Form Filling
platonai/Browser4
Automatically fills web forms using provided field data and can optionally submit the form.
Smart browser task agent - describe what you want done in natural language and it completes automatically.
Install Browser Task
$ npx skills add openakita/openakita --skill browser-task -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install openakita/openakita browser-task --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/openakita/openakita.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/system/browser-task .claude/skills/browser-task && rm -rf skills-srcUse ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.
Claude Code skills documentation · loads skills from .claude/skills/
Install the "browser-task" agent skill from https://github.com/openakita/openakita/tree/main/skills/system/browser-task into .claude/skills/browser-task/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "browser-task", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/openakita/openakita/tree/main/skills/system/browser-taskType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add openakita/openakita --skill browser-task -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install openakita/openakita browser-task --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/openakita/openakita.git skills-src && mkdir -p .agents/skills && cp -r skills-src/skills/system/browser-task .agents/skills/browser-task && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "browser-task" agent skill from https://github.com/openakita/openakita/tree/main/skills/system/browser-task into .agents/skills/browser-task/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "browser-task", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add openakita/openakita --skill browser-task -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install openakita/openakita browser-task --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/openakita/openakita.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/skills/system/browser-task .cursor/skills/browser-task && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "browser-task" agent skill from https://github.com/openakita/openakita/tree/main/skills/system/browser-task into .cursor/skills/browser-task/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "browser-task", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/openakita/openakita.git --path skills/system/browser-task--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add openakita/openakita --skill browser-task -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install openakita/openakita browser-task --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/openakita/openakita.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/skills/system/browser-task .gemini/skills/browser-task && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "browser-task" agent skill from https://github.com/openakita/openakita/tree/main/skills/system/browser-task into .gemini/skills/browser-task/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "browser-task", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install openakita/openakita browser-taskInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add openakita/openakita --skill browser-task -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/openakita/openakita.git skills-src && mkdir -p .github/skills && cp -r skills-src/skills/system/browser-task .github/skills/browser-task && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "browser-task" agent skill from https://github.com/openakita/openakita/tree/main/skills/system/browser-task into .github/skills/browser-task/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "browser-task", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add openakita/openakita --skill browser-task -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install openakita/openakita browser-task --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/openakita/openakita.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/skills/system/browser-task .opencode/skills/browser-task && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "browser-task" agent skill from https://github.com/openakita/openakita/tree/main/skills/system/browser-task into .opencode/skills/browser-task/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "browser-task", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
Facts
- Skill name
browser-task- GitHub stars
- 2k
- Token cost
- ~715 tokens
- SKILL.md length
- 146 words
- Files
- 2
- Skills in repo
- 29
- Repo updated
- First seen
- Licence
- AGPL-3.0
At a glance
Smart browser task agent - describe what you want done in natural language and it completes automatically.
- Works in 4 steps: 任务描述要清晰具体，避免歧义 → 复杂任务可能需要增加 max_steps → 首次使用会自动启动浏览器（可见模式） → …
- Tasks that involve Forms and invoices
- SKILL.md covers 用法, 参数, 何时使用（优先） and 示例, plus 7 more sections
- Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md
What it does
Browser Task is an agent skill from openakita/openakita. Smart browser task agent - describe what you want done in natural language and it completes automatically. PREFERRED tool for multi-step browser operations like searching, form filling, and data extraction.
Its SKILL.md is about 720 tokens, which your agent loads only when the skill is triggered. The skill folder holds 2 other files (for example `agents/openai.yaml`).
It sits in Documents & Office, covering Forms and invoices. It works with Chrome DevTools. The repository describes itself as: An open-source AI assistant framework with skills and agent architecture. The licence is AGPL-3.0.
When your agent uses it
- Tasks that involve Forms and invoices
Example prompts
- “/browser-task”
Requirements
- Python 3
Workflow steps
4 steps, taken from the first numbered list in SKILL.md.
- 任务描述要清晰具体，避免歧义
- 复杂任务可能需要增加 max_steps
- 首次使用会自动启动浏览器（可见模式）
- 自动继承系统 LLM 配置，无需额外配置 API Key
What it can do on your machine
Read from SKILL.md and the folder at commit 5f5b38d. It shows what the files ask for, not the result of running them.
Tool permissions
Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.
From allowed-tools in the SKILL.md frontmatter.
Runs code
No scripts in the folder and no shell commands in SKILL.md (its code samples are python, bash, json and cmd).
From the folder's file list and the shell code blocks in SKILL.md.
Network
Links to these hosts (documentation or services it may open):
github.com
From URLs in SKILL.md, links to its own repository left out.
Credentials
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Context cost
Browser Task loads about 715 tokens when it runs. Until then it costs about 55 tokens; SKILL.md has 146 words of instructions outside code blocks.
Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.
Safety
Auto-check passed
The automated check found no risky patterns in SKILL.md.
Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.
SKILL.md
The full file from openakita/openakita at commit 5f5b38d, republished under its AGPL-3.0 licence (© openakita). 146 words, ~715 tokens.
Download SKILL.mdSave it as
.claude/skills/browser-task/SKILL.md (or your agent's skills folder). This skill also uses 1 other file; get the full folder from GitHub.- name
- browser-task
- description
- Smart browser task agent - describe what you want done in natural language and it completes automatically. PREFERRED tool for multi-step browser operations like searching, form filling, and data extraction.
- system
- true
- handler
- browser
- tool-name
- browser_task
- category
- Browser
- priority
- high
browser_task - 智能浏览器任务
推荐优先使用 - 这是浏览器操作的首选工具。
基于 browser-use 开源项目实现。
用法
browser_task(
task="要完成的任务描述",
max_steps=15 # 可选，默认 15
)参数
| 参数 | 类型 | 必填 | 说明 |
|---|---|---|---|
| task | string | 是 | 任务描述，用自然语言描述你想完成的操作 |
| max_steps | integer | 否 | 最大执行步骤数，默认 15 |
何时使用（优先）
- 任何涉及多步骤的浏览器操作
- 网页搜索、表单填写、信息提取
- 不确定具体操作步骤时
- 复杂的网页交互流程
示例
搜索任务
browser_task(task="打开百度搜索福建福州天气")表单填写
browser_task(task="打开 example.com 的注册页面，填写用户名 test123")信息提取
browser_task(task="打开 GitHub 首页，获取今日热门项目的名称")截图任务
browser_task(task="打开百度搜索福建福州，截图保存")浏览器 & 网站操作工具选用指引
系统提供多条路径操作网站和浏览器，按场景选择最可靠的方案：
| 场景 | 推荐工具 | 说明 |
|---|---|---|
| 目标网站有 opencli adapter | opencli_run（最可靠） | 确定性命令 + JSON 输出，复用 Chrome 登录态 |
| 需要登录但无 adapter | browser_task → 手动组合 | 先尝试 browser_task，失败则用 click/type 手动操作 |
| 仅需读取网页内容 | web_fetch | 最快最省资源，无需浏览器 |
| 仅需搜索 | web_search | DuckDuckGo 直接搜索 |
| 复杂多步浏览器交互 | browser_task | 适合登录、填表、筛选等 |
| 单步浏览器操作 | browser_navigate/browser_click 等 | 精确控制单个操作 |
| 操作用户已登录的 Chrome | call_mcp_tool("chrome-devtools", ...) | 需用户 Chrome 开启调试端口 |
决策顺序：opencli_run（有 adapter 时）→ web_fetch/web_search（只读时）→ browser_task → 手动 browser_click/type 组合 → chrome-devtools MCP。
何时使用细粒度工具
仅在以下情况使用 browser_navigate、browser_click 等细粒度工具：
browser_task执行失败需要手动介入- 仅需单步操作（如只截图
browser_screenshot） - 需要精确控制特定元素
返回值
{
"success": true,
"result": {
"task": "打开百度搜索福建福州",
"steps_taken": 5,
"final_result": "搜索完成，已显示福建福州相关结果",
"message": "任务完成: 打开百度搜索福建福州"
}
}注意事项
- 任务描述要清晰具体，避免歧义
- 复杂任务可能需要增加 max_steps
- 首次使用会自动启动浏览器（可见模式）
- 自动继承系统 LLM 配置，无需额外配置 API Key
技术细节
- 通过 CDP (Chrome DevTools Protocol) 复用 OpenAkita 已启动的浏览器
- 自动继承 OpenAkita 系统配置的 LLM（来自 llm_endpoints.json）
- 基于 browser-use 开源项目
高级：操作用户已打开的 Chrome
如果想让 OpenAkita 操作你已打开的 Chrome 页面，需要以调试模式启动 Chrome：
Windows:
"C:\Program Files\Google\Chrome\Application\chrome.exe" --remote-debugging-port=9222macOS:
/Applications/Google\ Chrome.app/Contents/MacOS/Google\ Chrome --remote-debugging-port=9222Linux:
google-chrome --remote-debugging-port=9222启动后，OpenAkita 会自动检测并连接，可以操作你已打开的标签页。
相关技能
browser_screenshot- 单独截图browser_navigate- 单独导航deliver_artifacts- 发送结果给用户
© openakita, AGPL-3.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
Files
SKILL.md and 1 other file in skills/system/browser-task of openakita/openakita.
- SKILL.md
- agents/openai.yaml
Open the folder on GitHubat commit 5f5b38d
Compare with similar skills
Browser Task next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Browser Task this skillopenakita/openakita | 2k | — | ~715 | Automated safety check: Pass | AGPL-3.0 | |
| Form Fillingplatonai/Browser4 | 1.2k | — | ~1.1k | Automated safety check: Pass | Apache-2.0 | |
| Code2mediatsingliuwin/autoclaw | 283 | — | ~956 | Automated safety check: Pass | MIT | |
| Token ReceiptHchen1218/token-receipt | 126 | — | ~2.1k | Automated safety check: Pass | None | |
| Web Browsermitsuhiko/agent-stuff | 3.2k | — | ~1.5k | Automated safety check: Warn | Apache-2.0 | |
| Invoice Makertsingliuwin/autoclaw | 283 | — | ~612 | Automated safety check: Pass | MIT |
Similar skills
Code2media
tsingliuwin/autoclaw
Universal media renderer with no fixed template — any custom layout, size or style becomes pixel-perfect images (PNG/JPEG/WebP), vector SVG, paged PDFs or animations (WebP/GIF).
Token Receipt
Hchen1218/token-receipt
A skill your agent uses when the user wants to view AI conversation token usage as a receipt, invoice, checkout slip, token bill, usage receipt, cost snapshot, or creative monospace thermal-paper…
Web Browser
mitsuhiko/agent-stuff
Automate and interact with web pages through Chrome or Chromium using the Chrome DevTools Protocol (CDP): navigate, click, fill forms, inspect content, take screenshots, and debug console or network…
Invoice Maker
tsingliuwin/autoclaw
开发票/生成发票/报价单/收据/采购单/对账单/账单/付款通知 — formal business documents as paged PDFs with proper tables, right-aligned amounts, tax lines, repeating headers and page-number footers.
Invoice Generator
luzhenqian/ai-coding-lab
从 Excel 时间表或手动输入生成专业发票。当用户提到生成发票、创建账单、invoice、billing、开发票、时间表转发票、账单生成时使用此技能。
More from openakita/openakita
All 29 skills in this repoSmtp Email Sender
openakita/openakita
Send emails via SMTP (Gmail, Outlook, etc.). An agent skill from openakita/openakita.
Deliver Artifacts
openakita/openakita
Deliver artifacts (files/images/voice) to current IM chat via gateway, returning a receipt.
Switch Persona
openakita/openakita
Switch Agent persona preset. An agent skill from openakita/openakita.
Toggle Proactive
openakita/openakita
Toggle proactive messaging mode. An agent skill from openakita/openakita.
CLI Anything
openakita/openakita
Control desktop software (GIMP, Blender, LibreOffice, etc.) through CLI-Anything generated command-line interfaces.
Run Shell
openakita/openakita
Execute shell commands for system operations, directory creation, and script execution.
Related
Works with
Categories
Questions about Browser Task
What does Browser Task do?
Smart browser task agent - describe what you want done in natural language and it completes automatically. Browser Task is an agent skill from openakita/openakita. Smart browser task agent - describe what you want done in natural language and it completes automatically.
When should I use Browser Task?
Browser Task fits situations like: tasks that involve Forms and invoices.
How do I install Browser Task in Claude Code?
Run `npx skills add openakita/openakita --skill browser-task -a claude-code`. Or copy the skill folder (skills/system/browser-task in openakita/openakita) into .claude/skills/browser-task in your project. Claude Code loads it when a task matches its description.
How do I install Browser Task in Codex?
Run `npx skills add openakita/openakita --skill browser-task -a codex`. Or copy the skill folder (skills/system/browser-task in openakita/openakita) into .agents/skills/browser-task in your project. Codex loads it when a task matches its description.
Can I use Browser Task in Cursor, Gemini CLI or GitHub Copilot?
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add openakita/openakita --skill browser-task -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/browser-task, .gemini/skills/browser-task, .github/skills/browser-task and .opencode/skills/browser-task in your project.
What does Browser Task need to run?
SKILL.md names no scripts, command-line tools or credentials: Browser Task is instructions for the agent only. Our summary lists: Python 3.
Does Browser Task access the network?
SKILL.md names 1 domain. As links in the text: github.com. This is read from the text; nothing was executed.
Is Browser Task safe to install?
Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.
What licence does Browser Task use?
Browser Task is published under the AGPL-3.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
How many tokens does Browser Task use?
About 715 tokens (SKILL.md is roughly 2.9k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.
What are the alternatives to Browser Task?
Skills that share tags, products or a category with Browser Task: Form Filling (platonai/Browser4, 1.2k stars), Code2media (tsingliuwin/autoclaw, 283 stars), Token Receipt (Hchen1218/token-receipt, 126 stars) and Web Browser (mitsuhiko/agent-stuff, 3.2k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Browser Task?
openakita (a GitHub user) maintains it in openakita/openakita, which has 2,003 GitHub stars. The repository holds 29 skills in this directory. The repository was last updated on September 24, 2026.
Source: openakita/openakita on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.