CtrlK
BlogDocsLog inGet started
Tessl Logo

gitlab-skill

Use when designing or validating GitLab CI/CD and automatic release lifecycles, inspecting pipeline and job state read-only, composing non-interactive merge-request commands, or setting up protected refs and release credentials. Also covers reusable components and inputs, GitLab Functions, gitlab-ci-local, glab command composition, and GitLab Flavored Markdown. For pipeline execution or retry requests, provide inspection and command drafting while leaving execution to the operator.

72

Quality

87%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Low

Low-risk findings worth noting

SKILL.md
Quality
Evals
Security

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.

The body is an exemplary token-efficient index that routes precisely to per-topic references with explicit load triggers and fallback documentation links. Its weaknesses are modest: no inline example for common cases, one opaque authority sentence, and second-level reference nesting that hides most release-related files from the top-level index.

Suggestions

Add one minimal inline example (e.g., a tiny .gitlab-ci.yml snippet or a ready-to-run glab command) under the relevant entry so a common case is actionable without loading a reference file.

Rewrite the closing sentence to name the file directly, e.g. "For CI Lint on an existing ref, load references/glab-ci-existing-ref-inspection.md" instead of the cryptic "existing-ref glab inspection branch" phrasing.

Surface the second-level release-* references (or a one-line index of them) inside the Automatic Tags and Releases entry so every bundle file is discoverable from SKILL.md.

DimensionReasoningScore

Conciseness

The body is a lean ~22-line index where every entry is a trigger-conditioned pointer ("Load for include merge order, `extends`, `needs`, `parallel:matrix`") with zero padding or explanation of concepts Claude already knows — every token earns its place.

5 / 5

Actionability

Routing is concrete and unambiguous (specific files with specific load triggers plus fallbacks to official docs), but there is no inline example command or snippet covering a common case, so it is mostly rather than fully executable guidance per anchor 4.

4 / 5

Workflow Clarity

The single routing action is unambiguous and includes a behavioral checkpoint ("leaving execution to the operator"), but the closing authority sentence "The existing-ref glab inspection branch is this skill's CI Lint operational authority" is cryptic without reading the reference files — a minor clarity gap.

4 / 5

Progressive Disclosure

The index is well signaled and all 11 directly linked reference files exist, but disclosure is two levels deep (SKILL.md → automatic-tag-and-release.md → release-* adapter/credential references), leaving 18 of 29 reference files only indirectly discoverable — good structure with a minor organization gap rather than the clean one-level-deep anchor 5.

4 / 5

Total

17

/

20

Passed

Description

92%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 description: it names concrete read-only and authoring capabilities, gives explicit trigger conditions, and states an operator-execution boundary. The only weakness is missing a few natural trigger variations such as the .gitlab-ci.yml filename.

DimensionReasoningScore

Specificity

Quotes like "inspecting pipeline and job state read-only", "composing non-interactive merge-request commands", and "setting up protected refs and release credentials" list multiple concrete actions with comprehensive coverage, matching the top anchor; it is not anchor 4 because no meaningful capability area is missing.

5 / 5

Completeness

The description opens with an explicit "Use when..." clause containing concrete trigger phrases and clearly states what the skill does, plus an execution boundary ("leaving execution to the operator"), satisfying the top anchor for both what and when.

5 / 5

Trigger Term Quality

Natural terms such as "GitLab CI/CD", "pipeline", "merge request", "glab", "gitlab-ci-local", and "GitLab Flavored Markdown" give good keyword coverage, but the most natural artifact trigger users would say — ".gitlab-ci.yml" — is absent, keeping it below the comprehensive anchor 5.

4 / 5

Distinctiveness Conflict Risk

Distinctive GitLab-specific terms ("merge request", "glab", "GitLab Flavored Markdown", "protected refs") establish a clear niche with minimal overlap risk against generic git or other-platform CI skills.

5 / 5

Total

19

/

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
Jamie-BitFlight/claude_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.