Spec Driven Development
MCP Server that facilitates spec-driven development workflows, not just Vibe Coding.
作者提供的说明(英文原文)
Offline docs-as-code for any backend and frontend: a MkDocs site in your repo, by your AI agent.
这三项永远不会合并成一个分数:意见、测量和人气是不同的东西。
我们还没有为它写通俗的介绍。下面是我们从注册中心读取到的事实。
选择你使用的 AI 应用,然后复制设置。
你需要
你用的是哪个应用?
在上方选择你的应用。我们会记住它,下次按钮会显示“安装到 …”。
打开 Claude Desktop → Settings → Developer → Edit Config,把下面的内容粘贴到 claude_desktop_config.json
{
"mcpServers": {
"snapdoczilla": {
"command": "uvx",
"args": [
"snapdoczilla-mcp"
]
}
}
}在终端中运行这条命令
claude mcp add snapdoczilla -- uvx snapdoczilla-mcp粘贴到项目中的 .cursor/mcp.json,或 ~/.cursor/mcp.json
{
"mcpServers": {
"snapdoczilla": {
"command": "uvx",
"args": [
"snapdoczilla-mcp"
]
}
}
}浏览器会先询问是否打开应用,然后应用会显示设置并请你确认。密钥的值会留空,由你自己填写。
粘贴到项目中的 .vscode/mcp.json
{
"servers": {
"snapdoczilla": {
"type": "stdio",
"command": "uvx",
"args": [
"snapdoczilla-mcp"
]
}
}
}浏览器会先询问是否打开应用,然后应用会显示设置并请你确认。密钥的值会留空,由你自己填写。
这个服务器在你的电脑上运行,而 ChatGPT 只能连接互联网上的服务器。请选择其他应用。
你的选择通过 Cookie 保存在这台设备上,无需账户。
这些设置是根据作者在注册中心的条目生成的。如果 README 的写法不同,请以 README 为准。
它在你的电脑上运行;安装后,工具列表会显示在你的 AI 应用中。
我们检查的是任何人都能看到的信息;我们没有阅读代码。不适用的检查项不计入总数。 · 检查于 2026年11月6日
注册名称已通过 GitHub 账户 julvc 验证,该账户拥有此仓库
我们还没有从 GitHub 读取这个仓库
我们还没有从 GitHub 读取这个仓库
它在你的电脑上运行,没有互联网端点
在你的电脑上运行,改用本地设置
它在你的电脑上运行;我们只能读取互联网端点的工具列表
与注册中心里这个分类中所有活跃的服务器比较。只有当发布者拥有该仓库时,星标数才计入。
它在 1 项适用的基础检查中通过了 1 项。我们没有阅读代码。在添加密钥或令牌之前,请先看看这个服务器要求哪些权限,并使用只具备所需权限的密钥。
注册中心没有列出必需的密钥,不过有些服务器会在首次使用时要求你登录。
它在你的电脑上运行。你的 AI 应用会在需要时启动它,数据不会经过作者的服务器(除非它自己调用在线服务)。
GitHub 仓库最后更新于–,最新版本(1.2.0)于16天前进入注册中心。
支持 MCP 的应用,例如 Claude Desktop、Claude Code、Cursor 和 VS Code。你的电脑上还需要有 Python (uv)。
同一分类中有:Spec Driven Development, Remote Desktop Commander, Symantec Cloud DLP AIops
同一分类中其他作者的服务器,按星标数排序。
如何看卡片:★ GitHub 星标i三大支柱:评价 · 检查 · 使用情况i更新 = 最新版本发布到注册中心的时间i
MCP Server that facilitates spec-driven development workflows, not just Vibe Coding.
Remote Desktop Commander: use files, terminal and processes on your own computers from any AI app.
Governed Symantec Cloud DLP — 14 MCP tools, read-only with audit.
按原文从作者的仓库复制。PopNx MCP 没有审查或背书其内容。HTML、图片和脚本已被移除。链接会离开本站。
English · Español
Agent skills I use on real projects. Small, readable, easy to adapt. They follow the open Agent Skills format (SKILL.md), so they work in Claude Code first and also in Codex, OpenCode, Antigravity, Gemini CLI and other agents.
| Skill | What it does |
|---|---|
| SnapDoczilla | Documentation for any backend and any frontend as an offline HTML site inside your repo. Anyone reads it with a double click; any dev updates it with one command. Mermaid diagrams, API map, ADRs and react.dev-style component pages with real code and real usage. |
A component page generated by SnapDoczilla: real usage and real source, pulled from the repo on every build.
Two options. The Claude Code plugin is a managed bundle that updates when I ship. skills.sh copies editable files into your project, for any agent. Pick one: installing both gives you every skill twice.
Claude Code (plugin)
claude plugin marketplace add julvc/skills
claude plugin install snapdoczilla@juliovc
Or from inside a session:
/plugin marketplace add julvc/skills
/plugin install snapdoczilla@juliovc
Invoke it with /snapdoczilla:snapdoczilla, or just ask *"document this project"*: Claude picks it up on its own.
Codex, OpenCode, Antigravity, Gemini CLI and other agents
npx skills@latest add julvc/skills
Pick the skills and the agents to install them on. Or install one skill on one agent with no prompts:
npx skills@latest add julvc/skills --skill snapdoczilla -a codex -y
Agent ids: claude-code, codex, opencode, antigravity, gemini-cli. Add -g to install globally instead of in the current project.
Manual (no tooling)
Copy skills/snapdoczilla/ into your agent's skills folder:
| Agent | Project | Global |
|---|---|---|
| Claude Code | .claude/skills/ | ~/.claude/skills/ |
| Codex | .agents/skills/ | ~/.codex/skills/ |
| OpenCode | .agents/skills/ | ~/.config/opencode/skills/ |
| Antigravity | .agents/skills/ | ~/.gemini/antigravity/skills/ |
Prefer MCP over skills, or your client has no skills support? SnapDoczilla also ships as a local MCP server (stdio, Python). The agent still writes the docs from your code; the server does the deterministic parts: install, "what changed since the last documented commit", safe page writes and the strict build.
claude mcp add snapdoczilla -- uvx snapdoczilla-mcp
Claude Desktop, Cursor and other mcpServers clients:
{
"mcpServers": { "snapdoczilla": { "command": "uvx", "args": ["snapdoczilla-mcp"] } } }
Codex CLI (~/.codex/config.toml):
[mcp_servers.snapdoczilla]
command = "uvx" args = ["snapdoczilla-mcp"]
Needs uv, git and bash (on Windows: Git for Windows). The server does not read your code: your client does with its own file tools (in Claude Desktop, add a filesystem server). Use the MCP server or the skill in a given agent, not both.
| Tool | What it does |
|---|---|
snapdoczilla_status | Installed? Areas, commits not yet documented, pages, next ADR number, suggested next step |
snapdoczilla_install | Scaffolds documentation/, writes areas.conf, downloads Mermaid once |
snapdoczilla_get_rules | The rules the pages must follow (language, never invent, embed real code) |
snapdoczilla_changes_since_sync | Files and commits of an area since its last documented commit |
snapdoczilla_write_page | Writes one page, confined to documentation/source/, and adds it to nav |
snapdoczilla_build_html | Strict MkDocs build; a failed build keeps the previous site |
snapdoczilla_mark_synced | Records HEAD as the last documented commit of an area |
It also exposes the prompt document_project. Then just ask: *"Document this project"*.
What you get: a documentation/ folder in your repo. Anyone opens documentation/html/index.html with a double click: search and diagrams included, no install, no internet. Docs can't drift from code: pages embed the real source files on every build. See a full result in examples/shop (an Express API + React app; download the repo and open examples/shop/documentation/html/index.html).
Scope. It documents what lives in the repo, for any stack: Spring, Node (Express/Nest), Python (FastAPI/Django/Flask), .NET, Go, PHP, Ruby; Vue, React, Angular, Svelte.
| Backend | Frontend | Any project |
|---|---|---|
| Architecture with Mermaid flows, API map by resource, integrations, data model | Screens/routes, src/ structure, state, component pages (API + real usage + real code) | Overview, getting started, ADRs |
It does not take screenshots, run live demos, host anything or replace your OpenAPI/Swagger. Docs are written in the language you choose (English by default).
Requirements. To read: a browser. To generate/update: Git (with bash; on Windows, Git for Windows), Python 3 and an agent.
See Installation.
Document this project
The agent detects your areas (e.g. back=backend/, front=frontend/), installs the scaffolding, writes the first pages from your real code, builds the site and checks the diagrams. It never commits.
Open documentation/html/index.html.
Check git diff, fix anything flagged as *to be confirmed* and commit documentation/ (including html/, so readers need nothing installed).
./documentation/update.sh # all areas
./documentation/update.sh --front # one area ./documentation/update.sh --html-only # rebuild the HTML only, after editing .md by hand
On Windows, double-click documentation\update.cmd. Only what changed since the last sync goes to the agent. A pre-push hook reminds you (never blocks) when code changed without docs.
Claude Code is the default. Using another agent? Set DOCS_LLM:
| Agent | DOCS_LLM |
|---|---|
| Codex CLI | codex exec --full-auto |
| OpenCode | opencode run |
| Gemini CLI | gemini --yolo -p |
Or ask your agent *"update the docs"* inside a session. That works with every agent, Antigravity included.
Add a SnapDoczilla page for the Button component
You get what it is, how it works, props/events/slots, a real usage example from your app and the real source code.
cmmi profileDocument this project with SnapDoczilla using the CMMI profile
Same flows, plus a Process evidence page that maps CMMI practice areas (TS, DAR, PI, RDM, VV, PR, CM, PQA, OT, PAD) to the evidence in your repo, a *Requirement → Code → Tests → Page* traceability matrix and a baselines table per release tag. ADRs follow DAR (criteria + alternatives). Requirement IDs come only from real commits, branches or issues. The docs support an appraisal; they never claim compliance. Script: install.sh " " cmmi. MCP: snapdoczilla_install with profile: "cmmi".
Write the user manual for this app with SnapDoczilla
Adds a User manual section for the people who use the app: requirements, first steps, a screen map and one page per function with numbered steps, the exact button and field labels, the expected result and a *Message → Cause → What to do* table built from the real messages in the UI code. Screenshots are left as placeholders (img/ -NN.png) for a human to capture. With the cmmi profile the manual is also referenced as OT/VV evidence. Script: add-manual.sh . MCP: snapdoczilla_add_manual.
Architecture page, dark mode, diagram rendered offline.
They solve different problems. Docusaurus is an engine to build a site you write by hand. SnapDoczilla is a workflow: your agent writes the docs from the code and keeps them in sync.
| Docusaurus | SnapDoczilla | |
|---|---|---|
| Who writes | You | Your agent, from the real code |
| Staying current | Manual | Incremental, per git diff; code embedded from the real files |
| Read without a server | No | Yes, double-click |
| Stack | Node, React, MDX | Python only to build; nothing to read |
| Versions, multi-locale, blog, plugins | Yes | No |
Pick Docusaurus for a public product site with versions and many languages. Pick SnapDoczilla to make any codebase understandable to your team, today, and keep it that way.
documentation/html/ is a static site. To serve it with GitHub Pages, add .github/workflows/docs.yml to your repo and set *Settings → Pages → Source* to GitHub Actions:
name: docs
on: push: branches: [main] paths: [documentation/html/**] permissions: { contents: read, pages: write, id-token: write } jobs: deploy: runs-on: ubuntu-latest environment: github-pages steps:
documentation/
├── source/ # ed
只显示了开头部分;其余内容请在仓库中阅读