SKILLEMALL.ai
GitHub ↗ RU Sign in

BC browser-ladder

Climb the browser ladder — start free, escalate only when needed. L1 (fetch) → L2 (local Playwright) → L3 (BrowserCat) → L4 (Browserless.io for CAPTCHA/bot bypass).

ClawHub Agent Skills author: ktpriyatham v1.0.0 4 files · 2 scripts body ≈ 880 tokens Open the sourceclawhub.ai↗ analyzed 3 d ago

As a process C 51/100 · Has gaps — weak spots: result and completion, when it triggers, inputs and preconditions

ProcedurePlaywrightInfrastructuretype 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
B
89/100
safety, quality, tests
Safety 60%
94
Quality 40%
81
Run on models
none yet
Process rating
C
51/100
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 · 6

    ✓ No critical or high findings

    Medium and low: 6
    • low Exfiltration exfil-secret-in-url scripts/browse.sh:126
      Credential passed in a URL query string (normal for some APIs — verify the host is the intended service) (placeholder value)
      curl -s -X POST "https://production-sfo.browserless.io/screenshot?token=…" \
      placeholder
    • low Exfiltration net-credential-use scripts/browse.sh:126
      Credential used in a network call (verify the destination is the intended service) (the skill's own vendor host)
      curl -s -X POST "https://production-sfo.browserless.io/screenshot?token=…" \
      vendor-host
    • low Exfiltration exfil-secret-in-url scripts/browse.sh:131
      Credential passed in a URL query string (normal for some APIs — verify the host is the intended service) (placeholder value)
      curl -s -X POST "https://production-sfo.browserless.io/pdf?token=…" \
      placeholder
    • low Exfiltration net-credential-use scripts/browse.sh:131
      Credential used in a network call (verify the destination is the intended service) (the skill's own vendor host)
      curl -s -X POST "https://production-sfo.browserless.io/pdf?token=…" \
      vendor-host
    • low Exfiltration exfil-secret-in-url scripts/browse.sh:136
      Credential passed in a URL query string (normal for some APIs — verify the host is the intended service) (placeholder value)
      curl -s -X POST "https://production-sfo.browserless.io/content?token=…" \
      placeholder
    • low Exfiltration net-credential-use scripts/browse.sh:136
      Credential used in a network call (verify the destination is the intended service) (the skill's own vendor host)
      curl -s -X POST "https://production-sfo.browserless.io/content?token=…" \
      vendor-host

    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 51/100

    • 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
    • 20When it triggers. No condition that starts the skill
    • 50Failures and branches. 0 branches, has a failure section
    • 60Tools and files. Uses tools (web) that frontmatter does not declare
    • 100Steps. 4 steps
    • 100Consistency. Name and required fields are in place
    • 100Execution cost. Instruction body is 880 tokens
    • 100Running it twice. No mutating operations

    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 2 scripts are never mentioned in SKILL.md
    • +1No license
    • +2Single-language instructions
    • +3Description length 164: enough signal without eating the budget
    • +4Structure: 12 headings
    • +3Step-by-step instructions: 4 items
    • +4Has examples (8 code blocks)

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

    External checks

    ClawHub: suspicious
    This browser automation skill mostly does what it says, but it normalizes CAPTCHA/bot bypass, sends browsing tasks to third-party services, and runs mutable external tooling without enough safeguards.
    LLM: suspicious (high) · VirusTotal: benign · 10 Sept 2026