odyssey4me/gitlab
Create and manage GitLab issues, merge requests, pipelines, and repositories using the glab CLI. Use when asked to open an MR, review a merge request, check CI/CD pipelines, list issues, or manage code review on GitLab.
71
89%
Does it follow best practices?
Impact
—
No eval scenarios have been run
Advisory
Suggest reviewing before use
Quality
Discovery
100%Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.
This is a strong skill description that clearly identifies the tool (glab CLI), the platform (GitLab), specific capabilities (issues, merge requests, pipelines, repositories), and explicit trigger conditions. It uses third person voice correctly and includes natural user terms like 'MR', 'merge request', 'CI/CD pipelines', and 'code review' that would help Claude accurately select this skill.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: create and manage issues, merge requests, pipelines, and repositories. The description names the specific tool (glab CLI) and concrete GitLab entities. | 3 / 3 |
Completeness | Clearly answers both 'what' (create and manage GitLab issues, MRs, pipelines, repos using glab CLI) and 'when' (explicit 'Use when...' clause with specific trigger scenarios like opening MRs, checking pipelines, listing issues). | 3 / 3 |
Trigger Term Quality | Includes natural keywords users would say: 'MR', 'merge request', 'CI/CD pipelines', 'issues', 'code review', 'GitLab'. Covers both abbreviations ('MR') and full terms ('merge request'), which matches how users naturally speak. | 3 / 3 |
Distinctiveness Conflict Risk | Clearly scoped to GitLab specifically and the glab CLI tool, which distinguishes it from GitHub-related skills or generic git skills. The mention of GitLab-specific terminology (merge requests vs pull requests, glab CLI) creates a distinct niche. | 3 / 3 |
Total | 12 / 12 Passed |
Implementation
64%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a functional skill with strong actionability—all commands are concrete and executable. However, it's somewhat verbose, including sections like configuration, aliases, and troubleshooting that add limited value for Claude. The workflow examples include some verification steps but lack explicit error recovery loops for state-changing operations, and the inline command reference is extensive enough that much of it could be offloaded to reference files.
Suggestions
Move the detailed command listings (Issues, MRs, Pipelines, Repos, Releases) to a reference file and keep only the most essential commands inline, reducing the SKILL.md to a concise overview.
Add explicit error handling and feedback loops to the workflow examples, e.g., 'If glab mr create fails, check error output and verify branch exists before retrying.'
Remove or significantly trim the Configuration, Aliases, and Troubleshooting sections—Claude can derive these from general CLI knowledge and the linked official docs.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is reasonably efficient but includes some unnecessary sections like Configuration, Aliases, and Troubleshooting that Claude already knows or could look up. The direct glab command listings largely duplicate what the official docs provide and what Claude already knows about CLI tools. The Model Guidance section is useful but the overall content could be tightened. | 2 / 3 |
Actionability | All commands are concrete, copy-paste ready bash commands with clear arguments. The examples section shows real multi-step workflows with actual commands. Both the wrapper script usage and direct glab usage are fully executable. | 3 / 3 |
Workflow Clarity | The examples section includes some verification steps (e.g., 'check approval status', 'Verify MR was created'), but they are informal comments rather than explicit validation checkpoints with error recovery. For action commands like create/merge/close that are destructive or state-changing, there are no explicit feedback loops or error handling guidance. | 2 / 3 |
Progressive Disclosure | References to permissions.md and common-workflows.md are well-signaled and one level deep, which is good. However, the main SKILL.md is quite long with extensive inline command listings that could be moved to reference files. The balance between overview and detail leans too heavily toward inline content. | 2 / 3 |
Total | 9 / 12 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 — 11 / 11 Passed
Validation for skill structure
No warnings or errors.
Reviewed
Table of Contents