. 用一个批次检查所有输出,不为每张图重复启动检查流程:
    • 文件为 PNG,透明底时必须含 Alpha 通道。
    • 所有词均为水平文字。
    • 实际内容与画布四边均为 20px;非透明底以背景画布边界为准。
    • 输出词数等于 min(Top N, 有效关键词数)
    • 中文无乱码、文字无重叠、主要关键词层级清楚。
  2. 向用户展示预览、下载链接、实际输出词数和品牌配色来源。

输入整理

脚本配置格式:

{
  "margin": 20,
  "lists": [
    {
      "name": "品牌A",
      "topN": 50,
      "background": "transparent",
      "shape": "ellipse",
      "palette": ["#7A1F2B", "#C68A1D", "#E1B84B"],
      "words": [
        {"text": "关键词", "weight": 100}
      ]
    }
  ]
}

支持的 shapeellipsecirclerectanglediamond。支持的 backgroundtransparent#RRGGBB。同一关键词重复出现时先合并权重;删除空关键词和非正数权重。

排版原则

  • 保持全部文字水平,不允许旋转。
  • 字号采用对数缩放,避免头部词过度挤压尾部词。
  • 优先保证 Top N 全部出现;必要时缩小整体字号后重排。
  • 颜色按调色板循环使用,同时避免最大关键词全部使用同一颜色。
  • 透明背景只包含词云,不添加标题、来源、边框或装饰。
  • 文件名使用安全化后的列表名称加 _TOP{N}_词云.png

资源

  • scripts/generate_word_clouds.mjs:确定性批量词云生成器。
  • scripts/extract_xlsx.py:快速识别 Excel 工作表、关键词列和权重列并生成配置。
  • references/confirmation.md:确认话术和品牌配色来源规则。
  • references/brand_palettes.json:已核验的官方素材配色缓存;命中时避免重复联网取色。

Read the full file on GitHub · 91 lines

Files

What ships with it

5 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 12d ago First seen · 91 lines · 83 tokens per session scan A 1b0ea8b8c142

Subscribe to this mod's changes

generate-word-clouds is a skill published in the GitHub repository Lucas-Fong/html-report-stable-base (2 stars, last pushed 16d ago), licensed MIT. It adds 83 tokens to every session and 1,204 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Related

Other skills, from other repositories

arkgum-research-to-page

Autonomously orchestrate a source-grounded topic-to-page workflow through Google NotebookLM: create or reuse a notebook, run Deep Research, import and verify sources, produce a cited research report, rank audience/content opportunities, create a page brief, and return a final prompt for Google AI Studio or another…

arkgum/arkgum-agent-skills · 139 tokens

prompt-to-loop-engineering

Use when a natural-language task must be converted into a role-neutral, statically validated one-shot plan, workflow, or agent-loop specification before any user-task execution begins.

Beichen-H/Loopower · 40 tokens

baoyu-youtube-transcript

A tool for downloading the written captions, subtitles, chapter information, speaker labels, and cover image from a YouTube video using its URL or ID.

JimLiu/baoyu-skills · 107 tokens

nature-statistics

Audit, revise, or draft manuscript statistical reporting for Nature / high-impact journal submissions. Use when the user asks to check statistical analysis sections, p values, confidence intervals, sample size, biological versus technical replicates, randomization, blinding, multiple-comparison correction, model…

Yuan1z0825/nature-skills · 139 tokens

warp-delegate

Delegate a coding task to the Warp Agent CLI (oz) as a background implementer, then review its diff and land it yourself. Use this whenever the user wants to hand implementation work to Warp - phrasings like "have Warp implement X", "delegate this to the Warp CLI", "run it through Warp", "use oz to…

amElnagdy/delegate-skills · 144 tokens

zcode-delegate

Delegate a coding task to the Z.AI ZCode CLI as a background implementer, then review its diff and land it yourself. Use this whenever the user wants to hand implementation work to ZCode — phrasings like "have ZCode do X", "delegate this to ZCode", "run it through ZCode", or "use ZCode to implement/fix/refactor" — or…

amElnagdy/delegate-skills · 124 tokens