SKILLEMALL.ai
GitHub ↗ RU Sign in

BF screenclaw

用“截图 + 坐标网格”的方式操作任意桌面软件：截带网格的图，让任意多模态大模型读出目标的坐标数字，再调用点击/输入/按键等 API ，模拟人类视觉化操作软件。还能录制一次操作并沉淀成可复用的场景模板，下次直接复用。不依赖目标软件提供 API 或 CLI。 出现以下情况时使用： - 自动化操作 Windows 桌面软件（微信、风控严格的网页如小红书/抖音、手机模拟器、游戏、任意 Windows 程序），尤其是 Playwright/CDP/CLI/应用 API 无法覆盖的软件或元素（如隐藏按钮、游戏画面、验证码等） - 用户说“帮我操作/点/输入 XX”“自动操作 XX”“模拟点击”“桌面自动化”“RPA”“录制操作”“沉淀成模板”“下次自动跑”等 - 操作桌面元素或跨进程跨窗口（桌面图标、任务栏、托盘、开始菜单、文件选择框、跨窗口拖拽） 只要目标是能在屏幕上看到、需要鼠标键盘操作的 Windows 桌面程序，即使它没 API、没专用技能、不确定怎么自动化，都应优先用本技能尝试。

ClawHub Agent Skills author: 见星 v0.1.7 MIT-0 49 files · 6 scripts body ≈ 1 967 tokens Open the sourceclawhub.ai↗ analyzed 3 d ago

用“截图 + 坐标网格”的方式操作任意桌面软件：截带网格的图，让任意多模态大模型读出目标的坐标数字，再调用点击/输入/按键等 API ，模拟人类视觉化操作软件。还能录制一次操作并沉淀成可复用的场景模板，下次直接复用。不依赖目标软件提供 API 或 CLI。 出现以下情况时使用： - 自动化操作 Windows…

As a process F 35/100 · Will not run — References files that are not bundled: scripts/screenclaw.py|ps1|sh, references/api/{endpoint}.md, scripts/recording_windows.py|ps1|sh

IntegrationPlaywrightGitHubWriting and documentstype and topics are labelled automatically from the skill text
Runs in: OpenClaw 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) Goose OpenCode
JSON
Technical rating
B
77/100
safety, quality, tests
Safety 60%
85
Quality 40%
66
Run on models
none yet
Process rating
F
35/100
Will not run
References files that are not bundled: scripts/screenclaw.py|ps1|sh, references/api/{endpoint}.md, scripts/recording_windows.py|ps1|sh
Tools and files w 18
0
Result and completion w 14
0
Inputs and preconditions w 11
0
the three weakest of ten parameters · all ten

What is at stake

Medium-severity findings: the skill is probably honest, but read what alarmed the scanner.

Dangerous commands medium severity

Below is the worst case for this category. The finding here is medium: the guard saw a sign, not a proof.

If you install

The skill contains commands that delete files, rewrite disks or execute code fetched from the network. The agent may run them without asking if it believes the instructions require it.

For the author

Replace destructive commands with safe equivalents that ask for confirmation, scope them to one folder, and stop piping curl into a shell: pin a version and a checksum.

How to improve

  1. Say in the description WHEN to use the skill ("use when…", example requests): that is the agent's main cue.
  2. The text references files that are not there: add them or drop the references.
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 · 3

✓ No critical or high findings

Medium and low: 3
  • medium Dangerous commands cmd-execpolicy-bypass scripts/README.md:47
    Runs PowerShell with execution policy bypassed
    powershell -ExecutionPolicy Bypass -File scripts/scre…ps1 <endpoint> api_url=<url> token=<token> ai_app_type=<type> session_id=<id> [endpoint参数...]
  • medium Dangerous commands cmd-execpolicy-bypass scripts/README.md:75
    Runs PowerShell with execution policy bypassed
    powershell -ExecutionPolicy Bypass -File scripts/coor…ps1 `
  • medium Dangerous commands cmd-execpolicy-bypass scripts/README.md:150
    Runs PowerShell with execution policy bypassed
    powershell -ExecutionPolicy Bypass -File scripts/reco…ps1 path=record/record_YYYYMMDD_HHmmss

Files scanned: 49. Evidence is masked. Grey chips explain why severity was lowered.

Against the Agent Skills spec

  • warning description-no-when description does not say WHEN to use the skill (no "use when")
  • warning missing-ref reference to a missing file: scripts/screenclaw.py|ps1|sh
  • warning missing-ref reference to a missing file: references/api/{endpoint}.md
  • warning missing-ref reference to a missing file: scripts/recording_windows.py|ps1|sh
  • warning missing-ref reference to a missing file: scripts/coord_adapt.py|ps1|sh
  • warning missing-ref reference to a missing file: references/api/*.md

Process rating: all ten parameters 35/100

Will not run. References files that are not bundled: scripts/screenclaw.py|ps1|sh, references/api/{endpoint}.md, scripts/recording_windows.py|ps1|sh
  • 0Tools and files. 5 referenced file(s) missing: scripts/screenclaw.py|ps1|sh, references/api/{endpoint}.md, scripts/recording_windows.py|ps1|sh
  • 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
  • 100Steps. 60 steps
  • 100Consistency. Name and required fields are in place
  • 100Execution cost. Instruction body is 1967 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

  • +4Description does not say when NOT to use the skill (false activations)
  • +3Output format is not stated: the model decides each time
  • -35 of 10 scripts are never mentioned in SKILL.md
  • +1No license
  • +2Single-language instructions
  • +5Description quotes 3 example trigger phrases
  • +3Description length 446: enough signal without eating the budget
  • +4Structure: 18 headings
  • +3Step-by-step instructions: 60 items
  • +4Has examples (2 code blocks)
  • +4Reference files are cited in the instructions (2 of 2)

Quality base 70; lint remarks subtract, signals add up to 100. Result: 66.

External checks

ClawHub: suspicious
ScreenClaw is a real desktop automation skill, but it grants broad mouse, keyboard, screenshot, remote-transfer, install, and credential-handling authority that needs careful review before use.
LLM: suspicious (high) · 23 Jun 2026