Tessl • The package manager for agent skills

gitlab-ci-patterns

Build GitLab CI/CD pipelines with multi-stage workflows, caching, and distributed runners for scalable automation. Use when implementing GitLab CI/CD, optimizing pipeline performance, or setting up automated testing and deployment.

1.42x

Quality

—

Does it follow best practices?

Impact

97%

1.42x

Average score across 3 eval scenarios

Securityby

Passed

No known issues

Quality

Content

80%

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

The content is a lean, highly actionable pattern catalog with executable YAML throughout, scoring well on conciseness and actionability. Its weaknesses are missing validation feedback loops in deployment workflows and two referenced bundle files that do not actually exist.

Suggestions

Add explicit validation checkpoints to deployment workflows (e.g., after kubectl apply, verify rollout and halt/retry on failure) to lift workflow clarity above 2.

Either create the referenced assets/gitlab-ci.yml.template and references/pipeline-stages.md files or remove the 'Reference Files' section, since the links currently point to nonexistent files.

Move the large catalog of pattern snippets into a single reference file and keep SKILL.md as a concise overview with one-level-deep links to improve progressive disclosure.

Dimension	Reasoning	Score
Conciseness	The body is code-forward with minimal prose: each section is a short header plus executable YAML, with no padding explaining what GitLab CI or caching is. Not score 2 because there is no unnecessary conceptual explanation — tokens are spent on concrete patterns.	3 / 3
Actionability	Every section provides fully executable, copy-paste-ready YAML with specific images (node:20, hashicorp/terraform:1.6.0), real commands, and concrete variables, matching the score-3 anchor for executable examples.	3 / 3
Workflow Clarity	Stage sequencing is present (build/test/deploy; validate/plan/apply) and the Terraform pipeline has a manual gate, but deployment examples lack explicit validate-then-fix feedback loops for destructive operations, which caps this at 2 per the rubric.	2 / 3
Progressive Disclosure	Sections are well-organized, but the 'Reference Files' section points to assets/gitlab-ci.yml.template and references/pipeline-stages.md that do not exist in the bundle, so navigation is dead; this is better than a monolithic wall but fails the one-level-deep signaled-reference standard for a score of 3.	2 / 3
	Total	10 / 12 Passed

Description

100%

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 concise, specific, and fully answers both what the skill does and when to invoke it with natural trigger terms. It is a strong, low-conflict description that earns top marks across all dimensions.

Dimension	Reasoning	Score
Specificity	Names multiple concrete actions — 'Build GitLab CI/CD pipelines with multi-stage workflows, caching, and distributed runners' — matching the score-3 anchor for listing several specific concrete actions rather than a single vague domain mention.	3 / 3
Completeness	It explicitly answers both 'what' (build pipelines with multi-stage workflows, caching, distributed runners) and 'when' via an explicit 'Use when...' clause, matching the score-3 anchor.	3 / 3
Trigger Term Quality	'Use when implementing GitLab CI/CD, optimizing pipeline performance, or setting up automated testing and deployment' provides natural phrasings a user would actually say, with good coverage of common variations.	3 / 3
Distinctiveness Conflict Risk	The GitLab CI/CD framing carves a clear niche with distinct triggers unlikely to fire for unrelated skills; the cross-runner/GitOps scope is specific enough to avoid broad overlap.	3 / 3
	Total	12 / 12 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
referenced_paths_exist	Referenced path issues: 2 missing	Warning

	Total	15 / 16 Passed

Repository: Dicklesworthstone/pi_agent_rust
Commit: abece4a

Reviewed: 4 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.