Tessl • The package manager for agent skills

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.

1.55x

Quality

68%

Does it follow best practices?

Impact

76%

1.55x

Average score across 3 eval scenarios

Securityby

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

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

Quality

Content

61%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 highly actionable with concrete tool sequences and parameters, but it is a monolithic single file with redundant pitfall restatements and no validation feedback loops on its batch/write workflows.

Suggestions

Extract the per-workflow parameter catalogs and the Quick Reference table into a references/ file (e.g., REFERENCE.md), keeping SKILL.md an overview that links one level deep.

Add explicit validation/error-recovery checkpoints to the write and batch workflows (e.g., after GITLAB_CREATE_PROJECT_ISSUE, verify the returned issue_iid before further updates).

Deduplicate the 'Known Pitfalls' / 'Common Patterns' sections against the per-workflow 'Pitfalls' bullets to remove repeated guidance.

Dimension	Reasoning	Score
Conciseness	Mostly efficient and reference-like with no concept padding, but the 'Known Pitfalls' and 'Common Patterns' sections substantially restate per-workflow pitfalls (label replacement, issue_iid vs id, author_id/author_username exclusivity, assignee_ids:[0]) and could be deduplicated.	3 / 5
Actionability	Fully concrete guidance: named tool slugs, exact parameter names with types and example values (e.g., assignee_ids: [0], state_event: "close"), and a 22-row task→tool→params quick-reference table covering the common cases.	5 / 5
Workflow Clarity	Numbered tool sequences with role tags and a setup validation checkpoint are clear, but the batch (listing) and write (create issue/branch) workflows lack validate-after checkpoints or error-recovery feedback loops, which caps workflow clarity at 3 for destructive/batch operations.	3 / 5
Progressive Disclosure	A single ~252-line monolith with no bundle files; the detailed parameter catalogs and quick-reference table are bulk reference material inlined in SKILL.md rather than split into separate files, with no references present at all.	2 / 5
	Total	13 / 20 Passed

Description

75%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.

The description is specific, well-scoped, and distinct, but it omits explicit trigger guidance, capping completeness. Adding a 'Use when...' clause would raise the weakest dimension.

Suggestions

Add an explicit trigger clause, e.g., 'Use when automating GitLab issues, merge requests, CI/CD pipelines, branches, or user/membership operations.'

Include common synonyms a user might say (CI/CD, MRs, builds) to broaden trigger-term coverage toward comprehensive.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete capabilities across the GitLab surface — 'project management, issues, merge requests, pipelines, branches, and user operations' — giving comprehensive coverage of the toolkit's actions.	5 / 5
Completeness	Clearly states what the skill does but provides no 'Use when...' trigger clause; 'Always search tools first for current schemas' is procedural, not a trigger, so completeness is capped at 3.	3 / 5
Trigger Term Quality	Includes natural user-facing nouns like 'issues, merge requests, pipelines, branches' but misses common synonyms/variants a user might say (e.g., 'CI/CD', 'MRs', 'tickets').	4 / 5
Distinctiveness Conflict Risk	Scoped specifically to GitLab automation via Rube MCP (Composio), a clear niche with distinct triggers and minimal overlap with generic devops or GitHub skills.	5 / 5
	Total	17 / 20 Passed

Validation

93%

Warnings & errors only

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	15 / 16 Passed

Repository: davepoon/buildwithclaude
Path: plugins/all-skills/skills/gitlab-automation/SKILL.md
Commit: a9fa86d

Reviewed: about 20 hours ago

Table of Contents

Discovery Implementation Validation

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.