CtrlK
BlogDocsLog inGet started
Tessl Logo

deployment-pipeline-design

Architecture patterns for multi-stage CI/CD pipelines with approval gates and deployment strategies.

43

Quality

44%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./skills/deployment-pipeline-design/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

52%Scale 1-5

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

This skill provides comprehensive, actionable CI/CD pipeline guidance with real executable examples across multiple platforms and deployment strategies. However, it is significantly over-long for a SKILL.md, inlining detailed implementation patterns that should be in referenced files, and it explains many concepts Claude already knows well. The referenced bundle files don't exist, undermining the progressive disclosure structure.

Suggestions

Reduce the SKILL.md to a concise overview (~50-80 lines) covering the pipeline flow diagram, a brief description of each deployment strategy with selection criteria, and clear references to separate files for detailed examples.

Move the detailed YAML examples for each deployment strategy and approval pattern into the referenced files (e.g., 'resources/implementation-playbook.md', 'assets/approval-gate-template.yml') and actually create those bundle files.

Remove the generic 'Pipeline Best Practices' list of one-liners — Claude already knows these concepts — and replace with project-specific constraints or decision criteria if applicable.

Add explicit decision guidance (e.g., a decision matrix) for choosing between deployment strategies rather than listing all four with equal weight.

DimensionReasoningScore

Conciseness

The skill is significantly verbose, containing extensive code examples across multiple CI platforms (GitHub Actions, GitLab CI, Azure Pipelines), multiple deployment strategies, monitoring patterns, and best practices lists that Claude already understands well. The 'Pipeline Best Practices' section is a generic list of one-liners that adds little value. Much of this content explains well-known CI/CD concepts rather than providing novel, project-specific guidance.

2 / 5

Actionability

The skill provides concrete, executable YAML and code examples for multiple deployment strategies, approval gates, rollback procedures, and monitoring integration. The examples are mostly copy-paste ready with real tool configurations (Kubernetes, Argo Rollouts, GitHub Actions). Minor gaps exist where some examples use placeholder values without explaining customization points.

4 / 5

Workflow Clarity

The pipeline stages are clearly sequenced with a visual flow diagram and detailed stage breakdown. The multi-stage pipeline example shows proper job dependencies. The automated rollback section includes health check verification with a feedback loop. However, the overall document presents multiple independent patterns without clear guidance on when to validate between stages or how to choose between strategies, and the verification steps could be more explicit across all patterns.

4 / 5

Progressive Disclosure

The skill is a monolithic ~250-line document that inlines extensive code examples for multiple deployment strategies, approval patterns, and monitoring that should be split into separate reference files. It references files like 'resources/implementation-playbook.md', 'references/pipeline-orchestration.md', and 'assets/approval-gate-template.yml' but no bundle files are provided, making these dead references. The SKILL.md should be a concise overview pointing to these detailed materials.

2 / 5

Total

12

/

20

Passed

Description

36%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 identifies a specific domain (CI/CD pipelines) with some qualifying details but reads more like a topic label than an actionable skill description. It lacks concrete actions Claude would perform, has no 'Use when...' clause, and misses common trigger terms users would naturally use when requesting help with deployment pipelines.

Suggestions

Add a 'Use when...' clause with trigger phrases like 'when the user asks about setting up deployment pipelines, configuring CI/CD workflows, adding approval gates, or designing release strategies'.

Specify concrete actions such as 'Generates pipeline configuration files, designs stage workflows, configures approval gates, and recommends deployment strategies (blue-green, canary, rolling)'.

Include natural trigger terms and tool names users might mention: 'GitHub Actions', 'Jenkins', 'GitLab CI', 'deploy', 'release', 'pipeline YAML'.

DimensionReasoningScore

Specificity

Names the domain (CI/CD pipelines) and mentions concepts like 'approval gates' and 'deployment strategies', but doesn't describe concrete actions Claude would perform (e.g., 'generates pipeline configs', 'creates stage definitions').

2 / 5

Completeness

Provides a vague 'what' (architecture patterns for pipelines) but completely lacks a 'when' clause. There's no explicit guidance on when Claude should select this skill.

2 / 5

Trigger Term Quality

Includes relevant terms like 'CI/CD pipelines', 'approval gates', and 'deployment strategies', but misses common user phrases like 'deploy', 'release pipeline', 'GitHub Actions', 'Jenkins', 'staging', 'production', or specific tool names.

3 / 5

Distinctiveness Conflict Risk

The combination of 'multi-stage CI/CD pipelines' with 'approval gates' provides some specificity, but could overlap with general DevOps, infrastructure-as-code, or deployment automation skills.

3 / 5

Total

10

/

20

Passed

Validation

90%

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

Validation10 / 11 Passed

Validation for skill structure

CriteriaDescriptionResult

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

Total

10

/

11

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.