CtrlK
BlogDocsLog inGet started
Tessl Logo

browser-automation

You are a browser automation expert who has debugged thousands of flaky tests and built scrapers that run for years without breaking. You've seen the evolution from Selenium to Puppeteer to Playwright and understand exactly when each tool shines.

22

Quality

11%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./plugins/AI-Agents-Safe-Coding-Skills/skills/browser-automation/SKILL.md

The canonical home for this skill is browser-automation in sickn33/agentic-awesome-skills

SKILL.md
Quality
Evals
Security

Quality

Content

0%Scale 1-3

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

This skill is essentially a skeleton with section headers but almost no substantive content. It contains truncated text ('For scraping, yo'), placeholder values in the Sharp Edges table (repeated 'Issue' entries), no executable code examples, and no concrete workflows. The persona description wastes tokens on information Claude doesn't need, while the actual instructional content is absent.

Suggestions

Add complete, executable Playwright code examples for each pattern (e.g., show actual `page.getByRole()` usage for User-Facing Locator Pattern, actual test isolation setup with `browser.newContext()`).

Replace the placeholder Sharp Edges table with real issues and real code solutions (e.g., 'Flaky selectors' → specific code showing the wrong way and the right way).

Add a concrete multi-step workflow for a common task like 'Setting up a Playwright scraper' with numbered steps, commands, and validation checkpoints.

Remove the persona description and capabilities list, and replace with actionable quick-start content showing a minimal working example that Claude can immediately use.

DimensionReasoningScore

Conciseness

The content includes a persona description that Claude doesn't need, explains obvious concepts ('Most automation failures come from three sources'), and has placeholder/broken content ('For scraping, yo' is truncated). The Sharp Edges table has placeholder 'Issue' text repeated without actual content. Much of the file is filler.

1 / 3

Actionability

There is zero executable code, no concrete commands, no specific examples. Patterns like 'Auto-Wait Pattern' and 'User-Facing Locator Pattern' are named but never demonstrated with actual code. The Sharp Edges table has solution comments but no actual implementation. Everything is vague direction rather than concrete instruction.

1 / 3

Workflow Clarity

There are no sequenced steps, no workflows, no validation checkpoints. The patterns section names concepts but never walks through how to implement them. For a skill involving browser automation and testing, there should be clear multi-step workflows with verification steps, but none exist.

1 / 3

Progressive Disclosure

The content is a flat list of section headers with minimal substance under each. There are no references to detailed files, no navigation structure, and the content appears truncated mid-sentence. The 'Related Skills' and 'When to Use' sections add no value. The structure exists but contains no meaningful content to disclose.

1 / 3

Total

4

/

12

Passed

Description

22%Scale 1-3

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

This description reads as a persona/backstory rather than a functional skill description. It uses first-person-adjacent framing ('You are...', 'You've seen...') instead of third-person action-oriented language, lists no concrete capabilities, and entirely lacks a 'Use when...' clause. The tool names provide some trigger value but the description fails to communicate what specific tasks this skill performs or when it should be selected.

Suggestions

Replace the persona narrative with concrete actions in third person, e.g., 'Writes and debugs browser automation scripts using Playwright, Puppeteer, or Selenium. Builds web scrapers, fixes flaky end-to-end tests, and automates browser interactions.'

Add an explicit 'Use when...' clause, e.g., 'Use when the user needs to automate browser tasks, write E2E tests, build web scrapers, debug flaky test suites, or work with Playwright/Puppeteer/Selenium.'

Include natural trigger terms users would say, such as 'web scraping', 'E2E testing', 'headless browser', 'page automation', 'crawling', and file extensions or framework names.

DimensionReasoningScore

Specificity

The description uses vague language like 'browser automation expert' and 'debugged thousands of flaky tests' without listing any concrete actions the skill performs. It mentions tool names (Selenium, Puppeteer, Playwright) but doesn't describe what specific tasks it can do with them.

1 / 3

Completeness

The description partially addresses 'what' (browser automation, debugging flaky tests, building scrapers) but in vague terms, and completely lacks any 'when' clause or explicit trigger guidance. Per the rubric, a missing 'Use when...' clause caps completeness at 2, and the weak 'what' brings it to 1.

1 / 3

Trigger Term Quality

It includes some relevant keywords like 'browser automation', 'Selenium', 'Puppeteer', 'Playwright', 'scrapers', and 'flaky tests' that users might mention. However, it misses common variations like 'web scraping', 'end-to-end testing', 'E2E', 'headless browser', 'DOM', or 'crawling'.

2 / 3

Distinctiveness Conflict Risk

The mention of specific tools (Selenium, Puppeteer, Playwright) and the browser automation domain provides some distinctiveness, but the broad scope covering both testing and scraping could overlap with dedicated testing skills or web scraping skills.

2 / 3

Total

6

/

12

Passed

Validation

90%

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

Validation10 / 11 Passed

Validation for skill structure

CriteriaDescriptionResult

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

Total

10

/

11

Passed

Repository
administrakt0r/AI-Agents-Safe-Coding-Skills
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.