Ready to supercharge your AI agents?

Install any skill in seconds. Free to start, no credit card required.

Get Started Free →

ecnu-icalk/基于文本的虚拟网络浏览器模拟

NewSkillScoreMaintained

扮演一个基于文本的网络浏览器，根据用户提供的URL返回想象中的网页内容，并支持通过特定格式的编号进行链接点击、输入框填写及页面导航。

by ecnu-icalk

Links this skill to your agents and keeps it current with the author’s updates.

Automatic

Coding pack

1 · One-time — install the CLI (docs ↗)

pip install decimalai

2 · Get the skill — writes .claude/skills/ecnu-icalk-3859e9/SKILL.md

decimalai skills pull ecnu-icalk-3859e9 --out .claude/skills/

No CLI? Get the same file — curl · raw file

curl -fsSL --create-dirs -o .claude/skills/ecnu-icalk-3859e9/SKILL.md https://app.decimal.ai/s/ecnu-icalk-3859e9/SKILL.md

Raw file: /s/ecnu-icalk-3859e9/SKILL.md ↗ · machine-readable summary at /s/ecnu-icalk-3859e9.json ↗

In productionGlobal

how this skill behaves on real traffic · last 30 days

No production data for this skill yet — usage numbers appear here once agents start running it.

Anonymized aggregate across every org using this skill — proof from real production use, not a demo.

Does this skill help? · Benchmark: with vs. withoutsign in to run this on your agents

22 test cases from the publisher’s eval.yaml · each run twice on gemini-3.6-flash — with the skill injected, then without · last run 8h ago

Yes — +68% lift-3% tokens0% turns86% of whole cases pass with skill (19/22)

Test case	Without → With	Effect	Δ tokens	Δ turns
case-01	✗→✓	▲ Improved	-13%	0%
case-02	✗→✓	▲ Improved	5%	0%
case-03	✗→✓	▲ Improved	47%	0%
case-04	✗→✓	▲ Improved	3%	0%
case-06	✗→✓	▲ Improved	-2%	0%

Showing 5 of 22 cases

SkillSafety

✓ 3 of 3 passed

Code scan15 of 15 checks clean

0 critical · 0 warning · 0 info — scanner v4 — 8/3/2026

live_secretremote_code_executionreverse_shelldata_exfiltrationssrf_metadataagent_snoopinganti_refusaldestructive_commandsobfuscated_unicodeunicode_homoglyphopaque_blobsuspicious_urltool_overreachtrigger_abuseprompt_injection_phrasing

IntentSafe

LLM judge · does the skill do what it claims

ContentClean

LLM judge · policy & harmful-content review

Source

Imported

ecnu-icalk / autoskill

SkillBank/ConvSkill/chinese_gpt3.5_8/%E5%9F%BA%E4%BA%8E%E6%96%87%E6%9C%AC%E7%9A%84%E8%99%9A%E6%8B%9F%E7%BD%91%E7%BB%9C%E6%B5%8F%E8%A7%88%E5%99%A8%E6%A8%A1%E6%8B%9F/SKILL.md

View on GitHub ↗

Imported 8/3/2026Version v1

Skill contents

SKILL.md

基于文本的虚拟网络浏览器模拟

扮演一个基于文本的网络浏览器，根据用户提供的URL返回想象中的网页内容，并支持通过特定格式的编号进行链接点击、输入框填写及页面导航。

Prompt

Role & Objective

你是一个基于文本的网络浏览器，用于浏览一个想象中的互联网。你的任务是根据用户输入的URL返回该网页的内容。

Operational Rules & Constraints

输出格式：只回复页面的内容，不要写任何解释。
链接格式：页面上的链接旁边必须写上数字，并包含在方括号 ] 之间（例如：Gmail 1]）。
输入框格式：页面上的输入应在 ] 之间写上数字，输入占位符应写在圆括号 () 之间（例如：1] (搜索内容)）。
交互逻辑：

当用户回复链接的编号时，跳转到该链接并返回内容。
当用户输入 1 时，将“示例值”插入到编号为 1 的输入中。
当用户输入 (b) 时，返回上一页。
当用户输入 (f) 时，继续前进（如果有历史记录）。

Anti-Patterns

不要在输出中包含任何解释性文字或对话填充。
不要忽略用户输入的特定格式指令。

Triggers

扮演一个基于文本的网络浏览器
模拟一个文本浏览器
浏览想象中的互联网
text based browser simulation
我想让你扮演浏览器

Want to see if ecnu-icalk/基于文本的虚拟网络浏览器模拟 would activate on your phrasing? Try it before you install — no LLM call, no signup.

Other measured skills in the registry, with their headline benchmark lift.

a5c-ai/neutralino-js-configConfigure Neutralino.js for lightweight desktop applications+27 pts pass-rate lift
a5c-ai/file-watcher-setupSet up cross-platform file system watching with debouncing and efficient change detection+23 pts pass-rate lift
a5c-ai/api-inventory-scannerDiscover and document existing API endpoints from code, logs, and traffic analysis+77 pts pass-rate lift
agent-code-review-swarmAgent skill for code-review-swarm - invoke with $agent-code-review-swarm+82 pts pass-rate lift
camunda/analytics-exporterUse when adding support for a new event or metric in the analytics exporter at zeebe/exporters/analytics-exporter/ — creating handlers, adding AnalyticsAttributes, registering in the HandlerRegistry, and writing tests. Also use when modifying existing handlers or attributes.+70 pts pass-rate lift
MADR decision recordsUse when documenting an architecture or technology decision that has already been made, for a repo's docs or a team knowledge base: structure it as a MADR record with Context and Problem Statement, Decision Drivers, Considered Options, a Chosen-option sentence, and Good/Bad consequence bullets. Do NOT use for meeting minutes, status updates, or for weighing a decision that has not been made yet.+59 pts pass-rate lift
mohitagw15856/code-review-guideReview a pull request or diff like a thoughtful senior engineer — prioritized, kind, and focused on what matters. Use when reviewing code, giving PR feedback, or asked to 'review this change'. Produces a structured review: a correctness/design pass, comments ranked by severity (blocking → nit), what's done well, and a clear approve / request-changes call — feedback that improves the code and the author.+14 pts pass-rate lift
a5c-ai/code-review-orchestration6-agent parallel code review orchestration covering architecture, security, performance, testing, quality, and documentation dimensions with weighted scoring.+52 pts pass-rate lift