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.
npx skills add Morningstar202604/awesome-skillkit --skill zhihu-content-managergit clone --depth 1 https://github.com/Morningstar202604/awesome-skillkitWrote 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.
[](https://agentmods.dev/skills/morningstar202604/awesome-skillkit/zhihu-content-manager)<a href="https://agentmods.dev/skills/morningstar202604/awesome-skillkit/zhihu-content-manager"><img src="https://agentmods.dev/badge/skills/morningstar202604/awesome-skillkit/zhihu-content-manager/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.
<a href="https://agentmods.dev/skills/morningstar202604/awesome-skillkit/zhihu-content-manager"><img src="https://agentmods.dev/badge/skills/morningstar202604/awesome-skillkit/zhihu-content-manager.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00086 | $0.03989 |
| Opus 5 | $0.00043 | $0.01995 |
| Sonnet 5 | $0.00017 | $0.00798 |
| Haiku 4.5 | $0.00009 | $0.00399 |
Grade A, and why
zhihu-content-manager 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 8d ago.
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.
How it starts
The opening of the file, as written. The whole thing — 365 lines — stays where its author put it; the contents beside it link to each section on GitHub.
知乎发文管理 Skill
compatibility
- Python 3.8+ 与 Playwright(
pip install playwright && playwright install chromium) - Chromium 浏览器(默认用 Playwright 自带的;如需指定路径见下文)
zhihu_state.json:知乎登录态 cookies 文件(由用户本地浏览器登录后导出,不入库)
核心工作流
1. 环境准备
import sys
from pathlib import Path
from playwright.sync_api import sync_playwright
# Chromium 路径按优先级解析:
# 1) 环境变量 ZHIHU_CHROME_PATH
# 2) Playwright 自带浏览器(不传 executable_path 即可)
CHROME_PATH = os.environ.get("ZHIHU_CHROME_PATH") or None
STATE_FILE = os.environ.get("ZHIHU_STATE_FILE", "zhihu_state.json")
启动浏览器配置:
browser = p.chromium.launch(
executable_path=CHROME_PATH, # None 时使用 Playwright 自带 Chromium
headless=True,
args=[
'--no-sandbox', '--disable-gpu', '--disable-dev-shm-usage',
'--disable-blink-features=AutomationControlled'
]
)
context = browser.new_context(
storage_state=STATE_FILE,
user_agent='Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/120.0.0.0 Safari/537.36',
viewport={'width': 1920, 'height': 1080},
locale='zh-CN'
)
context.add_init_script("Object.defineProperty(navigator, 'webdriver', {get: () => undefined});")
page = context.new_page()
2. HTML内容规范
发布到知乎的HTML必须遵循以下格式:
段落:<p data-pid="X">内容</p>
标题:<h2> / <h3>(中文编号如"一、""1.1")
引用:<blockquote data-pid="X">内容</blockquote>
代码块:<code> 标签内所有 < > 必须转义为 < >
图片:必须用 <figure data-size="normal"><img src="URL"/></figure> 包裹
粗体:<b>,不要用 <strong>
列表:<ul><li> 用于结构化知识
公式:行内 <span class="FormulaCSR" data-tex="LaTeX" data-eeimg="1">$LaTeX$</span>,块级 <p data-pid="X"><span class="FormulaCSR" data-tex="LaTeX" data-eeimg="2">$$LaTeX$$</span></p>
绝对禁止:裸 <img> 标签(会被过滤)、<table>(Draft.js无法清除)、未转义的尖括号
3. 发布新文章
导航: https://zhuanlan.zhihu.com/write
↓
设置标题(React兼容方式):
Object.getOwnPropertyDescriptor(window.HTMLTextAreaElement.prototype, 'value').set.call(textarea, "标题")
textarea.dispatchEvent(new Event('input', { bubbles: true }))
↓
上传封面:
找到 input[type="file"][accept*="image"] (通常是第1个或第2个)
file_input.set_input_files("/path/to/cover.jpg")
等待3秒
清除弹窗: document.querySelectorAll('.Modal-backdrop, .Modal').forEach(el => el.remove())
↓
注入HTML内容(分块paste):
chunk_size = 15000
for chunk in [html[i:i+chunk_size] for i in range(0, len(html), chunk_size)]:
if not first:
定位到编辑器末尾: focus() + selectAllChildren() + collapseToEnd()
ClipboardEvent paste注入:
dt = new DataTransfer()
dt.setData('text/html', chunk)
dt.setData('text/plain', chunk)
editor.dispatchEvent(new ClipboardEvent('paste', { clipboardData: dt, bubbles: true, cancelable: true }))
等待2秒
↓
验证预览包含中文字符
↓
点击"发布"按钮(绕过Modal):
document.querySelectorAll('.Modal-backdrop, .Modal').forEach(el => el.remove())
遍历所有button找到textContent.trim() === '发布' 的并click()
↓
添加话题标签(编辑页底部):
找到placeholder包含"话题"的input
设置value为"编程"或相关话题
从Popover建议列表精确匹配点击第一个
↓
确认发布: 点击"确认发布"或"确认"按钮
What ships with it
4 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.
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.
- 8d ago First seen · 365 lines · 86 tokens per session scan A ddba602bde8f
zhihu-content-manager is a skill published in the GitHub repository Morningstar202604/awesome-skillkit (1 stars, last pushed yesterday), licensed Apache-2.0. It adds 86 tokens to every session and 3,989 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 2026-09-03.
Other skills, from other repositories
dingtalk_channel_connect
Use a headed browser to automatically complete DingTalk channel integration for QwenPaw. Applicable when the user mentions DingTalk, developer console, Client ID, Client Secret, bot, Stream mode, binding or configuring a channel. Supports pausing when a login page is detected and resuming after the user logs in.
browser_cdp
Use this skill when the user explicitly wants to connect to a running Chrome browser, scan local CDP ports, specify a cdpport, or share a single browser across multiple agents/tools. By default browser opens no debugging port; pass an explicit cdpport only when the user wants another local tool to attach.
browser_cdp
Browser connection controls for finding local debugging ports, attaching to an already running Chrome browser, or sharing one browser between tools.
browser_visible
Browser launch controls for choosing whether a Chromium-based browser window is visible, which browser program to run, and which startup options to pass.
browser_visible
Use this skill when the user needs to control the browser launch mode for browser. By default browser is managed by Playwright and opens no debugging port (pass an explicit cdpport to let another local tool attach); headed controls whether the window is visible, and privatemode is kept for backward compatibility and…
ego-browser
When you need a browser, read this Skill by default. Use it to open and operate websites, fill forms, click buttons, take screenshots, extract page data, sign in, and perform other browser automation tasks, as well as web app testing, dogfooding, QA, bug investigation, and app-quality review. ego-browser (ego-lite) is…