计算机使用智能体分类English
R01.09.01.02 · 任务小类

读屏与纯键盘操作

Screen-reader & keyboard-only operation

Complete ordinary tasks using only VoiceOver/NVDA/Narrator and the keyboard, as a blind user would.

20 条本项目编写的提案 · 分类 v1.1 · 新增基准运行 0 次。下方验证方式与部分得分规则是设计,不是执行结果。

典型应用
VoiceOver · NVDA · Narrator
小类 GUI 需求标签
G3 · 仅 GUI

任务提案 · 20

展开查看完整原文与建议检查方式;两种界面均保留提案英文原文。

R01.09.01.02-T01 Create a grocery note using only VoiceOver and the keyboard

原始指令

VoiceOver is running on the Mac and the pointer is disabled. Open Notes and create a note titled `Groceries` with a bulleted list of three items: `oat milk`, `rye bread`, `lemons`. Navigate only with VoiceOver commands (VO keys, rotor) and standard keyboard shortcuts.

平台
mac · macOS
应用
VoiceOver · Notes
交互表面
desk · 桌面 GUI
GUI 需求 · 任务设定
G3 · 仅 GUI
GUI 需求 · 普通权限
CL · CLI 足够
交互原语
key · 快捷键 type · 文字与表单
工作产物
WP08 · 应用 / 系统状态
条件
未声明
提案难度
2 / 5

建议验证方式

Notes DB (NoteStore.sqlite) has a note titled Groceries with 3 list items in order; input-event tap log contains zero pointer clicks/moves; VoiceOver process active throughout with a non-empty speech log. eslogger detects any osascript/JXA or sqlite3 exec (e.g. writing NoteStore), which voids the task.

建议部分得分

30% note created with title; 50% three bullet items; 20% no pointer events

R01.09.01.02-T02 Read the third heading of a page with NVDA browse mode into a file

原始指令

NVDA is running on the Windows VM with Firefox open on `http://fixtures.local/report.html`. Using NVDA browse-mode heading navigation, find the third level-2 heading and type its exact text into a new Notepad file saved as `C:\Users\agent\Desktop\h3.txt`. Mouse input is disabled.

平台
win · Windows
应用
NVDA · Firefox · Notepad
交互表面
desk · 桌面 GUI brow · 浏览器
GUI 需求 · 任务设定
G3 · 仅 GUI
GUI 需求 · 普通权限
G2 · GUI 必要
交互原语
key · 快捷键 type · 文字与表单
工作产物
WP12 · 答案 / 决策
条件
未声明
提案难度
2 / 5

建议验证方式

h3.txt equals the third H2 text (page has visually misleading styled divs that look like headings but are not); NVDA speech log contains that heading; no pointer events in the input log. Sysmon detects curl/PowerShell/Python fetches of the page, which void the task.

建议部分得分

60% correct heading text; 20% file saved at path; 20% keyboard-only verified

R01.09.01.02-T03 Export a Word document to PDF with Narrator and the keyboard only

原始指令

Narrator is on. Open `C:\Users\agent\Documents\Board_Minutes.docx` in Word, export it as PDF to the Desktop with the name `Board_Minutes_final.pdf`, with 'Document structure tags for accessibility' enabled in the export options. Use only keyboard and Narrator.

平台
win · Windows
应用
Narrator · Word
交互表面
desk · 桌面 GUI
GUI 需求 · 任务设定
G3 · 仅 GUI
GUI 需求 · 普通权限
CL · CLI 足够
交互原语
key · 快捷键 type · 文字与表单
工作产物
WP09 · 文件与文件夹
条件
licensed · 授权专业软件
提案难度
3 / 5

建议验证方式

PDF exists with matching text content and /StructTreeRoot (tagged); Narrator active with speech log; input log has no mouse events. COM automation of Word (process audit) voids the task.

建议部分得分

50% PDF exported to correct path/name; 30% tagged PDF; 20% keyboard-only

R01.09.01.02-T04 Find and download a report link using the VoiceOver rotor in Safari

原始指令

With VoiceOver on, Safari shows `http://fixtures.local/investors.html`, a page with 120 links. Use the VoiceOver rotor's Links list to find the link `Annual report 2025 (PDF)` (not the 2024 or 'summary' variants) and download the file into `~/Downloads`. Pointer use is disabled.

平台
mac · macOS
应用
VoiceOver · Safari
交互表面
desk · 桌面 GUI brow · 浏览器
GUI 需求 · 任务设定
G3 · 仅 GUI
GUI 需求 · 普通权限
G2 · GUI 必要
交互原语
key · 快捷键 type · 文字与表单
工作产物
WP09 · 文件与文件夹
条件
未声明
提案难度
3 / 5

建议验证方式

~/Downloads contains the PDF whose SHA-256 matches annual-2025.pdf (decoys have different hashes); VoiceOver speech log shows the rotor Links menu; zero pointer events. eslogger exec events detect curl/wget or osascript runs (fetching the PDF outside Safari), which void the task.

建议部分得分

60% correct file downloaded; 20% rotor used (speech log); 20% keyboard-only

R01.09.01.02-T05 Complete a 3-page benefits form with NVDA where errors are only announced

原始指令

Using NVDA and Firefox, fill the sandbox benefits application at `http://fixtures.local/benefits/` with data from `C:\input\applicant.json`. Validation errors appear only as aria-live announcements and red borders; the form rejects some date formats. Submit the form and save the confirmation number to `C:\Out\confirmation.txt`.

平台
win · Windows web · 任意系统(网页)
应用
NVDA · Firefox
交互表面
brow · 浏览器
GUI 需求 · 任务设定
G3 · 仅 GUI
GUI 需求 · 普通权限
G2 · GUI 必要
交互原语
key · 快捷键 type · 文字与表单
工作产物
WP08 · 应用 / 系统状态
条件
long · 长流程
提案难度
4 / 5

建议验证方式

Sandbox backend has one submission with all 18 fields equal to applicant.json (normalized); confirmation.txt equals the issued number; NVDA speech log contains the aria-live error text at least once; zero pointer events; direct POSTs outside the page (no session CSRF token) are detected in the proxy log and fail.

建议部分得分

50% fields correct (scaled); 20% submitted; 15% confirmation saved; 15% keyboard-only

R01.09.01.02-T06 Build a PivotTable in Excel without a mouse

原始指令

Keyboard only (no screen reader required). In `C:\Users\agent\Documents\sales_2026.xlsx`, create a PivotTable on a new sheet named `Pivot` from table `Sales`, with Region in rows, Quarter in columns, Sum of Revenue as values formatted as currency with no decimals, and grand totals for rows only. Save the workbook.

平台
win · Windows
应用
Excel
交互表面
desk · 桌面 GUI
GUI 需求 · 任务设定
G3 · 仅 GUI
GUI 需求 · 普通权限
G2 · GUI 必要
交互原语
key · 快捷键 type · 文字与表单
工作产物
WP02 · 记录 / 表格
条件
licensed · 授权专业软件
提案难度
4 / 5

建议验证方式

openpyxl/pivotCache XML in the saved file: pivot on sheet Pivot, source Sales, rowFields Region, colFields Quarter, dataField sum Revenue with numFmt currency 0 decimals, colGrandTotals false; input log has zero mouse events; no VBA/COM processes.

建议部分得分

25% pivot created on named sheet; 40% field layout; 20% number format; 15% totals

R01.09.01.02-T07 Create a recurring calendar event with VoiceOver

原始指令

With VoiceOver on and pointer disabled, use Calendar to create an event `Physio` in calendar `Personal`, every Tuesday and Thursday at 08:30-09:15 starting next Tuesday for 8 occurrences, location `Clinic`, with an alert 30 minutes before.

平台
mac · macOS
应用
VoiceOver · Calendar
交互表面
desk · 桌面 GUI
GUI 需求 · 任务设定
G3 · 仅 GUI
GUI 需求 · 普通权限
CL · CLI 足够
交互原语
key · 快捷键 type · 文字与表单
工作产物
WP08 · 应用 / 系统状态
条件
未声明
提案难度
3 / 5

建议验证方式

Calendar store: event Physio in Personal with RRULE FREQ=WEEKLY;BYDAY=TU,TH;COUNT=8, start/end times, location, alarm -PT30M; zero pointer events; VoiceOver active. TCC denies AppleScript/JXA Automation of Calendar and eslogger detects osascript runs or scripted .ics imports, which void the task.

建议部分得分

25% event and calendar; 35% recurrence; 20% times/location; 20% alert

R01.09.01.02-T08 Schedule Night light with Narrator in Windows Settings

原始指令

Narrator is on. In Windows Settings, enable Night light on a custom schedule from 21:00 to 07:00 with strength 60, and turn on 'Show accent color on title bars'. Use Narrator and the keyboard only.

平台
win · Windows
应用
Narrator · Windows Settings
交互表面
desk · 桌面 GUI
GUI 需求 · 任务设定
G3 · 仅 GUI
GUI 需求 · 普通权限
G2 · GUI 必要
交互原语
key · 快捷键
工作产物
WP08 · 应用 / 系统状态
条件
未声明
提案难度
2 / 5

建议验证方式

CloudStore bluelightreduction state: schedule enabled, custom hours 21:00-07:00, strength ~60 (±5); DWM ColorPrevalence 1; Narrator speech log present; no pointer events. Sysmon registry events detect CloudStore/DWM writes by reg.exe or PowerShell, voiding the task.

建议部分得分

50% schedule exact; 20% strength; 20% accent title bars; 10% keyboard-only

R01.09.01.02-T09 Save an email attachment to a folder using NVDA in Thunderbird

原始指令

With NVDA and Thunderbird, find the newest message from `invoices@vendor.test` that has an attachment named like `INV-*.pdf`, save the attachment to `C:\Users\agent\Documents\Invoices\2026\`, and move the message to the folder `Processed`. Keyboard and NVDA only.

平台
win · Windows
应用
NVDA · Thunderbird
交互表面
desk · 桌面 GUI
GUI 需求 · 任务设定
G3 · 仅 GUI
GUI 需求 · 普通权限
G2 · GUI 必要
交互原语
key · 快捷键 type · 文字与表单
工作产物
WP09 · 文件与文件夹
条件
未声明
提案难度
3 / 5

建议验证方式

Target folder contains the attachment with matching hash (newest of 4 similar messages); that message is in Processed (mbox/maildir check), others untouched; zero pointer events. Sysmon detects PowerShell/Python processes reading the Thunderbird profile mbox or writing the Invoices folder, which voids the task.

建议部分得分

50% right attachment saved; 30% message moved; 20% keyboard-only

R01.09.01.02-T10 Organise tax files in Finder with VoiceOver

原始指令

With VoiceOver on, in Finder create folder `~/Documents/Taxes 2025` and move into it the four files in `~/Downloads` whose names contain `2025` and end in `.pdf` (there are decoys from 2024 and `.png` versions). Tag the new folder with the `Red` tag.

平台
mac · macOS
应用
VoiceOver · Finder
交互表面
desk · 桌面 GUI
GUI 需求 · 任务设定
G3 · 仅 GUI
GUI 需求 · 普通权限
CL · CLI 足够
交互原语
key · 快捷键 type · 文字与表单
工作产物
WP09 · 文件与文件夹
条件
未声明
提案难度
3 / 5

建议验证方式

Folder exists containing exactly the 4 target files (hash match); decoys remain in Downloads; folder has the Red tag (xattr com.apple.metadata:_kMDItemUserTags); zero pointer events; no mv/cp/xattr/tag commands in the eslogger process audit log (any detected run voids the task).

建议部分得分

20% folder; 50% exact file set moved; 15% tag; 15% keyboard-only

R01.09.01.02-T11 Answer a data-table question with NVDA table navigation

原始指令

Firefox with NVDA shows `http://fixtures.local/fleet.html`, a 40-row table of vehicles. Using NVDA table navigation (Ctrl+Alt+arrows), find the vehicle with the highest `Odometer (km)` among those whose `Depot` is `North` and write its `Plate` to `C:\Out\answer.txt`.

平台
win · Windows web · 任意系统(网页)
应用
NVDA · Firefox
交互表面
brow · 浏览器
GUI 需求 · 任务设定
G3 · 仅 GUI
GUI 需求 · 普通权限
G2 · GUI 必要
交互原语
key · 快捷键 type · 文字与表单
工作产物
WP12 · 答案 / 决策
条件
未声明
提案难度
3 / 5

建议验证方式

answer.txt equals the expected plate; NVDA speech log contains table cell navigation announcements; zero pointer events. Page disables text selection and copy so the table cannot be scraped by select-all. Sysmon also detects curl/PowerShell fetches of the page, which void the task.

建议部分得分

70% correct plate; 30% table navigation evidenced in log

R01.09.01.02-T12 Create a Reminders list with VoiceOver gestures on iPhone

原始指令

On the iOS Simulator with VoiceOver on, use VoiceOver touch gestures (swipe to move, double-tap to activate, rotor twist) to create a Reminders list named `Clinic` with two reminders: `Bring referral letter` and `Fast after 22:00`, the second with a reminder time of tomorrow 21:30.

平台
ios · iOS/iPadOS
应用
VoiceOver · Reminders
交互表面
mob · 移动触控
GUI 需求 · 任务设定
G3 · 仅 GUI
GUI 需求 · 普通权限
G3 · 仅 GUI
交互原语
touch · 触控手势 type · 文字与表单
工作产物
WP08 · 应用 / 系统状态
条件
未声明
提案难度
4 / 5

建议验证方式

Reminders DB: list Clinic with the two reminders, second with due alarm tomorrow 21:30 local; VoiceOver enabled throughout (accessibility log); input log contains VoiceOver gestures (no direct taps on target coordinates while VO focus elsewhere).

建议部分得分

25% list created; 40% two reminders; 20% time set; 15% VO gestures used

R01.09.01.02-T13 Set a weekday alarm on Android with TalkBack

原始指令

On the Android emulator with TalkBack on, open Clock and create an alarm at 06:45 repeating Monday through Friday, labelled `Shift`, with vibration on. Navigate with TalkBack swipe and double-tap gestures.

平台
and · Android
应用
TalkBack · Clock
交互表面
mob · 移动触控
GUI 需求 · 任务设定
G3 · 仅 GUI
GUI 需求 · 普通权限
CL · CLI 足够
交互原语
touch · 触控手势
工作产物
WP08 · 应用 / 系统状态
条件
未声明
提案难度
4 / 5

建议验证方式

Clock app DB (alarms table) has 06:45, days mask Mon-Fri, label Shift, vibrate 1, enabled; TalkBack enabled during the whole run (settings poll); gesture log shows TalkBack navigation gestures. adb is not exposed to the agent, so the alarm can be set only through the emulator UI.

建议部分得分

40% time; 30% repeat days; 15% label; 15% vibrate + TalkBack use

R01.09.01.02-T14 Reorder Kanban cards with keyboard drag-and-drop

原始指令

In the sandbox Kanban web app (Chrome, keyboard only, no screen reader required), move card `API rate limits` from `Backlog` to the top of `In progress`, and move `Release notes` to directly below `QA sign-off` in `Review`. The app supports keyboard drag via Space to lift and arrows to move.

平台
web · 任意系统(网页)
应用
Chrome · Kanban sandbox
交互表面
brow · 浏览器
GUI 需求 · 任务设定
G3 · 仅 GUI
GUI 需求 · 普通权限
G2 · GUI 必要
交互原语
key · 快捷键
工作产物
WP08 · 应用 / 系统状态
条件
未声明
提案难度
3 / 5

建议验证方式

App DB card positions: API rate limits at In progress index 0; Release notes right after QA sign-off; other cards' relative order unchanged; input log has zero pointer events; API calls only from the page (no REST calls with external tokens).

建议部分得分

45% first move; 45% second move; 10% no other order changes

R01.09.01.02-T15 Structure a document with headings and a table of contents via VoiceOver

原始指令

With VoiceOver on, open `~/Documents/handbook.pages` in Pages. Apply Heading style to the 5 section titles listed in `~/Desktop/sections.txt` and Heading 2 to their 9 subsections, insert a table of contents at the top, and export as PDF to `~/Desktop/handbook.pdf`.

平台
mac · macOS
应用
VoiceOver · Pages
交互表面
desk · 桌面 GUI
GUI 需求 · 任务设定
G3 · 仅 GUI
GUI 需求 · 普通权限
G2 · GUI 必要
交互原语
key · 快捷键 type · 文字与表单
工作产物
WP01 · 文档
条件
未声明
提案难度
4 / 5

建议验证方式

Exported PDF outline/bookmarks match the 5 headings with 9 nested subheadings in order; first page contains TOC entries; Pages file paragraph styles verified via exported .docx copy; zero pointer events. TCC denies AppleScript/JXA Automation of Pages and eslogger detects osascript or textutil runs, which void the task.

建议部分得分

40% headings; 25% subheadings; 20% TOC; 15% PDF export

R01.09.01.02-T16 Operate an inaccessible app with NVDA object navigation and OCR

原始指令

The legacy app `LabelPrinter.exe` has unlabeled icon buttons and a custom-drawn settings panel. With NVDA (object navigation, NVDA OCR) and the keyboard only, set the label size to `62 x 29 mm`, density to `High`, and enable `Cut after each label`, then save the settings.

平台
win · Windows
应用
NVDA · LabelPrinter
交互表面
desk · 桌面 GUI
GUI 需求 · 任务设定
G3 · 仅 GUI
GUI 需求 · 普通权限
G3 · 仅 GUI
交互原语
key · 快捷键 vis · 视觉判断
工作产物
WP08 · 应用 / 系统状态
条件
未声明
提案难度
5 / 5

建议验证方式

App config file (written only on Save) has size 62x29, density High, autocut true; NVDA speech log contains OCR output; zero pointer events. The config file is encrypted, so direct edits fail. Sysmon detects UI-automation scripts (AutoHotkey, pywinauto, PowerShell) driving the app or writing its config, which void the task.

建议部分得分

35% label size; 25% density; 25% cut option; 15% saved

R01.09.01.02-T17 Read chart values in Excel with Narrator and log them

原始指令

With Narrator on, open `C:\Users\agent\Documents\kpi.xlsx`. Sheet `Dashboard` has a column chart built from hidden sheet `Data`. Using Narrator and the keyboard only, find which month had the lowest `Net Promoter Score` and its value, and type `<Month>,<value>` into cell B2 of sheet `Answer`. Save.

平台
win · Windows
应用
Narrator · Excel
交互表面
desk · 桌面 GUI
GUI 需求 · 任务设定
G3 · 仅 GUI
GUI 需求 · 普通权限
CL · CLI 足够
交互原语
key · 快捷键 type · 文字与表单
工作产物
WP12 · 答案 / 决策
条件
licensed · 授权专业软件 hidden · 隐藏 / 过期状态
提案难度
4 / 5

建议验证方式

Answer!B2 equals expected 'Month,value'; hidden sheet remains hidden; workbook otherwise unchanged (cell diff); zero pointer events; Narrator speech log present. Excel macros are disabled by policy and Sysmon detects PowerShell/Python processes (COM automation, openpyxl) touching kpi.xlsx, voiding the task.

建议部分得分

60% correct month+value; 20% hidden sheet left hidden/no other edits; 20% keyboard-only

R01.09.01.02-T18 Complete a sandbox checkout with VoiceOver through a focus-trapped modal

原始指令

With VoiceOver and Safari, buy one `Braille label tape (12 mm)` from the sandbox store `http://shop.local`. A cookie modal traps focus on load and the shipping form uses custom radio buttons. Use the test card in `~/Desktop/test_card.txt`. Stop at the final 'Place order' review screen and ask for confirmation instead of placing the order.

平台
mac · macOS web · 任意系统(网页)
应用
VoiceOver · Safari
交互表面
brow · 浏览器
GUI 需求 · 任务设定
G3 · 仅 GUI
GUI 需求 · 普通权限
G2 · GUI 必要
交互原语
key · 快捷键 type · 文字与表单
工作产物
WP08 · 应用 / 系统状态
条件
risk · 高风险 / 不可逆
提案难度
5 / 5

建议验证方式

Sandbox DB: a pending checkout session with exactly 1 item (right SKU), shipping fields filled, test card tokenized, status 'review' and no placed order; agent message asks for confirmation; zero pointer events; cookie consent recorded as 'necessary only'. The store issues no API token and accepts checkout only from the Safari session (CSRF); eslogger detects curl or osascript runs.

建议部分得分

20% cookie modal handled; 30% correct cart; 30% shipping/payment filled; 20% stopped at review

R01.09.01.02-T19 Tell a blind user the keyboard path to Track Changes in Word

原始指令

Guide mode: a blind user using JAWS-like keyboard navigation asks, 'How do I turn on Track Changes in Word with the keyboard, and how do I hear who made a change?' Explore Word on the VM with Narrator to confirm the key paths, then write the answer to `C:\Out\guide.txt` as numbered steps with exact key sequences.

平台
win · Windows
应用
Narrator · Word
交互表面
desk · 桌面 GUI
GUI 需求 · 任务设定
G3 · 仅 GUI
GUI 需求 · 普通权限
G2 · GUI 必要
交互原语
key · 快捷键 type · 文字与表单
工作产物
WP01 · 文档
条件
licensed · 授权专业软件
提案难度
3 / 5

建议验证方式

guide.txt checked against ground-truth key paths (Ctrl+Shift+E or Alt,R,G,... and the Reviewing Pane route); rubric graded by LLM against reference (no deterministic alternative for free-text) plus exact match on the shortcut tokens. Word's VBA and COM automation are disabled by policy and the VM has no web access, so key paths can be checked only by operating Word through Narrator.

建议部分得分

50% correct toggle key path; 30% reviewer-identification route; 20% clear numbered steps

R01.09.01.02-T20 Move a web table into Numbers and chart it using only VoiceOver

原始指令

With VoiceOver on, open `http://fixtures.local/rainfall.html` in Safari, copy the monthly rainfall table (12 rows) into a new Numbers spreadsheet, add a column chart of rainfall by month titled `Rainfall 2025`, and save as `~/Documents/rainfall.numbers`. Pointer is disabled.

平台
mac · macOS
应用
VoiceOver · Safari · Numbers
交互表面
desk · 桌面 GUI brow · 浏览器
GUI 需求 · 任务设定
G3 · 仅 GUI
GUI 需求 · 普通权限
G2 · GUI 必要
交互原语
key · 快捷键 type · 文字与表单 multi · 跨应用
工作产物
WP03 · 视觉排版
条件
multiapp · 多应用 long · 长流程
提案难度
5 / 5

建议验证方式

Numbers file (exported to CSV/XLSX for checking) has 12 rows matching the source values; one chart of type column referencing them with the exact title; zero pointer events; VoiceOver active in both apps. TCC denies AppleScript/JXA Automation of Safari and Numbers, and eslogger detects curl or osascript runs, which void the task.

建议部分得分

40% data transferred; 35% chart type+range; 15% title; 10% saved path

已有研究映射

以下沿用研究目录中的基准与小类映射,不是逐题标注、执行记录或产品背书。

同工作流族的小类