AB nstbrowser-ai-agent
Browser automation CLI with Nstbrowser integration for AI agents. Use when the user needs advanced browser fingerprinting, profile management, proxy configuration, batch operations on multiple browser profiles, or cursor-based pagination for large datasets. Triggers include requests to "use NST profile", "configure proxy for profile", "manage browser profiles", "batch update profiles", "start multiple browsers", "list profiles with pagination", or any task requiring Nstbrowser's anti-detection features.
As a process B 75/100 · Nearly there — weak spots: result and completion
How to improve
- The SKILL.md body is over 5,000 tokens: move reference detail into references/ and load it when needed.
- 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: 12. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
body-longSKILL.md body ≈ 5962 tokens (recommended < 5000); move details to references/
Process rating: all ten parameters 75/100
- 0Result and completion. Does not say what the result is
- 70When it triggers. States when to use, but not when not to
- 70Inputs and preconditions. Inputs and preconditions are listed
- 70Execution cost. Instruction body is 5962 tokens
- 85Steps. 129 steps, 1 vague phrases
- 100Tools and files. Tools declared in frontmatter
- 100Failures and branches. 6 branches, has a failure section
- 100Consistency. Name and required fields are in place
- 100Running it twice. Mutating operations check current state
- 100Progress reporting. Reports progress
- low 16 top-level sections: this looks like several domains in one skill
- low The response is described with custom markup (27 tags): a typed call is more reliable
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
- -2localhost URLs: will not work for another user
- +1No license
- +2Single-language instructions
- +5Description quotes 6 example trigger phrases
- +3Description length 508: enough signal without eating the budget
- +4Structure: 58 headings
- +3Step-by-step instructions: 129 items
- +4Has examples (57 code blocks)
- +4Reference files are cited in the instructions (5 of 5)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 81.