CtrlK
BlogDocsLog inGet started
Tessl Logo

verify-tests-fail-without-fix

Verifies tests catch the bug. Auto-detects test type (UI tests, device tests, unit tests) and dispatches to the appropriate runner. Supports two modes - verify failure only (test creation) or full verification (test + fix validation).

60

Quality

70%

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 ./.github/skills/verify-tests-fail-without-fix/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

81%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 a clear validated workflow and a clean one-level reference to the real verification script. Its main weakness is verbosity from duplicated command examples, decorative ASCII output boxes, and a 'What It Does' section that restates the workflow.

Suggestions

Remove the duplicated command examples in Mode 1 and Mode 2 since Step 2 already constructs the command; keep only the mode-specific flag deltas.

Replace or trim the ASCII-art output boxes in 'Expected Output'; a one-line description of each marker is sufficient.

Consider folding 'What It Does' into the existing Workflow steps to avoid restating the same sequence twice.

DimensionReasoningScore

Conciseness

Mostly efficient but padded: the Mode 1/2 command examples duplicate Step 2, the ASCII-art output boxes are decorative, and 'What It Does' re-narrates the workflow already covered in the steps.

3 / 5

Actionability

Fully executable copy-paste PowerShell commands per mode, a real referenced script (verify-tests-fail.ps1), a troubleshooting table, and documented optional parameters covering the common cases.

5 / 5

Workflow Clarity

A clear 4-step sequence with explicit result interpretation, feedback loops (Blocked status, 'do not manually mutate the worktree'), and validation for the destructive git-revert operations.

5 / 5

Progressive Disclosure

Well-sectioned with a single one-level-deep reference to the real scripts/verify-tests-fail.ps1; minor organization gaps where inline bulk (output examples, 'What It Does') could be split out.

4 / 5

Total

17

/

20

Passed

Description

58%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 states what the skill does with concrete actions and test-type coverage, but lacks an explicit 'Use when' trigger clause and natural user-facing trigger phrasing. It is distinct within the testing-tool niche but would benefit from trigger guidance.

Suggestions

Add a 'Use when...' clause stating when to activate this skill (e.g., 'Use when verifying that existing tests reproduce a bug before or after applying a fix').

Include more natural user phrasings and synonyms such as 'verify my tests reproduce the issue', 'check tests catch the bug', and test file extensions/patterns.

Tighten 'dispatches to the appropriate runner' into a more specific statement of the runners involved.

DimensionReasoningScore

Specificity

Names several concrete actions ('Auto-detects test type (UI tests, device tests, unit tests)', 'dispatches to the appropriate runner', two modes) with only minor gaps; not quite comprehensive enough for a 5.

4 / 5

Completeness

Has a clear 'what' but no explicit 'Use when...' trigger clause, so per the judging guideline completeness is capped at 3.

3 / 5

Trigger Term Quality

Contains relevant terms ('tests catch the bug', 'UI tests, device tests, unit tests', 'fix validation') but misses common natural phrasings and synonyms a user would actually say to invoke this skill.

3 / 5

Distinctiveness Conflict Risk

The 'verifies tests catch the bug' framing with inverted pass/fail semantics is a distinct niche with only minor overlap risk against general run-tests skills.

4 / 5

Total

14

/

20

Passed

Validation

100%

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

Validation16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
dotnet/maui
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.