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.

53

Quality

60%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./plugins/AI-Agents-Safe-Coding-Skills-claude/skills/gitlab-automation/SKILL.md

The canonical home for this skill is gitlab-automation in administrakt0r/AI-Agents-Safe-Coding-Skills

SKILL.md
Quality
Evals
Security

Quality

Content

58%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 content is well-organized and actionable with concrete tool sequences and parameter guidance, but it is long and somewhat duplicative (per-workflow pitfalls restated in Known Pitfalls), lacks validation checkpoints for destructive operations, and keeps all reference material inline with no separate bundle files.

Suggestions

Add explicit validation/verify steps to workflows that mutate state — e.g., after creating an issue or branch, call GITLAB_GET_PROJECT_ISSUE / GITLAB_GET_REPOSITORY_BRANCH to confirm the result; after RUBE_MANAGE_CONNECTIONS, confirm ACTIVE status before proceeding.

Move the large Quick Reference table and detailed parameter/pitfall lists into a references/ file (e.g., references/api_reference.md) and keep SKILL.md as a concise overview that links out one level deep.

Remove the 'Known Pitfalls' section or deduplicate it against the per-workflow 'Pitfalls' blocks to cut repeated content and save tokens.

DimensionReasoningScore

Conciseness

The body is mostly efficient and skips basic concept explanations, but the pitfall lists, the duplicated 'Known Pitfalls' section (which restates the per-workflow pitfalls), and the large Quick Reference table add padding that could be tightened.

3 / 5

Actionability

Tool sequences name concrete tool slugs with required/optional markers and document specific parameters and values (e.g., assignee_ids [0] to unassign, label replace semantics), giving mostly executable guidance with only minor gaps.

4 / 5

Workflow Clarity

Sequences are clearly ordered, but operations that mutate state (create/update issues, create branches, manage connections) lack validation checkpoints or verify-after-execute feedback loops, capping workflow clarity at 3.

3 / 5

Progressive Disclosure

There is section structure and a Quick Reference table, but no bundle files exist so all reference-grade API detail (parameter tables, pitfalls) is inlined in one long file rather than split into one-level-deep reference files.

3 / 5

Total

13

/

20

Passed

Description

61%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 concretely enumerates GitLab operation domains and is clearly distinguishable, but it lacks an explicit 'Use when...' trigger clause and pads in tool-internal implementation details ('Rube MCP (Composio)', 'Always search tools first').

Suggestions

Add an explicit trigger clause such as 'Use when the user wants to manage GitLab issues, merge requests, pipelines, branches, or project members.'

Drop the implementation directive 'Always search tools first for current schemas' from the description — that belongs in the body, not the frontmatter.

Include common synonyms/extensions users actually say (e.g., 'MRs', 'CI', 'merge requests / MRs') to improve trigger term coverage.

DimensionReasoningScore

Specificity

Lists several specific operations ('project management, issues, merge requests, pipelines, branches, and user operations') rather than vague abstractions, though they are enumerated at a domain level rather than as discrete concrete actions.

4 / 5

Completeness

It clearly states 'what' (automate GitLab operations) but has no 'Use when...' trigger clause — the 'when' is only weakly implied, which caps completeness at 3 per the rubric.

3 / 5

Trigger Term Quality

Includes natural terms a user would say ('issues', 'merge requests', 'pipelines', 'GitLab') with good coverage, but misses common synonyms and file extensions and adds the tool-internal phrasing 'via Rube MCP (Composio)'.

4 / 5

Distinctiveness Conflict Risk

GitLab-specific triggers are a clear niche distinct from general dev skills, with only minor overlap risk against a generic GitHub skill; the MCP-via-Composio framing further narrows it.

4 / 5

Total

15

/

20

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
administrakt0r/AI-Agents-Safe-Coding-Skills
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.