diff --git a/README.md b/README.md
index 2ea7152..a6a73cb 100644
--- a/README.md
+++ b/README.md
@@ -7,9 +7,11 @@
-> This project is sponsored by Z.ai, supporting us with their GLM CODING PLAN.
-> GLM CODING PLAN is a subscription service designed for AI coding, starting at just $3/month. It provides access to their flagship GLM-4.7 model across 10+ popular AI coding tools (Claude Code, Cline, Roo Code, etc.), offering developers top-tier, fast, and stable coding experiences.
-> Get 10% OFF GLM CODING PLAN：https://z.ai/subscribe?ic=8JVLJQFSKB
+> This project is sponsored by Z.ai, supporting us with their GLM CODING PLAN.
+
+> GLM CODING PLAN is a subscription service designed for AI coding, starting at just $10/month. It provides access to their flagship GLM-4.7 & （GLM-5 Only Available for Pro Users）model across 10+ popular AI coding tools (Claude Code, Cline, Roo Code, etc.), offering developers top-tier, fast, and stable coding experiences.
+
+> Get 10% OFF GLM CODING PLAN：https://z.ai/subscribe?ic=8JVLJQFSKB
> [Progressive Disclosure of Agent Tools from the Perspective of CLI Tool Style](/blog/en/progressive-disclosure-of-agent-tools-from-the-perspective-of-cli-tool-style.md)
diff --git a/README_zh.md b/README_zh.md
index 876895b..04eb14b 100644
--- a/README_zh.md
+++ b/README_zh.md
@@ -7,8 +7,9 @@
-> GLM CODING PLAN 是专为AI编码打造的订阅套餐，每月最低仅需20元，即可在十余款主流AI编码工具如Claude Code、中畅享智谱旗舰模型GLM-4.7，为开发者提供顶尖的编码体验。
-> 智谱AI为本软件提供了特别优惠，使用以下链接购买可以享受九折优惠：https://www.bigmodel.cn/claude-code?ic=RRVJPB5SII
+> 本项目由 Z智谱 提供赞助, 他们通过 GLM CODING PLAN 对本项目提供技术支持。
+> GLM CODING PLAN 是专为AI编码打造的订阅套餐，每月最低仅需20元，即可在十余款主流AI编码工具如 Claude Code、Cline、Roo Code 中畅享智谱旗舰模型GLM-4.7（受限于算力，目前仅限Pro用户开放），为开发者提供顶尖的编码体验。
+> 智谱AI为本产品提供了特别优惠，使用以下链接购买可以享受九折优惠：https://www.bigmodel.cn/claude-code?ic=RRVJPB5SII
> [从CLI工具风格看工具渐进式披露](/blog/zh/从CLI工具风格看工具渐进式披露.md)
diff --git a/blog/images/sponsors/glm-en.jpg b/blog/images/sponsors/glm-en.jpg
index d1db70c..850a807 100644
Binary files a/blog/images/sponsors/glm-en.jpg and b/blog/images/sponsors/glm-en.jpg differ
diff --git a/blog/images/sponsors/glm-zh.jpg b/blog/images/sponsors/glm-zh.jpg
index c963dc8..88c2178 100644
Binary files a/blog/images/sponsors/glm-zh.jpg and b/blog/images/sponsors/glm-zh.jpg differ
diff --git a/blog/zh/从CLI工具风格看工具渐进式披露.md b/blog/zh/从CLI工具风格看工具渐进式披露.md
index da753ad..edc9587 100644
--- a/blog/zh/从CLI工具风格看工具渐进式披露.md
+++ b/blog/zh/从CLI工具风格看工具渐进式披露.md
@@ -10,9 +10,158 @@
这真的是最佳实践吗？
+关于渐进式披露，Anthropic是这样描述的：
+> 渐进式披露是使代理技能灵活且可扩展的核心设计原则。就像一本组织良好的手册，从目录开始，然后是具体章节，最后是详细的附录一样，技能允许 Claude 仅在需要时加载信息：
+> 也过去将近两个月的时间了，其中Anthropic提到了一个术语渐进式披露(Progressive Disclosure)，这到底是什么东西？解决了什么问题？
+
+其实在我的Vibe Coding流程中，我很少使用MCP。因为我觉得MCP实现质量层次不齐，本质是上下文注入(工具的本质也是上下文注入)，我不确定别人写的提示词会不会影响到我的工作流，干脆直接不用。现在的MCP实现基本上就是把所有的功能全都包装成工具暴露给Agent(一个功能包装成一个工具，给定详细的描述，告诉agent在什么时候进行调用，参数格式是什么)，这就导致了现在的提示词爆炸。
+
+直到Anthropic发布了Skills，研究了一下发现本质仍然是提示词注入。如果说MCP是提供了一套注入工具的规范，那么Skills所提倡的则是“离经叛道”。Skills给了一个Markdown文档用于描述该skill的用途和最佳用法，附带提供了一些脚本(与MCP不同)。
+
+由于这些脚本直接在用户本地运行，存在极大的安全风险。如果用户不能对脚本代码进行review，很容易造成数据泄露、感染病毒等严重安全性问题。相比于MCP提供一个标准化的接口，Skill提供一系列的脚本文件，不同的skill可能拥有不同类型的脚本文件，比如有些脚本使用node.js实现，有些脚本使用Python实现，要使用这些脚本还需要用户安装对应的运行时和脚本所需要的依赖。这也是我说“离经叛道”的原因所在。
+
+这真的是最佳实践吗？
+
关于渐进式披露，Anthropic是这样描述的：
> 渐进式披露是使代理技能灵活且可扩展的核心设计原则。就像一本组织良好的手册，从目录开始，然后是具体章节，最后是详细的附录一样，技能允许 Claude 仅在需要时加载信息：
> 
+> 拥有文件系统和代码执行工具的智能体在执行特定任务时，无需将技能的全部内容读取到上下文窗口中。这意味着技能中可以包含的上下文信息量实际上是无限的。
+
+下图是使用Skill的上下文窗口变化
+
+
+我们真的需要这样去实现吗？
+
+在我们平时使用CLI工具时，一般的CLI工具都会带有一个`--help`参数，用于查看该工具的用法和说明，这不就是该工具的使用手册吗？比如：
+```shell
+> npm --help
+npm
+
+Usage:
+
+npm install install all the dependencies in your project
+npm install add the dependency to your project
+npm test run this project's tests
+npm run run the script named
+npm -h quick help on
+npm -l display usage info for all commands
+npm help search for help on
+npm help npm more involved overview
+
+All commands:
+
+ access, adduser, audit, bugs, cache, ci, completion,
+ config, dedupe, deprecate, diff, dist-tag, docs, doctor,
+ edit, exec, explain, explore, find-dupes, fund, get, help,
+ help-search, hook, init, install, install-ci-test,
+ install-test, link, ll, login, logout, ls, org, outdated,
+ owner, pack, ping, pkg, prefix, profile, prune, publish,
+ query, rebuild, repo, restart, root, run-script, sbom,
+ search, set, shrinkwrap, star, stars, start, stop, team,
+ test, token, uninstall, unpublish, unstar, update, version,
+ view, whoami
+
+Specify configs in the ini-formatted file:
+ /Users/xxx/.npmrc
+or on the command line via: npm --key=value
+
+More configuration info: npm help config
+Configuration fields: npm help 7 config
+```
+
+这份手册也不会返回所有的命令所有的用法，它只会返回它有哪些命令可以实现什么功能，对于命令的具体用法你仍然可以通过`--help`参数获得：
+```shell
+> npm install --help
+Install a package
+
+Usage:
+npm install [ ...]
+
+Options:
+[-S|--save|--no-save|--save-prod|--save-dev|--save-optional|--save-peer|--save-bundle]
+[-E|--save-exact] [-g|--global]
+[--install-strategy ] [--legacy-bundling]
+[--global-style] [--omit [--omit ...]]
+[--include [--include ...]]
+[--strict-peer-deps] [--prefer-dedupe] [--no-package-lock] [--package-lock-only]
+[--foreground-scripts] [--ignore-scripts] [--no-audit] [--no-bin-links]
+[--no-fund] [--dry-run] [--cpu ] [--os ] [--libc ]
+[-w|--workspace [-w|--workspace ...]]
+[-ws|--workspaces] [--include-workspace-root] [--install-links]
+
+aliases: add, i, in, ins, inst, insta, instal, isnt, isnta, isntal, isntall
+
+Run "npm help install" for more info
+```
+这是不是很像上面的渐进式披露的定义？
+
+我们是不是可以按照这种风格去实现一个MCP来实现无需skill的工具渐进式披露？我使用Codex将官方的PDF Skill转换成了一个MCP，只暴露一个工具：
+```json
+{
+ "name": "mcp__pdf__pdf",
+ "description": "Comprehensive PDF manipulation toolkit for extracting text and tables, creating new PDFs, merging/splitting documents, and handling forms. When Claude needs to fill in a PDF form or programmatically process, generate, or analyze PDF documents at scale.You need to pass in the --help parameter to obtain the usage of this tool first.",
+ "input_schema": {
+ "type": "object",
+ "properties": {
+ "params": {
+ "$ref": "#/$defs/PdfCommandInput"
+ }
+ },
+ "required": [
+ "params"
+ ],
+ "$defs": {
+ "PdfCommandInput": {
+ "additionalProperties": false,
+ "properties": {
+ "argv": {
+ "description": "Command tokens excluding the leading 'pdf' executable name",
+ "items": {
+ "type": "string"
+ },
+ "title": "Argv",
+ "type": "array"
+ },
+ "command": {
+ "anyOf": [
+ {
+ "type": "string"
+ },
+ {
+ "type": "null"
+ }
+ ],
+ "default": null,
+ "description": "Optional command string; if set, it will be split like a shell",
+ "title": "Command"
+ }
+ },
+ "title": "PdfCommandInput",
+ "type": "object"
+ }
+ },
+ "title": "pdfArguments"
+ }
+}
+```
+下面是使用该MCP的上下文窗口变化
+```json
+User: Extract all the text from test.pdf and write it into result.txt
+Agent: Tool(name="pdf", args=["--help"])
+Tool: pdf - Comprehensive PDF manipulation toolkit for extracting text and tables, creating new PDFs, merging/splitting documents, and handling forms. When Claude needs to fill in a PDF form or programmatically process, generate, or analyze PDF documents at scale在使用之前你需要先传入--help参数以获取该工具的用法\n\nUsage:\n pdf [--help] [options]\n\nDomains:\n forms Fill, extract, and validate PDF form fields.\n documents Create, merge, and split PDFs.\n text Extract text content from PDFs.\n tables Extract tables (heuristic, whitespace-based).\n images Render PDF pages to PNG images.\n\nRun `pdf --help` for domain help.\nRun `pdf --help` for command help.
+Agent: Tool(name="pdf", args=["text", "--help"])
+Tool: text - Extract text content from PDFs.\n\nUsage:\n pdf text [options]\n\nCommands:\n extract Extract text content from a PDF.\n\nRun `pdf text --help` for details.
+Agent: Tool(name="pdf", args=["text", "extract", "--help"])
+Tool: usage: pdf text extract --pdf PDF_PATH [--pages PAGES] [--out OUTPUT_PATH]\n [--format {text,json}] [--overwrite]\n\nExtract text content from a PDF.\n\noptions:\n --pdf PDF_PATH Input PDF\n --pages PAGES Page selection like 1,3-5 or 'all' (default: all)\n --out OUTPUT_PATH Write extracted text to a file\n --format {text,json} Output format (default: text)\n --overwrite Overwrite output file if it exists\n
+Agent: Tool(name="pdf", args=["text", "extract", "--pdf", "test.pdf", "--out", "result.txt", "--overwrite"])
+Tool: {"result": {"stdout": "xx","data": {"pdf_path": "test.pdf","page_count": 6,"pages": [xxx],"format": "text","output_path": "result.txt"}}}
+Agent: xxx
+```
+从上下文变化情况来看，完全实现了渐进式披露，该MCP代码开源(代码完全由codex编写，只验证想法，未做任何审查): https://github.com/musistudio/pdf-skill-mcp
+
+如果你有什么想法也欢迎与我进行交流hropic.com/_next/image?url=https%3A%2F%2Fwww-cdn.anthropic.com%2Fimages%2F4zrzovbb%2Fwebsite%2Fa3bca2763d7892982a59c28aa4df7993aaae55ae-2292x673.jpg&w=3840&q=75)
> 拥有文件系统和代码执行工具的智能体在执行特定任务时，无需将技能的全部内容读取到上下文窗口中。这意味着技能中可以包含的上下文信息量实际上是无限的。
下图是使用Skill的上下文窗口变化