awt-e2e-testing

AI-powered E2E web testing — eyes and hands for AI coding tools. Declarative YAML scenarios, Playwright execution, visual matching (OpenCV + OCR), platform auto-detection (Flutter/React/Vue), learning DB. Install: npx skills add ksgisang/awt-skill --skill awt -g

Quality

34%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./skills/awt-e2e-testing/SKILL.md

Quality

Content

18%Scale 1-5

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

This skill content reads like a project README or marketing page rather than an actionable skill file. It lists features and links but provides zero concrete instructions, examples, or workflows for Claude to follow. To function as a skill, it needs YAML scenario examples, CLI commands, configuration steps, and error-handling guidance.

Suggestions

Add a concrete quick-start workflow: e.g., 1) detect platform, 2) write a YAML scenario (with a complete example), 3) run `npx awt run scenario.yaml`, 4) interpret results.

Include at least one complete, copy-paste-ready YAML test scenario with expected output so Claude knows the exact format.

Add CLI commands for common operations (running tests, querying the learning DB, configuring providers) with concrete examples.

Remove promotional/marketing language ('Actively developed by a solo developer', 'Feedback welcome!') and replace with actionable content.

Dimension	Reasoning	Score
Conciseness	The content is relatively short but includes marketing-style language ('gives AI coding tools the ability to see and interact'), promotional lines ('Built with the help of AI coding tools'), and feature bullet points that read more like a README than actionable skill instructions. Some tokens are wasted on non-instructional content.	3 / 5
Actionability	There is no concrete guidance on how to actually use AWT — no YAML scenario examples, no commands to run tests, no code snippets, no configuration steps. The content only describes what AWT does at a high level without instructing Claude how to use it.	1 / 5
Workflow Clarity	There is no workflow described at all. No steps for creating scenarios, running tests, interpreting results, or handling failures. The content is purely descriptive with no sequenced process.	1 / 5
Progressive Disclosure	There are external links to GitHub repos and a cloud demo, but no bundle files are provided and no structured references to detailed documentation (e.g., YAML schema docs, configuration guides, API references). The skill body itself contains no actionable content to organize, and the links point to external sites rather than companion files.	2 / 5
	Total	7 / 20 Passed

Description

50%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 packs in many technical features and framework names, giving a sense of the tool's capabilities, but reads more like a marketing tagline than a skill description. It lacks a 'Use when...' clause entirely, and the installation instructions consume valuable space. The metaphorical language ('eyes and hands for AI coding tools') adds flair but not clarity for skill selection.

Suggestions

Add an explicit 'Use when...' clause with natural trigger phrases like 'Use when the user needs to write, run, or debug end-to-end web tests, browser automation, UI testing, or visual regression testing.'

Replace the installation instructions and marketing tagline ('eyes and hands for AI coding tools') with concrete user-facing actions like 'Creates and runs automated browser tests, validates visual UI elements, generates test scenarios from descriptions.'

Include common synonyms and natural phrases users would say: 'end-to-end testing', 'browser testing', 'UI testing', 'automated tests', 'test automation', 'visual regression'.

Dimension	Reasoning	Score
Specificity	Lists several specific capabilities: declarative YAML scenarios, Playwright execution, visual matching (OpenCV + OCR), platform auto-detection (Flutter/React/Vue), learning DB. However, the actual actions (what the user gets done) are somewhat obscured by feature-listing rather than describing concrete user-facing actions like 'write tests', 'run tests', 'validate UI elements'.	4 / 5
Completeness	The 'what' is present but somewhat unclear — it describes features/technologies more than user-facing capabilities. There is no 'when' clause at all — no 'Use when...' or equivalent trigger guidance. The inclusion of installation instructions wastes space that could be used for trigger guidance. Per rubric rules, missing 'Use when...' caps completeness at 3, and the weak 'what' brings it to 2.	2 / 5
Trigger Term Quality	Includes some relevant terms like 'E2E', 'web testing', 'Playwright', 'YAML', 'Flutter/React/Vue', and 'OCR'. However, it misses common natural user phrases like 'end-to-end testing', 'browser testing', 'UI testing', 'automated testing', 'test automation', or 'visual regression testing' that users would naturally say.	3 / 5
Distinctiveness Conflict Risk	The combination of 'E2E web testing', 'Playwright', 'visual matching', and 'YAML scenarios' creates a fairly distinct niche. Minor overlap risk with general testing or Playwright-specific skills, but the visual matching and platform auto-detection aspects help differentiate it.	4 / 5
	Total	13 / 20 Passed

Validation

90%

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 — 10 / 11 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	10 / 11 Passed

Repository: administrakt0r/AI-Agents-Safe-Coding-Skills
Path: skills/awt-e2e-testing/SKILL.md
Commit: debb2ec

Reviewed: 13 hours 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.