SKILLEMALL.ai
GitHub ↗ RU Sign in

DC steel-browser

Control cloud browser sessions via Steel.dev for web automation and computer-use agents. Use when you need to browse the web, fill forms, click elements, take screenshots, scrape content, or build browser automation loops. Uses Playwright selectors (CSS/text/aria) instead of pixel coordinates — more reliable than e2b-desktop for pure web tasks. Supports residential proxies and CAPTCHA solving.

Not recommendedlow grade D
modbender/skill-library-mcp Agent Skills author: modbender MIT 18 files · 16 scripts body ≈ 898 tokens Open the sourcegithub.com↗ analyzed 2 d ago

Control cloud browser sessions via Steel.dev for web automation and computer-use agents. Use when you need to browse the web, fill forms, click elements, take…

As a process C 56/100 · Has gaps — weak spots: result and completion, when it triggers, running it twice

GeneratorPlaywrightAI and agentstype 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
D
53/100
safety, quality, tests
Safety 60%
34
Quality 40%
81
Run on models
none yet
Process rating
C
56/100
Has gaps
Result and completion w 14
0
Progress reporting w 2
0
When it triggers w 12
20
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 · 14

    ✓ No critical or high findings

    Medium and low: 14
    • medium Dangerous commands cmd-eval-dynamic scripts/click_coords.sh:25
      Dynamic code execution from decoded/untrusted input
      exec(open(HELPER).read())
    • medium Dangerous commands cmd-eval-dynamic scripts/click.sh:18
      Dynamic code execution from decoded/untrusted input
      exec(open(HELPER).read())
    • medium Dangerous commands cmd-eval-dynamic scripts/eval_js.sh:16
      Dynamic code execution from decoded/untrusted input
      exec(open(HELPER).read())
    • medium Dangerous commands cmd-eval-dynamic scripts/get_content.sh:24
      Dynamic code execution from decoded/untrusted input
      exec(open(HELPER).read())
    • medium Dangerous commands cmd-eval-dynamic scripts/get_url.sh:12
      Dynamic code execution from decoded/untrusted input
      exec(open(HELPER).read())
    • medium Dangerous commands cmd-eval-dynamic scripts/hover.sh:13
      Dynamic code execution from decoded/untrusted input
      exec(open(HELPER).read())
    • medium Dangerous commands cmd-eval-dynamic scripts/navigate.sh:15
      Dynamic code execution from decoded/untrusted input
      exec(open(HELPER).read())
    • medium Dangerous commands cmd-eval-dynamic scripts/press_key.sh:19
      Dynamic code execution from decoded/untrusted input
      exec(open(HELPER).read())
    • medium Dangerous commands cmd-eval-dynamic scripts/screenshot.sh:23
      Dynamic code execution from decoded/untrusted input
      exec(open(HELPER).read())
    • medium Dangerous commands cmd-eval-dynamic scripts/scroll.sh:15
      Dynamic code execution from decoded/untrusted input
      exec(open(HELPER).read())
    • medium Dangerous commands cmd-eval-dynamic scripts/select.sh:15
      Dynamic code execution from decoded/untrusted input
      exec(open(HELPER).read())
    • medium Dangerous commands cmd-eval-dynamic scripts/type.sh:15
      Dynamic code execution from decoded/untrusted input
      exec(open(HELPER).read())
    • medium Dangerous commands cmd-eval-dynamic scripts/wait_for.sh:15
      Dynamic code execution from decoded/untrusted input
      exec(open(HELPER).read())
    • low Dangerous commands cmd-eval-dynamic scripts/_connect.py:5
      Dynamic code execution from decoded/untrusted input (quoted — discussed, not commanded)
      exec(open(HELPER).read())
      quoted

    Files scanned: 18. 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 56/100

    • 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. 2 mutating operations with no state check
    • 50Failures and branches. 0 branches, has a failure section
    • 60Tools and files. Uses tools (bash, python) that frontmatter does not declare
    • 70Inputs and preconditions. Inputs and preconditions are listed
    • 100Steps. 4 steps
    • 100Consistency. Name and required fields are in place
    • 100Execution cost. Instruction body is 898 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)
    • +3Output format is not stated: the model decides each time
    • -31 of 17 scripts are never mentioned in SKILL.md
    • +1No license
    • +2Single-language instructions
    • +3Description length 396: enough signal without eating the budget
    • +4Structure: 7 headings
    • +3Step-by-step instructions: 4 items
    • +4Has examples (4 code blocks)

    Quality base 70; lint remarks subtract, signals add up to 100. Result: 81.