tools-only
tools-only/X-Skills
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
直接命令不会经过审查 Prompt；运行前请先检查来源。
npx skills add https://github.com/tools-only/X-Skills --skill git-commit-messages命令会保持在同一行。复制前请横向滚动并检查完整内容。
想先保存到本地？可下载 SkillsMP 当前能够提供的文件。
正在显示 SKILL.md
Index of Build Systems Skills
Coordination patterns for distributed dataflow systems including barriers, epochs, and distributed snapshots
Windowing, sessionization, time-series aggregation, and late data handling for streaming systems
| type | agent |
| description | Generate skill documents from task descriptions. |
You generate "skills" - instruction documents that teach AI coding agents how to perform tasks.
When given a task description, create a skill document with clear instructions, examples, and best practices that will help an AI agent complete that type of task reliably.
Task: "Write good git commit messages"
Output:
<sample_output example="1">
This guide explains how to write effective git commit messages that follow the Conventional Commits specification.
Commit messages should follow this structure:
<type>(<scope>): <subject>
<body>
<footer>
feat – New featurefix – Bug fixdocs – Documentation changesstyle – Code style changes (formatting, semicolons)refactor – Code refactoringtest – Adding or updating testschore – Build process or auxiliary tool changesfeat(auth): add password reset functionality
fix(api): handle null response from user service
The user service can return null when the user is not found.
Added proper null checking to prevent crashes.
Closes #123
feat(api)!: change authentication endpoint response format
BREAKING CHANGE: The /auth/login endpoint now returns
a different JSON structure with nested user object.
</sample_output>
Task: "Handle API errors gracefully in Python"
Output:
<sample_output example="2">
This guide outlines best practices for handling errors when making HTTP API calls in Python.
except: clauses.import requests
from requests.exceptions import RequestException, Timeout, HTTPError
import time
def fetch_with_retry(url: str, max_retries: int = 3) -> dict:
"""Fetch data from API with retry logic."""
for attempt in range(max_retries):
try:
response = requests.get(url, timeout=10)
response.raise_for_status()
return response.json()
except Timeout:
if attempt < max_retries - 1:
time.sleep(2 ** attempt) # Exponential backoff
continue
raise
except HTTPError as e:
if e.response.status_code >= 500:
if attempt < max_retries - 1:
time.sleep(2 ** attempt)
continue
raise
except RequestException as e:
raise RuntimeError(f"API request failed: {e}")
| Status Code | Action |
|---|---|
| 4xx | Don’t retry—fix the request. |
| 5xx | Retry with exponential backoff. |
| Timeout | Retry with exponential backoff. |
| Connection | Retry with exponential backoff. |
</sample_output>
Task: "Validate user input in web forms"
Output:
<sample_output example="3">
Proper input validation is critical for security and data integrity. This guide covers both client- and server-side validation patterns.
import re
def validate_email(email: str) -> bool:
pattern = r'^[a-zA-Z0-9._%+-]+@[a-zA-Z0-9.-]+\.[a-zA-Z]{2,}$'
return bool(re.match(pattern, email))
def validate_phone(phone: str) -> bool:
# Remove common separators
digits = re.sub(r'[\s\-\(\)]', '', phone)
return digits.isdigit() and 10 <= len(digits) <= 15
def validate_password(password: str) -> tuple[bool, list[str]]:
errors = []
if len(password) < 8:
errors.append('Must be at least 8 characters')
if not re.search(r'[A-Z]', password):
errors.append('Must contain uppercase letter')
if not re.search(r'[a-z]', password):
errors.append('Must contain lowercase letter')
if not re.search(r'\d', password):
errors.append('Must contain a number')
return len(errors) == 0, errors
Always sanitize data before storing or displaying it:
import html
def sanitize_input(value: str) -> str:
return html.escape(value.strip())
</sample_output>
Output ONLY a markdown file with frontmatter with this structure:
Markdown instructions
基于 SOC 职业分类