CtrlK
BlogDocsLog inGet started
Tessl Logo

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.

81

1.55x
Quality

80%

Does it follow best practices?

Impact

76%

1.55x

Average score across 3 eval scenarios

SecuritybySnyk

Advisory

Suggest reviewing before use

Fix and improve this skill with Tessl

tessl review fix ./plugins/all-skills/skills/gitlab-automation/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

77%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

A highly actionable, well-sequenced GitLab automation reference with concrete tool names, parameters, and pitfalls, plus explicit workflow checkpoints. Its weaknesses are avoidable redundancy across pitfall sections and a monolithic structure that buries reference detail inline instead of splitting it into separate files.

Suggestions

Consolidate the duplicated pitfalls: keep a single 'Known Pitfalls' section and have per-workflow 'Pitfalls' reference it, or vice versa, to remove repeated content and improve conciseness.

Move the detailed 'Key parameters' lists and 'Quick Reference' table into a separate reference file (e.g., references/REFERENCE.md) and have SKILL.md link to it, improving progressive disclosure while keeping the overview lean.

DimensionReasoningScore

Conciseness

The body avoids explaining concepts Claude already knows and is information-dense, but pitfalls are duplicated between per-workflow 'Pitfalls' sections and the 'Common Patterns'/'Known Pitfalls' sections, and tool info repeats in the Quick Reference table — it could be tightened; not 1 because nothing is padded fluff, not 3 because the redundancy is avoidable.

2 / 3

Actionability

It gives exact tool slugs, parameter names, enum values (e.g., state 'opened'/'closed', assignee_ids [0]), and concrete pitfalls; as an instruction/tool-reference skill the absence of code blocks is not penalized because the guidance is concrete and copy-paste ready.

3 / 3

Workflow Clarity

Each workflow has a numbered tool sequence with [Prerequisite]/[Required]/[Optional] annotations, the Setup section includes an explicit 'Confirm connection status shows ACTIVE' checkpoint, and mutating calls are guarded by prerequisite verification; not 2 because validation checkpoints are explicit rather than implicit.

3 / 3

Progressive Disclosure

The body is well-organized with clear sections but is a single ~250-line monolithic file with no bundle files or internal references, so the detailed parameter/pitfall reference is inline where it could be split out; not 1 because it is structured rather than a disorganized wall, not 3 because there are no one-level-deep references to separate files.

2 / 3

Total

10

/

12

Passed

Description

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.

A specific, third-person description that names concrete GitLab action domains and natural trigger terms, with a clear niche that avoids conflict. Its main gap is the absence of an explicit 'Use when...' trigger clause, which caps completeness at 2.

Suggestions

Add a 'Use when...' clause naming the user situations that should activate this skill (e.g., 'Use when the user wants to automate GitLab issues, merge requests, pipelines, or branch management'), which would raise completeness and trigger_term_quality.

Optionally surface a couple of common user phrasings (e.g., 'GitLab MRs', 'CI/CD pipelines') so the trigger vocabulary matches how users actually ask for these tasks.

DimensionReasoningScore

Specificity

The description lists multiple concrete action domains — "project management, issues, merge requests, pipelines, branches, and user operations" — matching the 'Lists multiple specific concrete actions' anchor; it is comprehensive rather than naming only a few actions, so not a 2.

3 / 3

Completeness

It clearly states what the skill does but has no 'Use when...' clause or equivalent trigger guidance ('Always search tools first for current schemas' is operational, not a trigger), so completeness is capped at 2 per the guidelines; not 1 because the 'what' is explicit.

2 / 3

Trigger Term Quality

It surfaces natural terms users would actually say (GitLab, issues, merge requests, pipelines, branches, user operations), giving good coverage rather than only some relevant keywords.

3 / 3

Distinctiveness Conflict Risk

It carves a clear niche (GitLab via Rube MCP/Composio) with distinct triggers that are unlikely to fire for unrelated skills; not 2 because the scope is specific rather than broadly overlapping.

3 / 3

Total

11

/

12

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.

Validation15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

Total

15

/

16

Passed

Repository
davepoon/buildwithclaude
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.