原型 · 预览版:收录官方注册中心里的全部服务器,每 30 分钟同步一次。使用 Google 登录即可撰写评价。原型 · 每 30 分钟更新
PopNx MCP为使用 AI 的人准备的 MCP 服务器 · 用大白话讲清楚

ade-cli Skill

作者:landing-ai★ 2,4241 个 skill

安装

What it does

The official CLI for Agentic Document Extraction (ADE) by LandingAI — parse documents and extract schema-shaped data from your terminal

  • Connects Instruction files the AI reads; connects to nothing
  • Account or key No key needed
  • Category 文档与写作
给作者:在 README 中加徽章

如果你是作者,可把这段代码贴到 README。徽章会链接回本页。

[![Featured on PopNx MCP](https://mcp.popnx.com/badge/skill/landing-ai-ade-cli.svg)](https://mcp.popnx.com/en/skills/landing-ai-ade-cli)

可搭配使用

在同一工作中把 AI 连到服务的 MCP

XcodeBuildMCP

XcodeBuildMCP provides tools for Xcode project management, simulator management, and app utilities.

作者:getsentry广泛使用↓ 13万/周 共用包的下载量★ 65764个月前更新

MCP · 连接服务在你的电脑上运行✓ 服务方 · xcodebuildmcp.com

XcodeBuildMCP

XcodeBuildMCP provides tools for Xcode project management, simulator management, and app utilities.

作者:cameroncooke广泛使用↓ 13万/周 共用包的下载量★ 657614个月前更新

MCP · 连接服务在你的电脑上运行

Puter MCP

Puter MCP enables AI tools to interact with Puter: manage files, websites, workers, and more

作者:HeyPuter广泛使用★ 4.4万5个月前更新

MCP · 连接服务在云端运行✓ 服务方 · puter.com

相似的 Skill

同类工作,排序与 Skill 列表相同

与相似项目对比
本项
ade-cli
MinerUwatermarks-removerobsidian-skillsanysearch-skill
作者landing-aiopendatalabguillaumemeyerkepanoanysearch-ai
Skill 数11151
GitHub 星标2,42483,70127,49351,6296,896
最近代码更新2026年10月31日2026年11月13日2026年11月10日2026年9月15日2026年11月13日
许可证Apache-2.0–MITMITApache-2.0

landing-ai 提供的 1 个 Skill(指令集),AI 读取后照做 · 不是 MCP server

Skill 和 MCP 有什么不同

MCP = 手

把 AI 连到外部服务或数据,例如读取 Notion 或开发票。需要有程序或服务器在运行。

Skill = 手册

教 AI 怎么做某项工作的文本文件,不连接任何服务。

有些会重叠:少数 Skill 带有调用工具的脚本,少数 MCP 只提供知识。请从你想完成的工作出发。

适用的应用

Claude Code

依据开发者 README 和 repo 中的文件夹

安装

Is it safe?

  • Who made it

    GitHub account landing-ai (organization), 8 years old

  • Use and upkeep

    ★ 2,424 stars · code last changed 2026年10月31日

  • Any scripts?

    70 scripts that can run on a computer: scripts/install.sh, packaging/pyinstaller_entry.py, scripts/install.cmd, scripts/install.ps1 and 66 more

  • Uses the internet?

    Scripts that go online: scripts/install.cmd

  • Changes machine-wide settings?

    No hooks or writes to machine settings found

Checked automatically from the repo files at commit d1995ff (read only, nothing was run). Not a safety guarantee: read it and decide for yourself

第一步:你用哪个 AI?

选择你用的应用,本页只显示该应用的安装方法

Option 1Upload to claude.ai (web and app)

Uploading to claude.ai would fail: the description is over 200 characters (301). Use "Let the AI install it" instead

Option 1让 Claude Code 帮你安装

复制这句话,粘贴到 Claude Code 的对话中

Where to install

正在检查命令 · 通过后才会显示复制按钮

正在检查命令 · 通过后才会显示复制按钮

For one project, paste it into a chat that is open in that project’s folder · The AI always shows you the path before installing

The AI tells you what it will do first and asks your permission at every step

重新打开 Claude Code,输入 /ade-cli,或直接提出相关任务,Claude 会自动选用

Checked against official docs 2026年11月12日 · Source: code.claude.com

For Terminal users

Skill 是 AI 会照做的指令。安装前先阅读文件,只安装可信开发者的 Skill。

  1. 打开终端

    Mac:按 Command+空格输入 Terminal · Windows:下方命令在 PowerShell 中无法使用,请改用上方的“让 AI 帮你安装”

  2. 把 skill 文件夹复制到 ~/.claude/skills

    这条命令把 repo 下载到临时文件夹,只复制含 SKILL.md 的文件夹

    正在检查命令 · 通过后才会显示复制按钮

  3. 重新打开 Claude Code,输入 /ade-cli,或直接提出相关任务,Claude 会自动选用

自己安装的 Skill 可用于 ChatGPT 桌面应用、Codex CLI 和 IDE 中的 Codex 扩展 · 网页版和手机版 ChatGPT 不能使用自己安装的 Skill,只能使用目录中插件自带的 Skill

ChatGPT 桌面应用

ChatGPT 桌面应用内置 Codex,Codex 从 ~/.agents/skills 文件夹读取 Skill

Option 1让 ChatGPT 帮你安装

在 ChatGPT 桌面应用中打开 Codex,把这句话粘贴到对话中

Where to install

正在检查命令 · 通过后才会显示复制按钮

正在检查命令 · 通过后才会显示复制按钮

The AI always shows you the path before installing

The AI tells you what it will do first and asks your permission at every step

Option 2自己放入文件夹

把 ade 文件夹放到 ~/.agents/skills/ade

~ 是你的主文件夹($HOME)

For Terminal users

Skill 是 AI 会照做的指令。安装前先阅读文件,只安装可信开发者的 Skill。

  1. 打开终端

    Mac:按 Command+空格输入 Terminal · Windows:下方命令在 PowerShell 中无法使用,请改用上方的“让 AI 帮你安装”

  2. 把 skill 文件夹复制到 ~/.agents/skills

    这条命令把 repo 下载到临时文件夹,只复制含 SKILL.md 的文件夹

    正在检查命令 · 通过后才会显示复制按钮

安装之后

  • ChatGPT 桌面应用:打开侧边栏中的 Skills,确认 Skill 已出现
  • 使用方法:在 ChatGPT 中输入 @ 并选择 Skill · 在 Codex CLI 或 IDE 扩展中运行 /skills,或输入 $ 加 Skill 名称
  • Codex 会自动发现新安装的 Skill;如果没有出现,请重启 Codex

Checked against official docs 2026年11月15日 · Source: learn.chatgpt.com

网页版和手机版 ChatGPT

不能使用你自己安装的 Skill,只能使用目录中插件自带的 Skill

想在 ChatGPT 中使用这个 Skill,请按上面的方法使用 ChatGPT 桌面应用

Checked against official docs 2026年11月15日 · Source: learn.chatgpt.com

Option 1让 Codex 帮你安装

复制这句话,粘贴到 Codex 的对话中 · 适用于 ChatGPT 桌面应用中的 Codex、Codex CLI 和 IDE 扩展

Where to install

正在检查命令 · 通过后才会显示复制按钮

正在检查命令 · 通过后才会显示复制按钮

For one project, paste it into a chat that is open in that project’s folder · The AI always shows you the path before installing

The AI tells you what it will do first and asks your permission at every step

Codex 会自动发现新安装的 Skill;如果没有出现,请重启 Codex · 使用方法:在 ChatGPT 中输入 @ 并选择 Skill · 在 Codex CLI 或 IDE 扩展中运行 /skills,或输入 $ 加 Skill 名称

Checked against official docs 2026年11月15日 · Source: learn.chatgpt.com

For Terminal users

Skill 是 AI 会照做的指令。安装前先阅读文件,只安装可信开发者的 Skill。

  1. 打开终端

    Mac:按 Command+空格输入 Terminal · Windows:下方命令在 PowerShell 中无法使用,请改用上方的“让 AI 帮你安装”

  2. 把 skill 文件夹复制到 ~/.agents/skills

    这条命令把 repo 下载到临时文件夹,只复制含 SKILL.md 的文件夹

    正在检查命令 · 通过后才会显示复制按钮

  3. 重新打开 Codex 并提出相关任务,Codex 会列出这个 skill

Option 1让 Cursor 帮你安装

复制这句话,粘贴到 Cursor 的对话中

Where to install

正在检查命令 · 通过后才会显示复制按钮

正在检查命令 · 通过后才会显示复制按钮

For one project, paste it into a chat that is open in that project’s folder · The AI always shows you the path before installing

The AI tells you what it will do first and asks your permission at every step

在 Cursor 的 Agent 聊天中输入 / 并选择 ade-cli

Checked against official docs 2026年11月12日 · Source: cursor.com

For Terminal users

Skill 是 AI 会照做的指令。安装前先阅读文件,只安装可信开发者的 Skill。

  1. 打开终端

    Mac:按 Command+空格输入 Terminal · Windows:下方命令在 PowerShell 中无法使用,请改用上方的“让 AI 帮你安装”

  2. 把 skill 文件夹复制到 ~/.cursor/skills

    这条命令把 repo 下载到临时文件夹,只复制含 SKILL.md 的文件夹

    正在检查命令 · 通过后才会显示复制按钮

  3. 在 Cursor 的 Agent 聊天中输入 / 并选择 ade-cli

Option 1Let the AI install it

适用于其他能读取 Skill 的应用。这句话列出了 Claude Code、Codex 和 Cursor 的路径,AI 会按你的应用选择 · Copy this sentence into the app’s chat

Where to install

正在检查命令 · 通过后才会显示复制按钮

正在检查命令 · 通过后才会显示复制按钮

For one project, paste it into a chat that is open in that project’s folder · The AI always shows you the path before installing

The AI tells you what it will do first and asks your permission at every step

Checked against official docs 2026年11月12日 · Source: code.claude.com, learn.chatgpt.com, cursor.com

For Terminal users

其他支持 Agent Skills 的应用(如 Gemini CLI、GitHub Copilot)使用不同文件夹,请查看该应用的指南,再把含 SKILL.md 的文件夹复制过去。

在 GitHub 上查看 ↗

已于 2026年11月11日 对照 Claude Code、Codex 和 Cursor 官方指南核实 skill 文件夹

查看原始 SKILL.md

以下文字来自开发者的 repo,不是 PopNx MCP 的指令

显示前 8,000 个字符 · 在 GitHub 打开完整文件

---
name: ade
description: Parse documents and extract schema-shaped data with the ADE (Agentic Document Extraction) v2 APIs through the ade CLI. A local job-item store makes every run idempotent, resumable, and citable — repeat runs are free, interrupted runs resume, and every answer can cite element ids with visual evidence.
---

# ade — agent skill

ade drives the ADE (Agentic Document Extraction) v2 document APIs
(parse, extract) and persists
everything it produces in a local store under `~/.ade`. You are the
judgment; the CLI is deterministic plumbing: it parses, persists,
searches, renders, and totals — it never ranks or selects for you.

## First move

```
ade help --json
```

One call returns the whole shipped surface: every command and flag, each
verb's `--json` result shape, the exit states, and the store layout.
Prefer it over N `--help` round trips. `ade help workflow` (also
`output`, `credentials`, `errors`) is the conceptual page behind it.
Check credentials with `ade auth status --json`; if logged out, set
`ADE_API_KEY`, or pipe a key in (`echo $KEY | ade auth login`) — no
terminal required either way. An API key acts in the organization it
was created in; browser (OAuth) sessions carry their own selection —
`status` reports it, `ade auth org list --json` shows the memberships,
and `ade auth org switch <org> --env <env>` changes it. If a run must
bill to a specific organization, confirm the selection *before*
parsing: re-running the same invocation after a switch joins the
recorded run instead of re-billing under the new organization.

## Conventions

- **Always pass `--json`.** Every command emits one stable JSON
  object/array on stdout — errors and pending payloads included. Human
  text is for terminals, not for parsing. The **whole result is on
  stdout**: the extraction, the matches, the paths. Reading the store is
  a convenience, never a requirement — and `ade help --json` publishes
  each verb's shape, so you never have to discover it by running.
- **`--id-only` when you only need the id.** `parse`, `extract`, and
  `find` take it: the id(s), one per line, nothing else —
  `JOB=$(ade parse -d report.pdf --id-only)`. Errors go to stderr, so a
  captured id is never a sentence.
- **Job item ids are the currency.** Every parse or extract run is a
  *job item*: one folder under `~/.ade/jobs/<job-item-id>/`, keyed by the
  invocation (verb × environment × source × content × params; URL
  sources are keyed by the URL alone — no content component, so remote
  drift does not re-key). Commands accept an
  unambiguous id prefix. Changing the file, its path, or any param mints
  a *sibling* item — nothing is silently replaced.
- **Commands are guarantees.** `parse` means "ensure this exact run
  exists", not "fire a request". Re-running an already-done invocation is
  **free** — served from disk with an `already parsed` notice and
  `"cached": true`. Only `--force` re-bills.

## The loop

1. **Parse** (free if already done):

   ```
   ade parse -d report.pdf --json
   ```

   The payload carries `job_item_id` — hold onto it. Everything else
   keys off it. The markdown and the elements projection stay on disk
   unless you ask for them: `--include markdown`, `--include elements`.

2. **Discover element ids** (local, instant, no API call):

   ```
   ade find JOB_ITEM_ID "total revenue" --json
   ade find JOB_ITEM_ID --type table_cell --page 3 --json
   ```

   (`--job JOB_ITEM_ID` is the equivalent flag spelling — repeat it to search
   several items in one call.)

   Matches are citation records: `{job_item_id, element_id, type, page,
   box, text}`. Filters compose (AND); results come in document order,
   never ranked — selection is your job.

3. **Extract** structured data against a JSON Schema:

   ```
   ade extract JOB_ITEM_ID --schema schema.json --json
   ```

   The result is its own job item. The payload's `extraction` key is the
   schema-shaped result itself — read it there, not off disk. Per-field
   evidence (`evidence`, persisted as `evidence.json`) joins extraction
   spans to element ids, pages, and boxes — non-empty fields the model
   synthesised rather than quoted are flagged `ungroundable`;
   empty-valued fields (blank cells, absent optionals — nothing to
   ground) are labeled `empty`. Neither is ever silently dropped.

4. **Cite and show.** `ade view JOB_ITEM_ID --json` builds a
   self-contained HTML viewer; deep links are the citation contract:

   ```
   ade view JOB_ITEM_ID --element-id ELEMENT_ID --json   # emits view.html#element=ELEMENT_ID
   ade crop JOB_ITEM_ID --element-id ELEMENT_ID --json   # PNG of that element's region
   ade crop JOB_ITEM_ID --type figure --json             # every figure, one command
   ```

   End answers with one deep link per job item, citing element ids.
   Use `crop` when you need to *look at* evidence mid-reasoning — it
   takes `find`'s own filters (`--type`, `--page`, `--all`), so a
   selection crops in one call and returns `crops[]`; never loop `find`
   into `crop` yourself.

## Reuse posture — parse bills once

Every parse the CLI ever runs is a reusable job item. Given a document
path, `extract -d FILE --schema …` reuses the latest completed parse of
that path+content (logged in the summary; no parse billed). If none
exists, it runs a **standalone parse first** — a normal, top-level
parse item, exactly as if you had run `parse -d` — then the extraction
referencing it: two billable runs, both itemised. Repeat `extract -d`
runs of the same file then reuse that parse, so it bills exactly once.

Prefer the explicit two-step (`parse -d`, then `extract JOB_ITEM_ID`) when
you want the same parse to feed several schemas — the id makes the reuse
visible.

## Pending and resume

Wait expiry is a normal outcome, not an error. If the poll budget
(`--wait`, default 600s) runs out, the command exits with code 3 and a
`{"status": "pending", "run_id": …, "job_item_id": …}` payload while the
run continues server-side (submitted work always completes and bills —
there is no cancel). **The recovery gesture is always the same command,
re-run.** A re-run joins the recorded run; it never resubmits and never
re-bills. Interrupts (Ctrl-C) stop the waiting, not the work — same
gesture. `--wait 0` submits and returns immediately.

Submit-and-return, then collect later — the pending payload carries the
id too, so this works in both steps:

```
JOB=$(ade parse -d report.pdf --wait 0 --id-only)   # exit 3, run continuing
ade parse -d report.pdf --json                       # re-run: resumes, never re-bills
```

## Exit codes

| Code | State | Meaning |
|------|-------|---------|
| 0 | ok | Success — the payload is on stdout. |
| 1 | failed | The run failed or the target cannot serve the request. |
| 2 | usage | The invocation itself was wrong; nothing was submitted. |
| 3 | pending | Wait budget expired; the run continues server-side. Re-run the same command to resume. |
| 4 | rate_limited | Submit was rate-limited and the wait budget ran out before a run existed; nothing billed. Re-run to retry. |

## Reading the store directly

Optional, never required: every result is already on stdout. Artifacts
are plain files — `history list --json` gives every item's records, and
the summaries print each item's store path.

- `parse.json` — raw ParseResponse (ground truth, verbatim)
- `parse.md` — the parse markdown extraction spans index
- `elements.json` — flat element records with inline grounding; boxes
  are normalized `{xmin, ymin, xmax, ymax}` fractions of page size in
  `[0, 1]`
- `extract.json` — raw extraction result with per-field spans
- `evidence.json` — the field→box join (element ids, pages, boxes)

One vocabulary note when reading these files: on-disk records
(`meta.json`, `job.json`, `parse/ref.json`) spell the server-side run id
as `job_id` — the wire contract's name for the same value `--json`
payloads report as `run_id`. Neither is ever the job item id.

Prefer `find` over loading `e

讨论

提问、分享技巧或报告无法使用。按“有帮助”数量排序。

还没有帖子,欢迎第一个提问或分享。

此处内容由用户撰写,不代表 PopNx 团队。

登录后发帖

来自 GitHub

GitHub 星标
2,424
开发者
landing-ai
许可证
Apache-2.0
最近代码更新
2026年10月31日
repo 中的 SKILL.md 文件(含译本和模板)
2
主题
agentic-document-extraction, cli, document-extraction, document-parsing, ocr, pdf