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.
65
55%
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 trigger terms, listing concrete GitLab operations and natural keywords users would employ. Its main weakness is the absence of an explicit 'Use when...' clause, which would help Claude know precisely when to select this skill. The mention of 'Rube MCP (Composio)' adds distinctiveness but may not be meaningful to end users.
Suggestions
Add an explicit 'Use when...' clause, e.g., 'Use when the user asks about GitLab projects, issues, merge requests, CI/CD pipelines, or branch management.'
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: project management, issues, merge requests, pipelines, branches, and user operations. Also specifies the tooling 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. | 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 | Clearly scoped to GitLab specifically, with distinct triggers like 'GitLab', 'merge requests', 'pipelines', and the specific tooling (Rube MCP/Composio). Unlikely to conflict with GitHub or other VCS skills. | 3 / 3 |
Total | 11 / 12 Passed |
Implementation
27%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This skill is a comprehensive but overly verbose GitLab API reference that would consume significant context window space. Its main strengths are thorough coverage of tool names, parameters, and non-obvious pitfalls (like `assignee_ids: [0]`). Its main weaknesses are massive redundancy (pitfalls repeated twice, parameter documentation that duplicates what RUBE_SEARCH_TOOLS provides), lack of concrete invocation examples, and no progressive disclosure structure despite being well over 200 lines.
Suggestions
Move detailed parameter lists and pitfalls into a separate REFERENCE.md file, keeping SKILL.md as a concise overview with the quick reference table and one concrete example per workflow.
Add at least one concrete tool invocation example per workflow showing actual parameter values and expected response structure.
Remove the duplicated 'Known Pitfalls' section — keep pitfalls only under their respective workflows or consolidate into a single section.
Add validation/verification steps to workflows, e.g., 'After creating an issue, verify the response contains the expected `iid` and `web_url`' or 'If 4xx error, verify project ID with GITLAB_GET_PROJECT'.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is extremely verbose at ~250+ lines, with significant repetition. The 'Known Pitfalls' section largely duplicates pitfalls already listed under each workflow. The 'Common Patterns' section repeats ID format 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 | The skill provides concrete tool names, parameter names, and specific values (e.g., `assignee_ids: [0]` to unassign), which is useful. However, there are no executable code examples or actual tool invocation examples showing input/output. The tool sequences are listed but lack concrete call examples with sample parameters filled in. | 2 / 3 |
Workflow Clarity | Tool sequences are clearly numbered with prerequisites and optional steps marked. 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 could fail (wrong IDs, permission issues), there's no error recovery guidance beyond listing pitfalls. | 2 / 3 |
Progressive Disclosure | The entire skill is a monolithic wall of text with no bundle files to offload detailed parameter references or workflow specifics. The exhaustive parameter lists for each workflow and the duplicated pitfalls sections should be split into separate reference files. The quick reference table at the end is helpful but doesn't compensate for the inline bloat. | 1 / 3 |
Total | 6 / 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
857fe3a
- 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.