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.

39

Quality

38%

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-claude/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

33%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 structurally sectioned but substantively hollow: a truncated sentence, a broken Sharp Edges table whose issue cells all read 'Issue', no executable code, and no workflow. It tells Claude what categories matter without showing how to do anything.

Suggestions

Add copy-paste-ready Playwright/Puppeteer code for each Pattern (e.g. user-facing locators, auto-waiting) and fix the truncated 'For scraping, yo' sentence.

Rebuild the Sharp Edges table so each Issue cell names the actual problem and each Solution gives a concrete fix or code snippet instead of '# ...' comments.

Provide a short numbered workflow with a validation checkpoint (e.g. run test -> capture trace on failure -> fix locator -> re-run) so multi-step automation has explicit feedback loops.

DimensionReasoningScore

Conciseness

The body does not over-explain known concepts, but it repeats the frontmatter persona paragraph verbatim and pads space with placeholder rows, so it is mostly efficient yet could be tightened; not a 4 because the duplicated opener and broken table waste tokens.

3 / 5

Actionability

No executable code or commands appear anywhere; the 'Sharp Edges' solutions are comment-style hints ('# Use user-facing locators instead:', '# Use stealth plugins:') and patterns are mere titles, fitting minimal concrete guidance with high-level hints but no specific steps.

2 / 5

Workflow Clarity

There is no sequenced workflow at all — only categorized lists of patterns, anti-patterns, and edge cases — and no validation checkpoints for operations that can be destructive or batch-oriented, matching 'steps missing or incoherent; no validation'.

1 / 5

Progressive Disclosure

No bundle files exist, but the under-50-line body is broken into clearly labeled sections (Capabilities, Patterns, Anti-Patterns, Sharp Edges, Related Skills, When to Use), giving good organization with minor gaps such as the generic 'When to Use' filler.

4 / 5

Total

10

/

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 framing in second person rather than a capability statement: it describes an expert's background instead of what the skill does or when to invoke it. Trigger terms are strong, but missing actions and absent 'when' guidance cap its usefulness.

Suggestions

Rewrite in third person with concrete present-tense actions (e.g. 'Debugs flaky Playwright/Puppeteer tests, builds resilient web scrapers, and selects the right locator and wait strategies').

Add an explicit 'Use when...' clause naming natural triggers (e.g. 'Use when fixing flaky e2e tests, building web scrapers, or choosing between Selenium, Puppeteer, and Playwright').

Drop the credentialing language ('debugged thousands', 'run for years') which reads as fluff and adds no actionable signal.

DimensionReasoningScore

Specificity

The text lists credentials ('has debugged thousands of flaky tests and built scrapers that run for years without breaking') rather than concrete present-tense actions the skill performs, so the base of 2 (domain named, actions minimal) is reduced by 1 for second-person voice ('You are...'), landing at 1.

1 / 5

Completeness

It offers only a vague persona-based 'what' and entirely omits any 'when'/'Use when...' clause, matching the anchor for a vague what with no when; the missing-trigger cap of 3 is not reached because the what itself is non-actionable.

2 / 5

Trigger Term Quality

It includes natural terms users actually say — 'flaky tests', 'scrapers', and the tool names 'Selenium', 'Puppeteer', 'Playwright' — giving good keyword coverage, though phrases like 'web scraping' or 'e2e testing' are absent.

4 / 5

Distinctiveness Conflict Risk

Naming the specific toolchain (Selenium/Puppeteer/Playwright) carves a clear niche with only minor overlap risk against adjacent testing/coding skills, fitting 'mostly distinct'.

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.