deployment-strategy
Deployment Strategy Agent. Feature Flag, Canary/Blue-Green 배포, 롤백 전략을 담당합니다. 안전한 배포와 점진적 롤아웃을 관리합니다.
67
55%
Does it follow best practices?
Impact
Pending
No eval scenarios have been run
Passed
No known issues
Optimize this skill with Tessl
npx tessl skill review --optimize ./skills/deployment-strategy/SKILL.mdQuality
Discovery
32%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 clear domain (deployment strategies) and mentions specific deployment patterns, but lacks concrete actions and explicit trigger guidance. The mixed Korean/English terminology may help or hinder matching depending on user language. The absence of a 'Use when...' clause significantly weakens its utility for skill selection.
Suggestions
Add an explicit 'Use when...' clause with trigger scenarios like 'Use when the user asks about deploying applications, managing feature flags, setting up canary releases, or planning rollback strategies'
List specific concrete actions such as 'Configure feature flag rules, set up canary deployment percentages, define rollback triggers, manage blue-green traffic switching'
Include both Korean and English trigger terms consistently to improve matching: 'deployment, 배포, rollback, 롤백, feature toggle, release strategy'
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Names the domain (deployment) and mentions specific concepts like 'Feature Flag, Canary/Blue-Green 배포, 롤백 전략' but doesn't list concrete actions - only states it 'handles' and 'manages' these areas without detailing specific operations. | 2 / 3 |
Completeness | Describes what it does at a high level but completely lacks a 'Use when...' clause or any explicit trigger guidance. The 'when' is entirely missing, which per rubric guidelines should cap this at maximum 2, but since the 'what' is also weak, this scores 1. | 1 / 3 |
Trigger Term Quality | Includes relevant technical terms like 'Feature Flag', 'Canary', 'Blue-Green', '롤백' (rollback), '배포' (deployment) that users might mention, but missing common variations like 'release', 'deploy', 'gradual rollout', or English equivalents for Korean terms. | 2 / 3 |
Distinctiveness Conflict Risk | The deployment-specific terms (Feature Flag, Canary, Blue-Green) provide some distinctiveness, but 'deployment' and 'rollback' are generic enough to potentially overlap with CI/CD, DevOps, or infrastructure skills. | 2 / 3 |
Total | 7 / 12 Passed |
Implementation
77%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a comprehensive deployment strategy skill with excellent actionability - providing executable code for feature flags, Kubernetes deployments, and rollback scripts. The workflow clarity is strong with explicit validation checkpoints and staged rollout criteria. However, the document is somewhat verbose and could benefit from better progressive disclosure by splitting detailed implementations into separate reference files.
Suggestions
Consider moving detailed implementation code (LaunchDarkly setup, Kubernetes YAML, bash scripts) to separate reference files and keeping only quick-start examples in the main skill
Reduce the ASCII diagram to a simpler comparison table or remove it entirely - Claude understands deployment strategy concepts
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The content is reasonably efficient but includes some verbose elements like the ASCII diagram comparing deployment strategies and extensive markdown tables that could be more concise. The Korean explanations add context but some are redundant for Claude. | 2 / 3 |
Actionability | Provides fully executable code examples including TypeScript feature flag implementations, Kubernetes YAML configurations, bash scripts for canary rollout and traffic switching. All code is copy-paste ready with specific commands. | 3 / 3 |
Workflow Clarity | Clear multi-step workflows with explicit validation checkpoints. The Canary rollout stages include specific time durations and verification criteria. Rollback conditions are well-defined with thresholds and the deployment checklist provides clear pre/post deployment validation steps. | 3 / 3 |
Progressive Disclosure | Content is well-organized with clear sections, but it's a monolithic document that could benefit from splitting detailed implementations (LaunchDarkly setup, Kubernetes configs) into separate reference files. The output locations at the end suggest external files but don't link to them. | 2 / 3 |
Total | 10 / 12 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.
Validation — 10 / 11 Passed
Validation for skill structure
| Criteria | Description | Result |
|---|---|---|
allowed_tools_field | 'allowed-tools' contains unusual tool name(s) | Warning |
Total | 10 / 11 Passed | |
- Repository
- shaul1991/shaul-agents-plugin
- Commit
9242c58
- 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.