gitlab-automation
Automate GitLab project management, issues, merge requests, pipelines, branches, and user operations via Rube MCP (Composio). Always search tools first for current schemas.
68
58%
Does it follow best practices?
Impact
76%
1.55xAverage score across 3 eval scenarios
Advisory
Suggest reviewing before use
Optimize this skill with Tessl
npx tessl skill review --optimize ./plugins/all-skills/skills/gitlab-automation/SKILL.mdQuality
Discovery
82%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 is strong in specificity and distinctiveness, listing concrete GitLab operations and naming the specific integration mechanism. Its main weakness is the absence of an explicit 'Use when...' clause, which would help Claude know exactly when to select this skill. The trigger terms are naturally aligned with what users would say when needing GitLab automation.
Suggestions
Add an explicit 'Use when...' clause, e.g., 'Use when the user asks about GitLab projects, creating or managing issues, reviewing merge requests, checking pipeline status, or managing branches.'
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: project management, issues, merge requests, pipelines, branches, and user operations. Also specifies the mechanism (Rube MCP/Composio) and includes a procedural instruction to search tools first. | 3 / 3 |
Completeness | Clearly answers 'what does this do' (automate GitLab operations via Rube MCP), but lacks an explicit 'Use when...' clause or equivalent trigger guidance, which caps this at 2 per the rubric guidelines. | 2 / 3 |
Trigger Term Quality | Includes strong natural keywords users would say: 'GitLab', 'issues', 'merge requests', 'pipelines', 'branches', 'project management'. These are terms users naturally use when working with GitLab. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive due to the specific mention of 'GitLab' and 'Rube MCP (Composio)', which clearly differentiates it from generic CI/CD, GitHub, or other version control skills. | 3 / 3 |
Total | 11 / 12 Passed |
Implementation
35%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This skill is comprehensive in coverage but suffers from significant verbosity and redundancy — parameter documentation and pitfalls are repeated across sections, and exhaustive API parameter lists are inlined despite the skill's own instruction to use RUBE_SEARCH_TOOLS for current schemas. The workflows are well-structured but lack validation checkpoints and concrete invocation examples. The content would benefit greatly from being split into a concise overview with references to detailed parameter docs.
Suggestions
Remove redundant parameter documentation that can be discovered via RUBE_SEARCH_TOOLS — keep only the non-obvious pitfalls and gotchas that aren't in the tool schemas
Consolidate the duplicated pitfalls sections: each workflow's pitfalls are largely repeated in the 'Known Pitfalls' section at the bottom
Add at least one concrete example of an actual tool invocation with sample arguments for a common workflow (e.g., creating an issue)
Add validation/verification steps to workflows that modify state, such as confirming issue creation succeeded or checking branch existence after creation
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is extremely verbose at ~250+ lines, with significant redundancy. The 'Known Pitfalls' section largely repeats pitfalls already listed under each workflow. The 'Common Patterns' section repeats ID and pagination info that Claude already knows. Parameter lists are exhaustive API documentation that should be discovered via RUBE_SEARCH_TOOLS as the skill itself instructs. | 1 / 3 |
Actionability | Tool sequences are clearly named and ordered, and key parameters are specific and concrete. However, there are no executable code/command examples — no actual MCP tool invocation syntax or example payloads showing how to call these tools. The skill tells Claude which tools to call but not exactly how to call them with example arguments. | 2 / 3 |
Workflow Clarity | Workflows have clear sequences with numbered steps and prerequisite/optional annotations, which is good. However, there are no validation checkpoints or feedback loops — no steps like 'verify the issue was created successfully' or 'if the API returns an error, check X'. For operations that modify state (create/update issues, create branches), missing verification steps cap this at 2. | 2 / 3 |
Progressive Disclosure | The content is a monolithic wall of text with no references to external files for detailed parameter documentation or advanced workflows. The exhaustive parameter lists for each workflow could be split into separate reference files, with the main skill providing just the workflow overview and key gotchas. The quick reference table at the end is helpful but the inline detail is excessive. | 2 / 3 |
Total | 7 / 12 Passed |
Validation
90%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 10 / 11 Passed
Validation for skill structure
| Criteria | Description | Result |
|---|---|---|
frontmatter_unknown_keys | Unknown frontmatter key(s) found; consider removing or moving to metadata | Warning |
Total | 10 / 11 Passed | |
- Repository
- davepoon/buildwithclaude
- Commit
7cc63f3
- 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.