SKILLEMALL.ai
GitHub ↗ RU Sign in

AC camoufox-browse

Anti-detection browsing with a real Firefox (Camoufox) when Cloudflare, Datadome, or fingerprinting blocks the built-in browser tool. Node + Python entry points, session persistence, residential proxies, human-like input. Use for authorized access to sites that flag standard automation.

ClawHub Agent Skills author: zen v1.0.7 MIT-0 3 files body ≈ 4 575 tokens Open the sourceclawhub.ai↗ analyzed 2 d ago

Anti-detection browsing with a real Firefox (Camoufox) when Cloudflare, Datadome, or fingerprinting blocks the built-in browser tool.

As a process C 50/100 · Has gaps — weak spots: result and completion, inputs and preconditions, running it twice

AnalyzerCloudflarePlaywrightGitHubSoftware developmenttype 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
94/100
safety, quality, tests
Safety 60%
100
Quality 40%
84
Run on models
none yet
Process rating
C
50/100
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 · 0

    ✓ No critical or high findings

    Files scanned: 3. 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 50/100

    • 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. 4 mutating operations with no state check
    • 50Failures and branches. 0 branches, has a failure section
    • 60Tools and files. Uses tools (web, python, node) that frontmatter does not declare
    • 70When it triggers. States when to use, but not when not to
    • 70Execution cost. Instruction body is 4575 tokens
    • 85Steps. 18 steps, 1 vague phrases
    • 100Consistency. Name and required fields are in place
    • low 15 top-level sections: this looks like several domains in one skill

    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
    • +1No license
    • +2Single-language instructions
    • +3Description length 287: enough signal without eating the budget
    • +4Structure: 24 headings
    • +3Step-by-step instructions: 18 items
    • +4Has examples (24 code blocks)

    Quality base 70; lint remarks subtract, signals add up to 100. Result: 84.

    External checks

    ClawHub: clean
    This is a disclosed, documentation-only skill for user-directed anti-detection browser automation, with clear safety limits but meaningful dual-use risk.
    LLM: benign (high) · VirusTotal: · 9 Jul 2026