CtrlK
BlogDocsLog inGet started
Tessl Logo

windows-desktop-e2e

E2E testing for Windows native desktop apps (WPF, WinForms, Win32/MFC, Qt) using pywinauto and Windows UI Automation. Use when writing E2E tests for a Windows native desktop app with pywinauto or UI Automation.

68

Quality

83%

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

SKILL.md
Quality
Evals
Security

Quality

Content

78%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.

A highly actionable, well-organized body rich with executable examples and validation guidance for a complex multi-framework domain. Its main weakness is monolithic inlining — large code blocks and dedicated sections could be extracted into reference files for cleaner progressive disclosure.

Suggestions

Extract the full base_page.py / conftest.py / config.py listings into a scripts/ or references/ bundle and link to them from a concise Quick Start, keeping only key snippets inline.

Move the Qt-specific section and the Fallback Screenshot Mode into separate reference files (e.g. QT.md, SCREENSHOT_FALLBACK.md) referenced one level deep from the main body.

Split the three isolation tiers into a dedicated ISOLATION.md, summarizing the tier comparison table inline and pointing out for details.

DimensionReasoningScore

Conciseness

Largely lean and code/table-driven with most tokens earning their place across a genuinely complex domain, though the Core Concepts diagram/prose and a few explanatory passages could be trimmed; it is efficient rather than padded.

4 / 5

Actionability

Extensive copy-paste-ready, executable code (base_page.py, login_page.py, conftest.py, config.py, pytest.ini, CI workflow, Qt snippets, screenshot fallback) covering the common cases concretely.

5 / 5

Workflow Clarity

Content is well-sequenced (Setup → Testability → Page Objects → Locators → Waits → CI) with validation checkpoints present (verify UIA reachable, screenshot-on-failure, graceful-then-force kill), but it reads more as a topical reference than a single explicit validate→fix→retry workflow.

4 / 5

Progressive Disclosure

No bundle files exist and all ~880 lines are inlined into SKILL.md, including full code files and dedicated sections (Qt, fallback screenshot mode, three isolation tiers) that clearly belong in separate reference files; internal section structure is good, but nothing is split out one level deep.

3 / 5

Total

16

/

20

Passed

Description

87%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.

A strong, third-person description that clearly states both capability and activation triggers with concrete, natural keywords. It is comprehensive on framework/tool coverage, with only minor room to add action synonyms and a broader verb set.

DimensionReasoningScore

Specificity

Names the domain comprehensively — 'Windows native desktop apps (WPF, WinForms, Win32/MFC, Qt)' and the tools 'pywinauto and Windows UI Automation' — but the action is a single E2E testing verb rather than multiple distinct concrete actions, so it sits just below the comprehensive multi-action anchor.

4 / 5

Completeness

Explicitly answers both what ('E2E testing for Windows native desktop apps... using pywinauto and Windows UI Automation') and when with a concrete trigger phrase ('Use when writing E2E tests for a Windows native desktop app with pywinauto or UI Automation'), matching the top anchor.

5 / 5

Trigger Term Quality

Strong natural keywords a user would say ('E2E tests', 'Windows native desktop app', 'pywinauto', 'UI Automation', framework names), but missing common synonyms like 'end-to-end', 'GUI automation', or 'UI tests' that would push it to comprehensive coverage.

4 / 5

Distinctiveness Conflict Risk

Clear niche — Windows native desktop E2E with pywinauto/UIA — with distinct triggers and minimal overlap risk; the body even enumerates 'When NOT to Use' to disambiguate from web/mobile skills.

5 / 5

Total

18

/

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

skill_md_line_count

SKILL.md is long (889 lines); consider splitting into references/ and linking

Warning

metadata_version

'metadata.version' is missing

Warning

Total

14

/

16

Passed

Repository
affaan-m/ECC
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.