SKILLEMALL.ai
GitHub ↗ RU Sign in

AC qa-browser-tester

Launch a real headless browser on the server and perform exhaustive end-to-end QA testing of a web application — clicking every button, filling every form, navigating every menu, and simulating a complete user journey. Use this skill whenever the user asks to "test the app", "check if everything works", "simulate a user", "run QA", "click through the site", or "browse the website automatically". Also trigger when the user says things like "בדוק את האתר", "תדמה משתמש", or "תבדוק שהכל עובד". Always use this skill — do not attempt browser automation without it, as it contains critical Docker-safe configuration required for Chromium to run on Linux servers.

ClawHub Agent Skills author: melnikdavid v1.0.0 MIT-0 4 files body ≈ 994 tokens Open the sourceclawhub.ai↗ analyzed 3 d ago

As a process C 63/100 · Has gaps — weak spots: result and completion, inputs and preconditions, running it twice

ProcedureDockerInfrastructuretype 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
A
92/100
safety, quality, tests
Safety 60%
91
Quality 40%
93
Run on models
none yet
Process rating
C
63/100
Has gaps
Result and completion w 14
0
Inputs and preconditions w 11
0
Progress reporting w 2
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

    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 · 5

    ✓ No critical or high findings

    Medium and low: 5
    • medium Dangerous commands cmd-privilege SKILL.md:90
      Privilege escalation / world-writable permissions
      --disable-setuid-sandbox
    • low Dangerous commands cmd-privilege references/docker-setup.md:24
      Privilege escalation / world-writable permissions (quoted — discussed, not commanded)
      "--disable-setuid-sandbox",# required when running as root
      quoted
    • low Dangerous commands cmd-privilege references/docker-setup.md:69
      Privilege escalation / world-writable permissions (documentation table row)
      | `No usable sandbox` | Add `--no-sandbox` and `--disable-setuid-sandbox` |
      table
    • low Dangerous commands cmd-privilege references/test-phases.md:25
      Privilege escalation / world-writable permissions (test fixture / example file; quoted — discussed, not commanded)
      "--disable-setuid-sandbox",
      fixturequoted
    • low Dangerous commands cmd-privilege SKILL.md:104
      Privilege escalation / world-writable permissions (quoted — discussed, not commanded)
      "--disable-setuid-sandbox",
      quoted

    Files scanned: 4. 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 63/100

    • 0Result and completion. Does not say what the result is
    • 0Inputs and preconditions. Does not say what the process needs to start
    • 0Progress reporting. Says nothing while it works
    • 30Running it twice. 1 mutating operations with no state check
    • 60Failures and branches. 2 branches
    • 70When it triggers. States when to use, but not when not to
    • 100Tools and files. No external tools needed
    • 100Steps. 4 steps
    • 100Consistency. Name and required fields are in place
    • 100Execution cost. Instruction body is 994 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

    • +4Description does not say when NOT to use the skill (false activations)
    • +3Output format is not stated: the model decides each time
    • +1No license
    • +2Single-language instructions
    • +5Description quotes 9 example trigger phrases
    • +3Description length 661: enough signal without eating the budget
    • +4Structure: 10 headings
    • +3Step-by-step instructions: 4 items
    • +4Has examples (10 code blocks)
    • +4Reference files are cited in the instructions (2 of 2)

    Quality base 70; lint remarks subtract, signals add up to 100. Result: 93.

    External checks

    ClawHub: suspicious
    This browser QA skill is useful, but it can broadly click, submit forms, create accounts, and expose screenshots if run against the wrong site.
    LLM: suspicious (high) · VirusTotal: · 29 May 2026