SKILLEMALL.ai
GitHub ↗ RU Sign in

AC browser-setup

Install and configure headless Chrome for OpenClaw browser tool in environments without root/sudo access (cloud containers, VPS, sandboxed hosts). Use when: (1) browser tool fails with No supported browser found, (2) Chrome crashes with Page crashed or missing library errors, (3) setting up browser automation on a fresh server or container, (4) user asks to install or fix the browser for OpenClaw. NOT for macOS/Windows desktops with Chrome already installed, or Chrome extension relay setup.

ClawHub Agent Skills author: huangdawei v1.0.0 2 files · 1 script body ≈ 1 420 tokens Open the sourceclawhub.ai↗ analyzed 3 d ago

As a process C 60/100 · Has gaps — weak spots: result and completion, inputs and preconditions, running it twice

ProcedurePlaywrightOperations and projectstype 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
96/100
safety, quality, tests
Safety 60%
99
Quality 40%
91
Run on models
none yet
Process rating
C
60/100
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

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 · 1

    ✓ No critical or high findings

    Medium and low: 1
    • low Dangerous commands cmd-privilege SKILL.md:73
      Privilege escalation / world-writable permissions (documentation of a security skill)
      --no-first-run --disable-setuid-sandbox \
      security skill

    Files scanned: 2. 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 60/100

    • 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. 3 mutating operations with no state check
    • 50When it triggers. No condition that starts the skill
    • 55Failures and branches. 1 branches
    • 100Tools and files. No external tools needed
    • 100Steps. 14 steps
    • 100Consistency. Name and required fields are in place
    • 100Execution cost. Instruction body is 1420 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
    • +3Output format is not stated: the model decides each time
    • +1No license
    • +2Single-language instructions
    • +4Description says when NOT to use the skill
    • +3Description length 495: enough signal without eating the budget
    • +4Structure: 15 headings
    • +3Step-by-step instructions: 14 items
    • +4Has examples (6 code blocks)
    • +3All 1 scripts are documented

    Quality base 70; lint remarks subtract, signals add up to 100. Result: 91.

    External checks

    ClawHub: clean
    This skill appears to do what it claims—install a user-local headless Chrome setup—but users should notice that it downloads external packages and recommends no-sandbox/CDP browser settings.
    LLM: benign (medium) · VirusTotal: · 29 May 2026