CtrlK
BlogDocsLog inGet started
Tessl Logo

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

45

Quality

48%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./plugins/AI-Agents-Safe-Coding-Skills-claude/skills/awt-e2e-testing/SKILL.md

The canonical home for this skill is awt-e2e-testing in administrakt0r/AI-Agents-Safe-Coding-Skills

SKILL.md
Quality
Evals
Security

Quality

Content

30%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 reads as a marketing overview rather than operational guidance: it lists features and links but provides almost no executable instruction or workflow. It needs concrete examples and a sequenced process to be actionable.

Suggestions

Add a minimal runnable example: a short YAML scenario and the command to execute it with Playwright.

Provide a sequenced workflow — design scenario → run → diagnose failure (with the investigation checklist) → record to learning DB — with a validation/verification checkpoint before recording.

Replace the marketing lines and the repeated feature list with pointers to where detailed usage lives, or move detail into reference files and link to them.

DimensionReasoningScore

Conciseness

The body is short and does not over-explain known concepts, but it includes marketing padding ('eyes and hands for AI coding tools', 'Built with the help of AI coding tools ...', 'Actively developed by a solo developer at AILoopLab. Feedback welcome!') and restates the description's feature list.

3 / 5

Actionability

The only executable guidance is the install command; there is no concrete code, YAML scenario example, or specific steps for designing and running tests, leaving Claude with high-level hints only.

2 / 5

Workflow Clarity

No multi-step process is described at all — 'What works now' is a feature list, not a sequence — and there are no validation checkpoints for the design-YAML → execute → diagnose → learn flow this skill implies.

1 / 5

Progressive Disclosure

Content is organized into clean sections and is short, but there are no in-skill references to detailed material (no reference bundle files exist; only external GitHub/demo URLs), so a complex tool is reduced to a flat overview.

3 / 5

Total

9

/

20

Passed

Description

66%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 concretely names the domain and several specific capabilities with an install command, giving strong specificity and decent trigger terms. Its main weakness is the absence of an explicit 'Use when' trigger clause, which caps completeness at 3.

Suggestions

Add an explicit 'Use when ...' clause naming natural trigger phrases (e.g., 'Use when you need to run end-to-end browser tests, automate web UI testing, or diagnose web app failures').

Include common synonyms users say — 'end-to-end testing', 'browser testing', 'UI testing', 'automated web testing' — to broaden trigger coverage.

Lead with the concrete actions Claude performs rather than the marketing metaphor 'eyes and hands for AI coding tools'.

DimensionReasoningScore

Specificity

Lists several concrete capabilities — 'Declarative YAML scenarios, Playwright execution, visual matching (OpenCV + OCR), platform auto-detection (Flutter/React/Vue), learning DB' — plus an executable install command; minor gaps in that these are tool features rather than Claude-facing verbs.

4 / 5

Completeness

The 'what' is clear and specific, but there is no 'Use when...' clause or equivalent explicit trigger guidance, so per the rubric completeness is capped at 3 with only a weakly implied 'when'.

3 / 5

Trigger Term Quality

Good natural coverage with 'E2E web testing', 'web applications', 'Playwright', and 'test scenarios'; a few common synonyms like 'end-to-end testing', 'browser testing', or 'UI testing' are missing.

4 / 5

Distinctiveness Conflict Risk

The E2E web testing niche combined with Playwright/YAML/visual-matching is mostly distinct, with only minor overlap risk against generic Playwright or testing skills.

4 / 5

Total

15

/

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.