Text Tools

Documents

text-tools

Text Tools is an Agent Skill for documents published in the fuyuxiang/echo-agent repository on GitHub: a SKILL.md instruction file an AI agent can load to do this task.

Text processing toolkit: translate, rewrite, regex, encoding/decoding, and formatting.

View on GitHub ↗

QUICK START

How to use this skill

Bring this guide into your coding agent with a prompt tailored to the tool you use.

Open your project in Codex.
Copy and paste the prompt below.
Review files and risks before approving any action.

Prompt to paste

Inspect the Agent Skill at https://github.com/fuyuxiang/echo-agent/blob/HEAD/skills/utility/text-tools/SKILL.md and all supporting files. Report provenance, permissions, scripts, dependencies, and security risks. Propose an exact installation into .agents/skills/text-tools, but wait for my approval before writing files or running scripts.

Copying this prompt does not install or run the skill. Review third-party files before use.

Text Tools

Text processing utilities powered by Python stdlib.

Text Cleaning

import re
# Strip HTML
clean = re.sub(r'<[^>]+>', '', html_text)
# Normalize whitespace
clean = ' '.join(text.split())
# Fix common encoding issues
text.encode('utf-8').decode('utf-8')

Regex Helpers

Pattern	Matches
`r'[\w.-]+@[\w.-]+'`	Email addresses
`r'https?://\S+'`	URLs
`r'1[3-9]\d{9}'`	Chinese phone numbers
`r'\d{1,3}\.\d{1,3}\.\d{1,3}\.\d{1,3}'`	IPv4
`r'\d{4}-\d{2}-\d{2}'`	Dates (YYYY-MM-DD)
`r'[一-鿿]+'`	Chinese characters

Encoding/Decoding

from urllib.parse import quote, unquote
import html, base64

# URL encode/decode
quote("你好世界")         # '%E4%BD%A0%E5%A5%BD%E4%B8%96%E7%95%8C'
unquote('%E4%BD%A0')     # '你'

# HTML entities
html.escape('<script>')  # '&lt;script&gt;'
html.unescape('&amp;')  # '&'

# Base64
base64.b64encode(b"hello").decode()  # 'aGVsbG8='
base64.b64decode("aGVsbG8=")         # b'hello'

Word/Character Count

text = "Hello 你好世界"
chars = len(text)           # 8
chars_no_space = len(text.replace(' ', ''))  # 7
words = len(text.split())  # 2
chinese = len(re.findall(r'[一-鿿]', text))  # 3

Text Diff

import difflib
diff = difflib.unified_diff(old.splitlines(), new.splitlines(), lineterm='')
print('\n'.join(diff))

Translation

For translation, use the agent's LLM capability directly — no external API needed. The agent can translate between any languages in-context.

Script

python3 scripts/text_process.py clean "  messy   text  "
python3 scripts/text_process.py count "your text here"
python3 scripts/text_process.py regex-extract "email" "Contact: [email protected]"
python3 scripts/text_process.py encode url "你好"
python3 scripts/text_process.py decode base64 "aGVsbG8="