AC agentlink
Cloud sandbox capabilities (Browser + Windows Desktop). Proactively use this skill when: - User asks to open/visit any URL, view web content, or take web screenshots - Need to extract data from websites, scrape information, or read page content - Need to fill online forms, log in to websites, click buttons, or perform web interactions - User asks to execute code (Python/PowerShell/Shell), run scripts, or install packages - Need to operate Windows desktop applications (Notepad, browsers, File Manager, etc.) - Need to run commands in an isolated environment, read/write files, or manage processes - User asks for automated testing, RPA, or periodic web monitoring Even if the user doesn't explicitly mention "sandbox" or "browser", proactively use this skill whenever the task involves web browsing, code execution, or desktop operations. Powered by agentlink_sdk (China Mobile AgentLink).
Cloud sandbox capabilities (Browser + Windows Desktop).
As a process C 50/100 · Has gaps — weak spots: result and completion, inputs and preconditions, consistency
How to improve
- 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: 3. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- note
frontmatter-keyunknown frontmatter key "metadata.openclaw"
Process rating: all ten parameters 50/100
- 0Result and completion. Does not say what the result is
- 0Inputs and preconditions. Does not say what the process needs to start
- 40Consistency. Frontmatter name (agentlink) differs from the folder (agentlink-skill)
- 50Failures and branches. 0 branches, has a failure section
- 60Tools and files. Uses tools (bash, python) that frontmatter does not declare
- 70When it triggers. States when to use, but not when not to
- 70Execution cost. Instruction body is 4450 tokens
- 85Steps. 29 steps, 2 vague phrases
- 100Running it twice. Mutating operations check current state
- 100Progress reporting. Reports progress
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)
- +3Description length 893: 120–800 characters recommended
- +3Output format is not stated: the model decides each time
- +1No license
- +2Single-language instructions
- +5Description quotes 2 example trigger phrases
- +4Structure: 17 headings
- +3Step-by-step instructions: 29 items
- +4Has examples (9 code blocks)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 85.