SKILLEMALL.ai
GitHub ↗ RU Sign in

BD computer-use

构建 GUI 自动化 Agent、让 Agent 像人一样看屏幕并用鼠标键盘操作桌面或浏览器软件时使用。 覆盖感知-思考-行动循环、动作空间（GUI/bash/文件编辑）、视觉定位 Grounding 三条路线 （结构化元素索引、Set-of-Mark、纯坐标预测）、分辨率坐标缩放、关键帧观察接口、世界模型与移动端生态壁垒。 触发词：Computer Use、GUI 自动化、截图、Grounding、browser-use、Set-of-Mark、视觉定位、坐标缩放、OSWorld。

bojieli/ai-agent-book Agent Skills author: bojieli Apache-2.0 1 file body ≈ 1 098 tokens Open the sourcegithub.com↗ analyzed 6 d ago

构建 GUI 自动化 Agent、让 Agent 像人一样看屏幕并用鼠标键盘操作桌面或浏览器软件时使用。 覆盖感知-思考-行动循环、动作空间（GUI/bash/文件编辑）、视觉定位 Grounding 三条路线…

As a process D 46/100 · Unfinished process — weak spots: result and completion, when it triggers, inputs and preconditions

ProcedureAI and agentstype and topics are labelled automatically from the skill text
Runs in: Claude / Claude Code ChatGPT / Codex Gemini CLI Cursor GitHub Copilot / VS Code Qwen Code Kimi Code CLI Z.ai (GLM) DeepSeek (Deep Code) Mistral Vibe LangChain (deepagents) OpenClaw Goose OpenCode
JSON
Technical rating
B
92/100
safety, quality, tests
Safety 60%
100
Quality 40%
80
Run on models
none yet
Process rating
D
46/100
Unfinished process
Result and completion w 14
0
Inputs and preconditions w 11
0
Failures and branches w 10
0
the three weakest of ten parameters · all ten

How to improve

    For the model run — optional
    • Your own cases (evals/evals.json, 4–6 real requests with expected answers): the full check would then run those instead of a model-drafted suite.
    • A spec.yaml with trigger phrases and assertions — a behaviour contract for CI; `skilltest init` writes a template.

    Guard findings · 0

    ✓ No critical or high findings

    Files scanned: 1. Evidence is masked. Grey chips explain why severity was lowered.

    Against the Agent Skills spec

    ✓ No remarks against the Agent Skills spec

    Process rating: all ten parameters 46/100

    • 0Result and completion. Does not say what the result is
    • 0Inputs and preconditions. Does not say what the process needs to start
    • 0Failures and branches. Linear process with no failure handling
    • 0Progress reporting. Says nothing while it works
    • 20When it triggers. No condition that starts the skill
    • 60Tools and files. Uses tools (bash) that frontmatter does not declare
    • 100Steps. 52 steps
    • 100Consistency. Name and required fields are in place
    • 100Execution cost. Instruction body is 1098 tokens
    • 100Running it twice. No mutating operations

    Everything here is measured from the skill text rather than judged by a model, so the numbers are checkable. A parameter weighs more when it is a more common reason for the process to stall.

    Quality signals

    • +5Description has no quoted example phrases that should trigger the skill
    • +4Description does not say when NOT to use the skill (false activations)
    • +3Output format is not stated: the model decides each time
    • +4No input/output examples
    • +1No license
    • +2Single-language instructions
    • +3Description length 244: enough signal without eating the budget
    • +4Structure: 7 headings
    • +3Step-by-step instructions: 52 items

    Quality base 70; lint remarks subtract, signals add up to 100. Result: 80.