Tessl • The package manager for agent skills

cicd-expert

Elite CI/CD pipeline engineer specializing in GitHub Actions, GitLab CI, Jenkins automation, secure deployment strategies, and supply chain security. Expert in building efficient, secure pipelines with proper testing gates, artifact management, and ArgoCD/GitOps patterns. Use when designing pipelines, implementing security gates, or troubleshooting CI/CD issues.

Quality

76%

Does it follow best practices?

Impact

—

No eval scenarios have been run

Securityby

Advisory

Suggest reviewing before use

Fix and improve this skill with Tessl

tessl review fix ./skills/cicd-expert/SKILL.md

Quality

Content

62%

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

This skill provides excellent actionable content with complete, executable pipeline examples and clear workflow sequences with validation checkpoints. However, it suffers from severe verbosity - the content is roughly 4-5x longer than necessary, with redundant patterns, explanations of concepts Claude already knows, and content that should be in reference files rather than inline. The quality of individual examples is high, but the token cost is excessive.

Suggestions

Reduce content by 60-70% by removing redundant examples (caching is shown 3+ times), eliminating explanations of basic concepts (what SAST/SCA are, how caching works), and cutting verbose commentary

Move Patterns 2-7, the 8 Common Mistakes section, and the OWASP table to reference files, keeping only Pattern 1 and brief summaries with links in the main skill

Consolidate the Pre-Implementation Checklist and Summary sections - they repeat information already covered in the patterns and principles

Remove the 'Core Responsibilities' section (5.1-5.5) entirely as it describes capabilities rather than providing actionable instructions

Dimension	Reasoning	Score
Conciseness	Extremely verbose at ~800+ lines with significant redundancy. Explains concepts Claude knows (what SAST/DAST are, basic caching concepts), repeats similar patterns multiple times (caching shown in sections 4, Pattern 3, and Mistake 2), and includes excessive commentary that doesn't add actionable value.	1 / 3
Actionability	Provides fully executable, copy-paste ready YAML configurations throughout. Code examples are complete with proper syntax, real action versions, and working commands. The patterns are immediately usable in real pipelines.	3 / 3
Workflow Clarity	Multi-step processes are clearly sequenced with explicit validation checkpoints. The TDD workflow (Step 1-4) includes verification steps, Pattern 1 shows proper job dependencies with security gates, and Mistake 5 explicitly demonstrates health check validation loops.	3 / 3
Progressive Disclosure	References external files (pipeline-examples.md, security-gates.md) appropriately, but the main document is a monolithic wall of text with too much inline content. The 7 patterns, 8 mistakes, and detailed security sections could be split into separate reference files with just summaries in the main skill.	2 / 3
	Total	9 / 12 Passed

Description

89%

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

This is a solid skill description with excellent trigger term coverage and clear 'when to use' guidance. The main weakness is the use of persona language ('Elite...engineer specializing in', 'Expert in') rather than action-oriented verbs describing what the skill does. The description would be stronger if it replaced identity claims with concrete actions like 'Designs, builds, and troubleshoots CI/CD pipelines...'

Suggestions

Replace persona language ('Elite CI/CD pipeline engineer specializing in', 'Expert in') with action verbs describing concrete capabilities (e.g., 'Designs and builds CI/CD pipelines using GitHub Actions, GitLab CI, and Jenkins')

Add more specific actions beyond 'building' - e.g., 'configures workflow triggers, manages secrets, sets up matrix builds, implements caching strategies'

Dimension	Reasoning	Score
Specificity	Names the domain (CI/CD) and lists several areas of expertise (GitHub Actions, GitLab CI, Jenkins, ArgoCD/GitOps), but uses vague terms like 'specializing in' and 'expert in' rather than concrete actions. Does mention some specific concepts like 'testing gates, artifact management' but doesn't describe what actions are performed.	2 / 3
Completeness	Clearly answers both what (CI/CD pipeline engineering with specific tools and patterns) and when ('Use when designing pipelines, implementing security gates, or troubleshooting CI/CD issues'). The explicit 'Use when...' clause provides clear trigger guidance.	3 / 3
Trigger Term Quality	Good coverage of natural terms users would say: 'GitHub Actions', 'GitLab CI', 'Jenkins', 'CI/CD', 'pipelines', 'deployment', 'ArgoCD', 'GitOps'. These are terms users would naturally use when seeking help with continuous integration and deployment.	3 / 3
Distinctiveness Conflict Risk	Clear niche focused specifically on CI/CD pipelines with distinct tool mentions (GitHub Actions, GitLab CI, Jenkins, ArgoCD). Unlikely to conflict with general coding skills or other DevOps skills due to the specific pipeline and deployment focus.	3 / 3
	Total	11 / 12 Passed

Validation

75%

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 — 12 / 16 Passed

Validation for skill structure

Criteria	Description	Result
skill_md_line_count	SKILL.md is long (1272 lines); consider splitting into references/ and linking	Warning
metadata_version	'metadata' field is not a dictionary	Warning
license_field	'license' field is missing	Warning
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	12 / 16 Passed

Repository: martinholovsky/claude-skills-generator
Commit: 1086ef2

Reviewed: 5 months 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.