wordcloud-skill

this skill is for generate a word cloud from text/file/directory and save it to a picture, you can use it visualize the text

Security Scan

The skill's code and instructions are consistent with its stated purpose (generating word clouds from provided text/files) and request no credentials or unusual system access.

Purpose & Capability

Name/description (word cloud generation) match the included script and SKILL.md. The script only needs standard text-processing libraries (jieba, numpy, wordcloud, PIL) and operates on user-provided text, files, or directories — all coherent with the stated purpose.

Instruction Scope

SKILL.md directs the agent to run the provided Python script and to supply target_text, target_file, or target_dir. The script will recursively read all .md files under a provided directory and read any specified files (and an optional stopwords file). This is within scope, but users should avoid pointing the skill at directories containing sensitive markdown files since the script will read any .md it finds.

Install Mechanism

No install spec (instruction-only) and the script runs with standard Python packages. SKILL.md lists required Python packages; installation is manual (pip) which is low-risk. No downloads from remote URLs or archive extraction occur.

Credentials

The skill requires no environment variables, credentials, or config paths. All file access is limited to paths explicitly supplied by the user via CLI arguments.

Persistence & Privilege

always is false and the skill does not request persistent presence or modify other skills or system-wide settings. It runs only when invoked and does not attempt autonomous elevation of privileges.

Assessment

This skill appears to do exactly what it says: generate a word cloud from text or markdown files. Before using it, (1) ensure you run it in an environment with the listed Python packages installed, (2) only point --target_file or --target_dir at files/directories you trust (it will read every .md under a target_dir), (3) provide a valid PNG mask and a known font path if needed, and (4) verify output_dir is where you want images written. No credentials or network calls are requested by the code. If you need higher assurance, review the script yourself or run it in an isolated environment.

Word Cloud

Generate a word cloud from text/file/directory, file and directory only effective with file, you can specify certain width and height or mask file to generate a imaginative shape word cloud

When to use

• user indicates to generate a word cloud
• user wants to visualize the text in a different way, you can suggest this skill

Requirements

Run on python3.x，and install the following packages if you find the package does not exist：

• os
• argparse
• jieba
• numpy
• datetime
• wordcloud
• PIL

Commands

# create a word cloud with certain width and height
python {baseDir}/scripts/generate_wordcloud.py --target_text "..." --width 500 --height 400 --max_words 30 --font_path "C:\Windows\Fonts\msyh.ttc" --output_dir "..."

# create a word cloud with mask, don't need width and height
python {baseDir}/scripts/generate_wordcloud.py --target_text "..." --mask "..." --font_path "C:\Windows\Fonts\msyh.ttc" --output_dir "..."

Paramters

name	description	type	example
target_text	text to generate word cloud	string	"你好，世界"
target_file	text in the file to generate word cloud	string	"D:\WorkSpace\pythonSpace\MEMORY.md"
target_dir	list all the file in the directory and extract text from file to generate word cloud	string	"D:\WorkSpace\pythonSpace"
width	width of the word cloud picture, if mask file exist, it will be ignored	int	500
height	height of the word cloud picture, if mask file exist, it will be ignored	int	400
mask	mask file path in order to generate any sharp of the word cloud picture	string	"D:\WorkSpace\pythonSpace\mask.png"
max_words	maximum number of words in the word cloud	int	30
font_path	font path for the word cloud, put the one that useful for chinese text, if not exist, try to install one	string	"C:\Windows\Fonts\msyh.ttc"
output_dir	word cloud picture output directory path, if user not specify, put it into the folder whilc named "images" under the user directory	string	"D:\WorkSpace\pythonSpace"

Note

• Parameter target_text, target_file, target_dir can be used at the same time, and make sure one of them is provided
• Parameter mask must be a png file, if user upload a png file and specify it as the parameter mask, you should mask sure the file path is correct
• if user specify exclude a word, append it to the stopwords.md，follow the format:

- hello
- world