SKILLEMALL.ai

BF browser-driver

Attach to the user's OWN already-logged-in system browser over the Chrome DevTools Protocol (CDP) with Playwright, so automation reuses their existing session and avoids re-logging-in with 2FA. Use this ONLY when a fresh/headless browser won't do because the task needs the user's live login — e.g. 'do this in my browser', 'use my existing session/login', 'I'm already signed in, don't make me log in again', driving a console/dashboard behind 2FA while they watch. Do NOT use for ordinary browsing, scraping public pages, headless tests, or any automation that doesn't need their real session — use the agent's built-in browser tool / Playwright or chrome-devtools MCP / computer-use for those. Covers launching Chrome/Edge/Brave with a remote-debugging port, per-step one-shot Playwright scripts, screenshot-audited steps, shadow-DOM/overlay handling, handing control back at Touch ID/security-key/QR walls, one-time-secret capture, and cleanup. Own browser, own accounts, never to bypass auth.

ClawHub Hermes author: clarezoe v1.0.0 MIT-0 6 files body ≈ 1 384 tokens Open the sourceclawhub.ai analyzed 2 d ago

Attach to the user's OWN already-logged-in system browser over the Chrome DevTools Protocol (CDP) with Playwright, so automation reuses their existing session…

As a process F 35/100 · Will not run — References files that are not bundled: references/*

ProcedurePlaywrightAI and agentstype and topics are labelled automatically from the skill text
JSON
Technical rating
B
87/100
safety, quality, tests
Safety 60%
95
Quality 40%
74
Run on models
none yet
Process rating
F
35/100
Will not run
References files that are not bundled: references/*
Tools and files w 18
0
Result and completion w 14
0
Inputs and preconditions w 11
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.

Broad scope 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 asks for more than the task needs: broad tool access, credential environment variables, binaries. Every extra permission widens the damage from a mistake or a compromise.

For the author

Narrow allowed-tools and the variable list to the minimum; replace binaries with readable sources or scripts.

How to improve

  1. For Hermes the description must be one sentence under 60 characters; move the conditions to a "When to Use" section.
  2. The text references files that are not there: add them or drop the references.
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
  • medium Broad scope meta-broad-allowed-tools SKILL.md:1
    Broad tool permissions pre-approved: Bash
    allowed-tools: Read Write Edit Bash Glob Grep

Files scanned: 6. Evidence is masked. Grey chips explain why severity was lowered.

Against the Agent Skills spec

  • warning description-long-hermes description is 997 chars; the Hermes authoring standard requires ≤ 60 (one sentence, ending with a period)
  • warning missing-ref reference to a missing file: references/*

Process rating: all ten parameters 35/100

Will not run. References files that are not bundled: references/*
  • 0Tools and files. 1 referenced file(s) missing: references/*
  • 0Result and completion. Does not say what the result is
  • 0Inputs and preconditions. Does not say what the process needs to start
  • 0Failures and branches. Linear process with no failure handling
  • 30Running it twice. 1 mutating operations with no state check
  • 50When it triggers. No condition that starts the skill
  • 60Consistency. The Hermes dialect needs category and tags
  • 100Steps. 26 steps
  • 100Execution cost. Instruction body is 1384 tokens
  • 100Progress reporting. Reports progress

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
  • +3Description length 997: 120–800 characters recommended
  • +3Output format is not stated: the model decides each time
  • +4No input/output examples
  • +2Single-language instructions
  • +4Description says when NOT to use the skill
  • +4Structure: 7 headings
  • +3Step-by-step instructions: 26 items
  • +4Reference files are cited in the instructions (3 of 3)
  • +1License stated

Quality base 70; lint remarks subtract, signals add up to 100. Result: 74.

External checks

ClawHub: clean
This skill is high-impact because it controls a logged-in browser, but the artifacts clearly disclose that purpose and include meaningful scope and cleanup guidance.
LLM: benign (high) · VirusTotal: · 11 Jun 2026