microservices-patterns
Design microservices architectures with service boundaries, event-driven communication, and resilience patterns. Use when building distributed systems, decomposing monoliths, or implementing microservices.
72
58%
Does it follow best practices?
Impact
98%
1.81xAverage score across 3 eval scenarios
Passed
No known issues
Optimize this skill with Tessl
npx tessl skill review --optimize ./tests/ext_conformance/artifacts/agents-wshobson/backend-development/skills/microservices-patterns/SKILL.mdQuality
Discovery
82%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 description that clearly communicates both what the skill does and when to use it, with good trigger term coverage for the microservices domain. Its main weaknesses are that the capabilities listed are somewhat conceptual rather than concrete discrete actions, and there is moderate overlap risk with adjacent architecture or distributed systems skills.
Suggestions
Make capabilities more concrete by listing specific deliverables, e.g., 'Define service boundaries, design API contracts, configure circuit breakers, plan event schemas, and create deployment topologies'.
Improve distinctiveness by adding differentiating terms or narrowing scope, e.g., specifying output formats like 'architecture diagrams' or mentioning specific patterns like 'saga pattern, CQRS, API gateway'.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Names the domain (microservices) and some actions ('design architectures', 'service boundaries', 'event-driven communication', 'resilience patterns'), but these are more like architectural concepts than concrete discrete actions. Compare to the level 3 example which lists very specific operations like 'extract text', 'fill forms', 'merge documents'. | 2 / 3 |
Completeness | Clearly answers both 'what' (design microservices architectures with service boundaries, event-driven communication, and resilience patterns) and 'when' (use when building distributed systems, decomposing monoliths, or implementing microservices) with an explicit 'Use when...' clause. | 3 / 3 |
Trigger Term Quality | Includes strong natural keywords users would say: 'microservices', 'distributed systems', 'decomposing monoliths', 'service boundaries', 'event-driven', 'resilience patterns'. These cover the main terms a user working in this domain would naturally use. | 3 / 3 |
Distinctiveness Conflict Risk | While 'microservices' is a fairly specific domain, terms like 'distributed systems' and 'resilience patterns' could overlap with skills focused on general system design, cloud architecture, or infrastructure. The description could be more distinctive by specifying unique differentiators. | 2 / 3 |
Total | 10 / 12 Passed |
Implementation
35%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This skill is a comprehensive but overly verbose reference document that explains many concepts Claude already knows. The code examples are illustrative but not executable due to missing type definitions and infrastructure dependencies. The content would benefit significantly from being condensed into a concise overview with references to separate detailed files for each pattern.
Suggestions
Reduce the main file to ~100 lines: a brief pattern selection guide and one concise example, moving detailed implementations to referenced files (e.g., references/saga-pattern.md, references/circuit-breaker.md).
Remove the 'Core Concepts' section entirely — it duplicates the code sections and explains things Claude already knows (what REST is, what a circuit breaker does).
Make code examples executable by including all type definitions (StepResult, SagaResult, Order, etc.) or use simpler self-contained examples.
Add a decision workflow: 'When decomposing, follow these steps: 1. Identify bounded contexts → 2. Define service contracts → 3. Choose communication pattern → 4. Validate with [specific criteria]' with explicit checkpoints.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Extremely verbose at ~500+ lines. Explains concepts Claude already knows well (what circuit breakers are, what REST/gRPC/GraphQL are, what saga patterns are). The bullet-point concept summaries in 'Core Concepts' are entirely redundant with the later code sections. Best practices and common pitfalls are generic knowledge Claude possesses. | 1 / 3 |
Actionability | Code examples are fairly detailed but not truly executable — they reference undefined types (Order, PaymentRequest, StepResult, SagaResult, etc.), missing imports, and depend on unshown infrastructure. They're illustrative patterns rather than copy-paste ready implementations. | 2 / 3 |
Workflow Clarity | The Saga pattern shows a clear sequence with compensation logic, and the circuit breaker has state transitions. However, there's no explicit workflow for when to apply which pattern, no validation checkpoints for the overall design process, and no guidance on verifying the architecture works correctly. | 2 / 3 |
Progressive Disclosure | References to external files exist in the Resources section, but the main file is a monolithic wall of code examples that could be split into separate reference files. The Core Concepts section duplicates what's shown in the code sections below, and the inline content is far too long for an overview skill file. | 2 / 3 |
Total | 7 / 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 |
|---|---|---|
skill_md_line_count | SKILL.md is long (596 lines); consider splitting into references/ and linking | Warning |
Total | 10 / 11 Passed | |
- Repository
- Dicklesworthstone/pi_agent_rust
- Commit
47823e3
- 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.