CtrlK
BlogDocsLog inGet started
Tessl Logo
PluginPublic

testland/gitlab-ci-test-jobs

Use for any question or task about running tests in GitLab CI/CD, including quick ones such as showing test results in a merge request or skipping tests on docs-only changes: test stages in .gitlab-ci.yml, parallel matrix jobs, junit and coverage artifact reports, Postgres or Redis services, needs between jobs, rules for triggers and retry policy.

Quality

92%

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

Overview
Quality
Evals
Security
Files

Quality

Content

82%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 strong, highly actionable reference: complete executable YAML for every common GitLab test-job scenario, a useful anti-patterns table, and honest limitations. The main weaknesses are minor — a small amount of beginner-level explanation in the Overview, no explicit config validation step, and a rough References section.

Suggestions

Trim the Overview's explanation of basic .gitlab-ci.yml structure (stages → jobs → steps) — Claude already knows this; keep only project-specific conventions.

Add a final validation step after assembling the config, e.g. lint via GitLab's CI Lint API (`curl --header 'PRIVATE-TOKEN: <token>' 'https://gitlab.example.com/api/v4/ci/lint' ...`) or the Web IDE lint, so users catch YAML/rules errors before pushing.

Clean up the References section formatting (the dangling '- ' on the alternatives line) and make cross-skill pointers explicit links; if deeper material like a full end-to-end pipeline example exists, move it to a references/ file with a clearly signaled link.

DimensionReasoningScore

Conciseness

The body is lean — nine terse code blocks plus short GitLab-specific notes like 'runner died; safe to retry' — but the Overview explains basics Claude already knows ('stages (sequential phases) → jobs (parallel within a stage) → steps'), a minor instance of over-explanation that could be trimmed. This fits the 4 anchor; the 5 anchor's 'every token earns its place' is undercut by that section, while 3 would require more pervasive padding.

4 / 5

Actionability

Nine complete, copy-paste-ready YAML configurations cover the common cases (basic job, matrix, services, junit/coverage artifacts, stages/needs, retry, rules, cache, variables), and the anti-patterns table pairs each failure mode with a concrete fix. This matches the 5 anchor ('copy-paste ready code... specific examples cover the common cases'); no example is pseudocode or missing key details.

5 / 5

Workflow Clarity

Steps 1–9 form a clear, progressive sequence with cross-references ('rules: (Step 7)', 'when: always (Step 4)') and no destructive/batch operations that would cap the score. It sits at 4 rather than 5 because there is no explicit validation checkpoint (e.g., linting the assembled config or verifying the pipeline passes), and at 4 rather than 3 because the sequence is coherent and gaps are minor.

4 / 5

Progressive Disclosure

A single-file skill (~240 lines) with well-titled step sections, an anti-patterns table, limitations, and a References section — no bundle files exist, and the inline content is appropriately sized for the topic. It falls short of 5 because the References section is sloppily formatted (dangling '- ' lines) and points only to other skills and external docs rather than well-signaled bundle references, and the References entry for 'ci-test-job-conventions' mentions 'references/circleci.md' in another skill without a clear pointer.

4 / 5

Total

17

/

20

Passed

Description

100%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.

An exemplary skill description: it opens with an explicit 'Use for' trigger clause, enumerates concrete capabilities across the full GitLab CI test domain, and stays GitLab-specific throughout, minimizing conflict risk. Both 'what' and 'when' are answered explicitly with natural user phrasing and the canonical config filename.

DimensionReasoningScore

Specificity

The description lists multiple concrete capabilities — 'showing test results in a merge request', 'skipping tests on docs-only changes', 'parallel matrix jobs, junit and coverage artifact reports, Postgres or Redis services, needs between jobs, rules for triggers and retry policy' — with comprehensive coverage of the GitLab CI test domain. A 4 anchor requires 'minor gaps in coverage', and no meaningful capability area of GitLab test jobs is missing.

5 / 5

Completeness

It explicitly answers both 'what' (the enumerated capability list after the colon) and 'when' ('Use for any question or task about running tests in GitLab CI/CD, including quick ones such as...') with concrete trigger phrases. This matches the 5 anchor ('Use when working with PDF files or when the user mentions PDFs...') in structure; the 4 anchor requires the 'when' to be less explicit, which is not the case here.

5 / 5

Trigger Term Quality

Natural user phrases are covered ('running tests', 'test results in a merge request', 'skipping tests on docs-only changes') alongside platform keywords and the config filename '.gitlab-ci.yml', matching the 5 anchor's 'synonyms and file extensions' standard. A 4 would require noticeably missing natural terms, but users asking about matrix jobs, junit reports, Postgres/Redis services, or retry policy all find their trigger here.

5 / 5

Distinctiveness Conflict Risk

Every trigger is GitLab-specific ('GitLab CI/CD', '.gitlab-ci.yml', 'merge request'), giving it a clear niche with minimal conflict risk against generic CI or other-platform skills. The 4 anchor ('minor overlap risk') does not fit better since nothing in the description would naturally fire for a non-GitLab task.

5 / 5

Total

20

/

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.

Validation — 15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

referenced_paths_exist

Referenced path issues: 1 missing

Warning

Total

15

/

16

Passed

Reviewed

On this page