CtrlK
BlogDocsLog inGet started
Tessl Logo

browser-automation

Use when the user asks to automate browser tasks, scrape websites, fill forms, capture screenshots, extract structured data from web pages, or build web automation workflows. NOT for testing — use playwright-pro for that.

67

Quality

81%

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

The canonical home for this skill is browser-automation in alirezarezvani/claude-skills

SKILL.md
Quality
Evals
Security

Quality

Content

71%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-organized and actionable with concrete workflow code, but two issues hold it back: referenced bundle files and scripts are missing (broken progressive disclosure), and the batch workflows lack integrated validate-fix-retry feedback loops. Conciseness is good with minor hype/explainer padding.

Suggestions

Add the referenced files (references/data_extraction_recipes.md, references/playwright_browser_api.md, references/anti_detection_patterns.py) and the scripts (scraping_toolkit.py, form_automation_builder.py, anti_detection_checker.py) so the progressive-disclosure links resolve.

Integrate an explicit validate->fix->retry feedback loop into the batch scraping workflows (e.g., on extraction failure or 429: log, back off, retry) rather than only describing retry in a separate competency section.

Define or inline the helper functions referenced by the workflow examples (extract_listings, human_delay, login, fill_step_1/2) so the code is copy-paste executable, and drop the 'POWERFUL' hype word from the title.

DimensionReasoningScore

Conciseness

Dense, information-rich body that mostly assumes Playwright competence (concise competency bullets with inline code), but includes some trimmable padding — the 'POWERFUL' hype word in the title and the 'Why Playwright over Selenium or Puppeteer' comparison section. Fits the score-4 anchor (efficient with minor over-explanation) rather than the fully-lean score-5 anchor.

4 / 5

Actionability

Provides three concrete, mostly-executable workflow functions plus specific API calls and a tools table with flags, but the examples reference undefined helpers (extract_listings, human_delay, login, fill_step_1) so they are not fully copy-paste ready. Matches score-4 (mostly executable, minor gaps) rather than score-5 (fully copy-paste ready).

4 / 5

Workflow Clarity

Three workflows have clear numbered sequences with some checkpoints (validate extracted data for nulls/types, deduplicate results, check Next-button state, write incrementally), and retry/backoff is documented in a dedicated competency. It stays at 4 rather than 5 because the validate->fix->retry feedback loop is documented separately rather than integrated into the batch workflows, leaving minor validation gaps for a batch operation.

4 / 5

Progressive Disclosure

Structure and signaling are good — one-level-deep references to data_extraction_recipes.md, playwright_browser_api.md, and anti_detection_patterns.md are clearly linked — but none of the referenced files or scripts actually exist in the bundle, so every reference is a broken link. Scored at 3 rather than 4-5 because the disclosure navigation does not resolve to any real material.

3 / 5

Total

15

/

20

Passed

Description

92%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 strong: it explicitly states both capabilities and trigger conditions, uses natural user language, and disambiguates from the related testing skill. The only minor gap is a few missing synonyms (crawl, web scraping) in trigger term coverage.

DimensionReasoningScore

Specificity

Lists multiple concrete actions — 'automate browser tasks, scrape websites, fill forms, capture screenshots, extract structured data from web pages, or build web automation workflows' — giving comprehensive coverage of the skill's capabilities. It exceeds the score-4 anchor (which allows minor gaps) with no meaningful actions omitted.

5 / 5

Completeness

Explicitly answers both 'what' (the enumerated automation actions) and 'when' via the 'Use when the user asks to...' trigger clause, plus a negative boundary ('NOT for testing — use playwright-pro for that'). This matches the score-5 anchor of clearly answering what AND when with concrete trigger phrases.

5 / 5

Trigger Term Quality

Strong natural keywords users would say ('scrape websites', 'fill forms', 'capture screenshots', 'automate browser tasks') with some synonym coverage, but missing common variations like 'crawl'/'crawling', 'web scraping', or 'headless browser'. Solid coverage with a few natural terms absent, matching the score-4 anchor rather than the comprehensive score-5 anchor.

4 / 5

Distinctiveness Conflict Risk

Clear niche (browser automation/scraping) with an explicit disambiguation against the sibling testing skill ('NOT for testing — use playwright-pro for that'), minimizing conflict risk. Fits the score-5 anchor of a clear niche with distinct triggers and minimal conflict risk.

5 / 5

Total

19

/

20

Passed

Validation

87%

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

Validation14 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

relative_links

Relative link issues: 8 missing

Warning

referenced_paths_exist

Referenced path issues: 8 missing

Warning

Total

14

/

16

Passed

Repository
alirezarezvani/claude-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.