Tessl • The package manager for agent skills

gitlab-ci-review

Review fallow's GitLab CI integration, scripts, jq filters, MR comments, and report formatting. Use when changes touch ci/ or GitLab-specific output behavior.

Quality

68%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./.claude/skills/gitlab-ci-review/SKILL.md

Quality

Content

68%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.

An extremely token-efficient orchestrator skill that correctly delegates detail to the reviewer agent file. Its weakness is that the inline guidance — what specifically to check in jq filters and scripts, and in what order — stays high-level, leaving workflow and actionability short of fully executable.

Suggestions

Add one or two concrete examples of the formatting/quoting pitfalls to check in jq filters and shell scripts (e.g. quoting style, jq string interpolation), so the skill is actionable without the referenced agent file.

Make the review sequence explicit (1. read the agent doc, 2. check tests in ci/tests/, 3. inspect scripts/jq filters, 4. emit verdict) so the workflow order is unambiguous.

Since no bundle files exist, either inline the minimal review criteria or add a references file so the delegated detail is discoverable within the skill itself.

Dimension	Reasoning	Score
Conciseness	The body is four lean lines with zero padding; it assumes Claude's competence and every token (read this file, check these tests, emit one of these verdicts) earns its place.	5 / 5
Actionability	It gives concrete paths ('.agents/agents/ci-integration-reviewer.md', 'ci/tests/') and a specific output protocol ('APPROVE', 'CONCERN', or 'BLOCK'), but 'check any formatting or quoting behavior in shell scripts and jq filters' is a high-level hint with the substantive review criteria delegated elsewhere.	3 / 5
Workflow Clarity	A rough sequence is present (read reviewer doc, check tests and scripts, output verdict) but the steps are loosely joined ('Also check...') with no checkpoints or ordering emphasis; it falls short of 'clear sequence with most checkpoints'.	3 / 5
Progressive Disclosure	The tiny body is well organized with a clearly signaled one-level reference to the reviewer agent file; however no bundle files (references/, scripts/, assets/) exist to back the structure, and navigation is minimal.	4 / 5
	Total	15 / 20 Passed

Description

67%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.

A solid description with a clear what/when structure and a distinct project-scoped niche. Its main weaknesses are missing natural trigger synonyms (pipeline, merge request, .gitlab-ci.yml) and a 'when' clause that could be more concrete.

Suggestions

Add natural trigger terms users would actually say, e.g. 'GitLab CI pipelines', 'merge requests', or '.gitlab-ci.yml', to the 'Use when' clause.

Spell out 'MR comments' as 'merge request (MR) comments' on first use so the trigger matches both phrasings.

Dimension	Reasoning	Score
Specificity	The description lists several concrete review targets ('GitLab CI integration, scripts, jq filters, MR comments, and report formatting') though all under the single verb 'Review', leaving minor coverage gaps.	4 / 5
Completeness	It answers both 'what' (reviews integration, scripts, jq filters, MR comments, formatting) and 'when' ('Use when changes touch ci/ or GitLab-specific output behavior'), but the 'when' clause could name more concrete trigger artifacts.	4 / 5
Trigger Term Quality	Relevant keywords like 'GitLab CI', 'jq filters', 'MR comments', and 'ci/' are present, but common natural variations users would say — 'pipeline', 'merge request', '.gitlab-ci.yml' — are missing.	3 / 5
Distinctiveness Conflict Risk	Scoping to 'fallow's GitLab CI integration' carves a clear niche, but the trigger 'changes touch ci/' carries minor overlap risk with the same repo's general code-review skills.	4 / 5
	Total	15 / 20 Passed

Validation

100%

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 — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: fallow-rs/fallow
Path: .claude/skills/gitlab-ci-review/SKILL.md
Commit: 74177e5

Reviewed: 5 days 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.