CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

test-conventions

Shared test conventions for all testing agents in the Lichtblick repo. Defines GWT pattern, core quality rules, and the standard test-writing workflow.

Quality

71%

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/test-conventions/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

75%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 a well-structured, lean conventions document with executable code examples for both unit and E2E contexts and a clear sequenced workflow. The main gaps are small: no concrete test-run command, no explicit fail-and-retry loop, and per-framework detail that could move to references as the skill grows.

Suggestions

Add the concrete test-run commands (e.g. the Jest and Playwright invocations used in this repo) to the "Run the tests" steps so the workflow is fully executable end-to-end.

Add an explicit failure-recovery step, e.g. "If a test fails, fix the test or flag the underlying bug and re-run before reporting."

If the skill grows, split per-framework sections (naming, cleanup, error testing) into unit/E2E reference files and link them from the body.

DimensionReasoningScore

Conciseness

The body is lean — convention statements and code examples with no explanation of concepts Claude already knows — but a few clauses could be trimmed (e.g. "understand the component or feature under test" restates the step), so it sits at 'efficient with minor over-explanation' rather than every-token-earns-its-place.

4 / 5

Actionability

Executable GWT examples for both desktop/inline styles, concrete cleanup and error-testing snippets, and real paths ("testing/builders/", "e2e/fixtures/", "e2e/page-objects/") make the guidance mostly executable, but "Run the tests to confirm they pass" lacks the concrete command to execute.

4 / 5

Workflow Clarity

The six-step workflow is clearly sequenced with a validation checkpoint ("Run the tests to confirm they pass") and a reporting step, but there is no explicit error-recovery loop telling the agent what to do when tests fail, which keeps it just below the full-feedback-loop anchor.

4 / 5

Progressive Disclosure

For a single-file skill with no bundle files, all sections are well-organized and appropriately inline; the per-framework naming, cleanup, and error-testing sections could optionally live in separate reference files, leaving minor organization headroom rather than a clear 5.

4 / 5

Total

16

/

20

Passed

Description

53%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 identifies its niche and audience, but reads more like a table of contents than a capability statement. It lacks an explicit 'Use when...' trigger clause and the natural trigger terms (unit tests, E2E, Jest, Playwright) that would help it fire at the right moments.

Suggestions

Add an explicit trigger clause, e.g. "Use when writing or updating unit (Jest) or E2E (Playwright) tests in the Lichtblick repo."

Include natural trigger terms users would actually say — "unit tests", "E2E tests", "Jest", "Playwright" — since they currently appear only in the body, not the description.

State concrete capabilities instead of content labels, e.g. "Write unit and E2E tests using the GWT pattern, existing builders/fixtures, and sibling-matching conventions."

DimensionReasoningScore

Specificity

"Defines GWT pattern, core quality rules, and the standard test-writing workflow" names the domain and its contents, but these are content-area labels rather than several concrete, specific actions, matching the '1-2 concrete actions, not comprehensive' anchor.

3 / 5

Completeness

A clear 'what' is present (defines GWT pattern, quality rules, workflow), but there is no 'Use when...' clause; "for all testing agents in the Lichtblick repo" states the audience rather than an explicit trigger, so completeness is capped at 3 per the judging guidelines.

3 / 5

Trigger Term Quality

Relevant keywords like "test conventions" and "testing agents" are present, but natural phrases users would say — "unit tests", "E2E", "Jest", "Playwright" — are missing from the description, matching the 'some relevant keywords but missing common variations' anchor.

3 / 5

Distinctiveness Conflict Risk

The description is scoped to a specific repo ("Lichtblick repo") and a narrow niche (test conventions for testing agents), making it mostly distinct with only minor overlap risk against a generic testing skill.

4 / 5

Total

13

/

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.

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository

lichtblick-suite/lichtblick

Path

.github/skills/test-conventions/SKILL.md

Revision

9589f38

Reviewed

Table of Contents

DiscoveryImplementationValidation

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.

Claim skill