CtrlK
BlogDocsLog inGet started
Tessl Logo

browser-auth

Documents how to use Chrome DevTools MCP to navigate authenticated web pages, extract data (tokens, configuration values), take screenshots, and handle login flows. Use when you need to interact with Buildkite, AWS Console, or other authenticated web UIs via the Chrome browser. Triggers when users ask about "browser auth", "extract token from browser", "navigate to buildkite", "chrome mcp", or need to scrape data from authenticated pages.

72

Quality

87%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Critical

Do not install without reviewing

SKILL.md
Quality
Evals
Security

Quality

Content

75%Weight 40%Scale 1-5

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The body is well-structured and actionable, with concrete MCP tool calls, real config examples, and clear workflows including a login-state validation checkpoint. Main room for improvement is tightening repeated prose and making numbered pattern steps more literally executable.

Suggestions

Consolidate the login-page detection guidance (currently repeated in Step 1 and the 'Login Flow Handling' section) into one place to reduce token cost.

Convert the numbered pattern lists (Buildkite token, AWS Console) into literal copy-paste tool-call sequences mirroring the Step 1-5 format for stronger actionability.

Tighten the macOS --user-data-dir note and troubleshooting table entries to drop explanatory padding while keeping the actionable fix.

DimensionReasoningScore

Conciseness

Largely efficient — tight tables, no padding explaining what a browser or Chrome is — but includes a few explanatory passages (the macOS user-data-dir note, repeated login-detection guidance across sections) that could be trimmed. Not quite the lean 'every token earns its place' level 5.

4 / 5

Actionability

Provides concrete, executable tool calls (navigate_page, take_snapshot, evaluate_script, take_screenshot), real config JSON, and specific URLs. Some workflow bullets (e.g. the Buildkite token and AWS Console numbered lists) are prose-style steps rather than literal copy-paste commands, leaving minor gaps.

4 / 5

Workflow Clarity

Clear five-step sequence with an explicit validation checkpoint at Step 1 (check logged in → stop and ask the user) and a login-flow feedback loop (detect → screenshot → ask user → wait → re-navigate). Not quite level 5 because some checkpoints are implicit rather than spelled out as explicit pass/fail gates.

4 / 5

Progressive Disclosure

Single self-contained SKILL.md (~200 lines) with well-organized headers, tables, and no nested external references — appropriate structure with no bundle files needed. It is longer than a lean overview, keeping it just below the level-5 'clear overview' anchor.

4 / 5

Total

16

/

20

Passed

Description

100%Weight 40%Scale 1-5

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

The description is exemplary: third-person voice, concrete capabilities, explicit what/when guidance, and a rich set of natural trigger terms anchored to specific services. No vague fluff or over-claims.

DimensionReasoningScore

Specificity

Lists multiple concrete actions — 'navigate authenticated web pages, extract data (tokens, configuration values), take screenshots, and handle login flows' — giving comprehensive, specific coverage of capabilities rather than vague language.

5 / 5

Completeness

Explicitly answers both what (navigate/extract/screenshot/handle login flows) and when, with a 'Use when...' clause and a 'Triggers when...' clause providing concrete trigger phrases.

5 / 5

Trigger Term Quality

Comprehensive natural trigger phrasings a user would actually say: 'browser auth', 'extract token from browser', 'navigate to buildkite', 'chrome mcp', plus 'scrape data from authenticated pages', covering synonyms and service names.

5 / 5

Distinctiveness Conflict Risk

Clear niche — Chrome DevTools MCP interacting with authenticated web UIs — anchored by named services (Buildkite, AWS Console) and specific triggers, minimizing overlap with other skills.

5 / 5

Total

20

/

20

Passed

Validation

100%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
mock-server/mockserver-monorepo
Reviewed

Table of Contents

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.