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.

41

Quality

41%

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

40%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 a sparse skeleton of labels and one-liners with no executable examples, no real workflow, and a malformed Sharp Edges table whose solutions are comment hints rather than code. It is organized into clear sections but delivers little actionable guidance.

Suggestions

Add concrete, copy-paste-ready code examples for the named patterns (e.g. a Playwright user-facing locator + auto-wait snippet, an isolated context setup).

Replace the malformed Sharp Edges table with real issue/severity/solution rows containing actual code or commands, not '# comment' placeholders.

Provide an explicit workflow with validation checkpoints (write selector → run → on failure inspect trace → fix → re-run) instead of the vague 'When to Use' line.

Remove the duplicated persona opening and the truncated 'For scraping, yo' fragment.

DimensionReasoningScore

Conciseness

The body is mostly lean and does not over-explain concepts Claude already knows, but the opening persona paragraph duplicates the description and the malformed Sharp Edges table (every Issue cell says "Issue") is noise that could be trimmed.

3 / 5

Actionability

There is no executable code or concrete command anywhere; patterns are high-level one-liners ("Select elements the way users see them") and the table "solutions" are just # comment hints, leaving the specific steps to execute missing.

2 / 5

Workflow Clarity

Only a rough conceptual order appears in the "core insight"; there is no numbered sequence and no validation checkpoints for a domain where batch test runs and scraping routinely need validate/fix/retry loops.

2 / 5

Progressive Disclosure

No bundle files exist, so the single short body is appropriately split into clearly labeled sections (Capabilities, Patterns, Anti-Patterns, Sharp Edges) for a thin skill needing no external references; the malformed table is a minor organization gap.

4 / 5

Total

11

/

20

Passed

Description

42%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 persona-flavored and written in second person, naming the domain and tools but no concrete actions the skill performs and providing no trigger guidance. It reads as a character bio rather than a what/when skill summary.

Suggestions

Rewrite in third person stating concrete actions (e.g. "Writes and debugs Playwright/Puppeteer browser tests, builds resilient scrapers, and selects user-facing locators").

Add an explicit 'Use when...' clause with natural triggers (e.g. "Use when debugging flaky e2e tests, building web scrapers, or choosing between Selenium/Puppeteer/Playwright").

Drop the persona backstory to convert experience claims into actionable capability statements.

DimensionReasoningScore

Specificity

The description names the browser-automation domain and tools but frames them as a persona ("has debugged thousands of flaky tests", "built scrapers that run for years") rather than concrete skill actions; it is also second-person ("You are..."), which per the rubric reduces specificity by one from a base of 2.

1 / 5

Completeness

It gives only a vague persona-style "what" and has no "when"/"Use when..." clause at all, matching the anchor for a vague what with no when.

2 / 5

Trigger Term Quality

It includes natural terms users actually say — Playwright, Puppeteer, Selenium, flaky tests, scrapers — with good coverage, though some common variations (e2e, headless, selectors) are absent.

4 / 5

Distinctiveness Conflict Risk

Browser automation anchored to specific named tools (Playwright/Puppeteer/Selenium) carves a mostly distinct niche with only minor overlap against general testing skills.

4 / 5

Total

11

/

20

Passed

Validation

93%

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

Validation15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

frontmatter_unknown_keys

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

Warning

Total

15

/

16

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.