BF windows-browser-ops
Windows Desktop 浏览器远程操控。用于在 Discord / 本地会话中触发 Edge/Chrome 执行“打开网页、交互、截图、打包下载”等动作，并回传证据。
As a process F 45/100 · Will not run — References files that are not bundled: scripts/launch_edge.ps1, scripts/focus_edge.ps1, scripts/edge_nav.ps1
How to improve
- Say in the description WHEN to use the skill ("use when…", example requests): that is the agent's main cue.
- 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 · 0
✓ No critical or high findings
Files scanned: 5. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
description-no-whendescription does not say WHEN to use the skill (no "use when") - warning
missing-refreference to a missing file: scripts/launch_edge.ps1 - warning
missing-refreference to a missing file: scripts/focus_edge.ps1 - warning
missing-refreference to a missing file: scripts/edge_nav.ps1 - warning
missing-refreference to a missing file: scripts/capture_screenshot.ps1 - warning
missing-refreference to a missing file: scripts/download_and_zip.ps1
Process rating: all ten parameters 45/100
Will not run. References files that are not bundled: scripts/launch_edge.ps1, scripts/focus_edge.ps1, scripts/edge_nav.ps1
- 0Tools and files. 5 referenced file(s) missing: scripts/launch_edge.ps1, scripts/focus_edge.ps1, scripts/edge_nav.ps1
- 0Result and completion. Does not say what the result is
- 0Progress reporting. Says nothing while it works
- 20When it triggers. No condition that starts the skill
- 30Running it twice. 1 mutating operations with no state check
- 50Failures and branches. 0 branches, has a failure section
- 70Inputs and preconditions. Inputs and preconditions are listed
- 100Steps. 26 steps
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 794 tokens
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)
- +3Description length 87: 120–800 characters recommended
- +3Output format is not stated: the model decides each time
- -4Absolute local paths (C:\Users, /home/…): not portable
- +1No license
- +2Single-language instructions
- +4Structure: 12 headings
- +3Step-by-step instructions: 26 items
- +4Has examples (1 code blocks)
- +4Reference files are cited in the instructions (2 of 2)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 57.
External checks
ClawHub: suspicious
This skill openly controls a Windows browser, but it gives broad access to screenshots, downloads, logged-in sessions, and uploads without enough limits.
LLM: suspicious (high) · VirusTotal: · 29 May 2026