CtrlK
BlogDocsLog inGet started
Tessl Logo

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.

51

Quality

57%

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 ./skills/browser-automation/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

65%

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

This is a rich, highly actionable browser-automation reference with excellent executable examples and structured troubleshooting, but it is a long monolithic file with redundant coverage of the same lessons across Patterns, Sharp Edges, and Validation Checks. Splitting the troubleshooting and reference material into separate files and de-duplicating would materially improve it.

Suggestions

Move Sharp Edges and Validation Checks into separate reference files (e.g. SHARP_EDGES.md, CHECKS.md) and link to them from SKILL.md, turning the main file into a lean overview — this also improves progressive disclosure.

De-duplicate the auto-wait/waitForTimeout, user-facing-locator, and stealth guidance so each lesson lives in one place rather than recurring across Patterns, Sharp Edges, and Validation Checks.

Add a brief top-level workflow or decision flow (e.g. testing vs scraping vs agentic control → which pattern to reach for first) with a validation checkpoint, to give the catalog a coherent sequence.

DimensionReasoningScore

Conciseness

The body is mostly high-value executable code rather than basic-concept explanation, but the same lessons recur across sections — auto-wait/waitForTimeout, user-facing locators, and stealth each appear in Patterns, Sharp Edges, and Validation Checks — so it could be materially tightened.

2 / 3

Actionability

It provides abundant copy-paste-ready executable TypeScript for test isolation, shared auth, stealth, retry-with-backoff, network interception, popups, and iframes, with concrete 'When to use' guidance per pattern.

3 / 3

Workflow Clarity

Individual patterns carry 'When to use' notes and feedback loops (e.g. error-recovery retry with backoff) and Sharp Edges use a structured symptom/why/fix form, but there is no overarching sequenced workflow with explicit validation checkpoints — it is a reference catalog, not a guided process.

2 / 3

Progressive Disclosure

No bundle files exist and the entire ~1100-line skill lives in one SKILL.md; internal section organization is good, but content that should be split out (Sharp Edges, Validation Checks, detailed pattern code) is all inline rather than one level deep in referenced files.

2 / 3

Total

9

/

12

Passed

Description

50%

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 its domain and the technical levers that matter, but it reads as a conceptual framing rather than an action-and-trigger statement. It lacks a 'Use when...' clause and the framework trigger terms users most often say.

Suggestions

Add an explicit 'Use when...' clause listing concrete triggers (e.g. 'Use when the user mentions Playwright, Puppeteer, Selenium, headless browsers, web scraping, or e2e tests').

Replace abstract framing with concrete actions the skill performs (e.g. 'drives browsers with Playwright/Puppeteer, locates elements, waits reliably, and evades bot detection').

Include the framework names (Playwright, Puppeteer, Selenium) as trigger terms since those are what users actually say.

DimensionReasoningScore

Specificity

It names concrete domains ('web testing, scraping, and AI agent interactions') and technical topics ('selectors, waiting strategies, and anti-detection patterns'), but these are domains/topics rather than the multiple specific concrete actions the score-3 anchor requires (e.g. 'extract text, fill forms, merge documents').

2 / 3

Completeness

It answers 'what' (powers web testing/scraping/agent interactions) but has no 'Use when...' clause or equivalent explicit trigger guidance, which the rubric caps at 2.

2 / 3

Trigger Term Quality

It includes natural terms a user might say ('browser automation', 'web testing', 'scraping') but omits the common framework variations users actually invoke — Playwright, Puppeteer, Selenium, headless, e2e — so coverage is incomplete.

2 / 3

Distinctiveness Conflict Risk

'Browser automation' is a clear niche, but without explicit triggers the broad 'web testing' and 'scraping' framing could overlap with non-browser testing or scraping skills.

2 / 3

Total

8

/

12

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

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
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.