browser-automation

Browser automation powers web testing, scraping, and AI agent interactions. The difference between a flaky script and a reliable system comes down to understanding selectors, waiting strategies, and anti-detection patterns.

Quality

56%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Medium

Suggest reviewing before use

Fix and improve this skill with Tessl

tessl review fix ./skills/browser-automation/SKILL.md

Quality

Content

65%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 highly actionable with comprehensive executable examples and useful sharp-edge/validation guidance, but it is monolithic and verbose with notable duplication between the Patterns and Sharp Edges sections and no progressive disclosure into separate reference files.

Suggestions

Move the large code catalogs (Patterns, Sharp Edges, Validation Checks) into reference files under references/ and keep SKILL.md as a concise overview with one-level-deep links.

De-duplicate guidance that appears in both Patterns and Sharp Edges (waitForTimeout, stealth, CSS selectors) by cross-referencing instead of restating.

Trim concept explanations Claude already knows (e.g., what headless/headed means, what bot detection checks) to reduce token cost.

Dimension	Reasoning	Score
Conciseness	Content is dense and actionable rather than padded fluff, but at ~1100 lines it repeats material across Patterns and Sharp Edges (e.g., waitForTimeout, stealth, CSS selectors appear twice) and explains some concepts Claude already knows; could be tightened.	3 / 5
Actionability	Provides extensive copy-paste-ready, executable code for Playwright and Puppeteer covering locators, auto-wait, stealth, error recovery, parallelism, and network interception across the common cases.	5 / 5
Workflow Clarity	Organized as a pattern catalog with "When to use" tags rather than a single sequenced workflow; validation exists via the Validation Checks section and error-recovery retries, but checkpoints are implicit and there is no unified end-to-end process.	3 / 5
Progressive Disclosure	Section headers are well organized (Principles, Tooling, Patterns, Sharp Edges, Validation Checks), but no bundle files exist and ~1100 lines of code reference are inlined in SKILL.md with no one-level-deep references to split the material.	3 / 5
	Total	14 / 20 Passed

Description

48%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 clearly identifies the skill's domain and distinguishing focus on selectors, waiting, and anti-detection, but it is conceptual rather than action-oriented and omits an explicit "Use when" trigger clause plus common tool-name keywords.

Suggestions

Add an explicit "Use when..." clause listing concrete triggers (e.g., Playwright, Puppeteer, e2e tests, headless browsers, web scraping).

Replace conceptual topics with concrete actions the skill performs (e.g., "drive browsers to click, fill forms, extract data, and run end-to-end tests").

Include common tool/framework keywords (Playwright, Puppeteer, Selenium, headless) so the description matches natural user phrasing.

Dimension	Reasoning	Score
Specificity	Names the domains ("web testing, scraping, and AI agent interactions") and topics ("selectors, waiting strategies, and anti-detection patterns") but describes concepts rather than concrete actions like clicking, filling forms, or extracting text.	2 / 5
Completeness	Provides a clear "what" (powers web testing, scraping, AI agent interactions) but lacks any "Use when..." trigger clause; per the rubric, a missing explicit trigger guidance caps completeness at 3.	3 / 5
Trigger Term Quality	Contains natural terms users would say ("browser automation", "web testing", "scraping") but omits the most common tool-trigger synonyms users actually mention, such as Playwright, Puppeteer, e2e, or headless.	3 / 5
Distinctiveness Conflict Risk	"Browser automation" carves a clear niche distinct from general testing or scraping skills, with only minor overlap risk against related testing/scraping skills.	4 / 5
	Total	12 / 20 Passed

Validation

87%

Warnings & errors only

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

Validation — 14 / 16 Passed

Validation for skill structure

Criteria	Description	Result
skill_md_line_count	SKILL.md is long (1117 lines); consider splitting into references/ and linking	Warning
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	14 / 16 Passed

Repository: sickn33/antigravity-awesome-skills
Path: skills/browser-automation/SKILL.md
Commit: 1f67c44

Reviewed: 1 day ago

Table of Contents

Discovery Implementation Validation

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.