CtrlK
BlogDocsLog inGet started
Tessl Logo

microservices-patterns

Design microservices architectures with service boundaries, event-driven communication, and resilience patterns. Use when building distributed systems, decomposing monoliths, or implementing microservices.

78

1.81x
Quality

68%

Does it follow best practices?

Impact

98%

1.81x

Average score across 3 eval scenarios

SecuritybySnyk

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./tests/ext_conformance/artifacts/agents-wshobson/backend-development/skills/microservices-patterns/SKILL.md

The canonical home for this skill is microservices-patterns in wshobson/agents

SKILL.md
Quality
Evals
Security

Quality

Content

53%Weight 40%Scale 1-5

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

The body delivers substantial, mostly executable pattern implementations, but suffers from a redundant Core Concepts section that re-explains known material, no sequenced workflow for applying the patterns, and severe progressive-disclosure failures — hundreds of lines of template code inlined while every referenced bundle file is missing. It functions as a reference document rather than a lean skill overview.

Suggestions

Create the actual bundle files (references/service-decomposition-guide.md, references/communication-patterns.md, references/saga-implementation.md, assets/circuit-breaker.py, assets/event-bus-template.py, assets/api-gateway-template.py) or remove the Resources section — currently all six referenced paths are broken.

Delete or drastically shrink the 'Core Concepts' section: it duplicates the detailed pattern sections and explains concepts (circuit breaker, database-per-service, saga) Claude already knows; move the inline template code into the referenced assets/ files and keep only short usage sketches in SKILL.md.

Add a sequenced workflow for the most common use case (e.g., a numbered Strangler Fig decomposition process: identify seam → proxy routes → extract service → validate parity → repeat) so the patterns are actionable as a process, not just a catalog.

DimensionReasoningScore

Conciseness

The ~80-line "Core Concepts" section re-explains well-known concepts ("Fail fast on repeated errors", "Each service owns its data", "Distributed transactions / Compensating actions") and duplicates the later detailed pattern sections almost wholesale (decomposition, communication, data management, and resilience are each covered twice), which the rubric explicitly penalizes. The bulk is reasonably dense code, keeping it above anchor 2, but the redundancy is too extensive for anchor 4.

3 / 5

Actionability

Roughly 400 lines of concrete Python (event bus, saga orchestrator, circuit breaker, API gateway) provide mostly executable guidance, but with minor gaps: SagaResult/StepResult/Order/PaymentRequest types are undefined, `asyncio` and `List` are unimported in the gateway example, and `APIGateway = Depends()` misuses FastAPI's Depends. This sits between anchor 3 (pseudocode/missing key details) and anchor 5 (fully copy-paste ready), fitting anchor 4.

4 / 5

Workflow Clarity

The body is a pattern catalog organized by category, not a sequenced process — there is no ordered workflow for actually decomposing a monolith or applying these patterns (e.g., Strangler Fig is described in bullets but never as a step sequence). Anchor 3's "steps listed but validation gaps / sequence present but checkpoints missing" is the best fit; not anchor 2 since organization is coherent, not anchor 4 since no sequence with checkpoints exists.

3 / 5

Progressive Disclosure

The body inlines ~590 lines including three complete template implementations the Resources section claims live in assets/ files, and all six referenced bundle files (references/service-decomposition-guide.md, assets/circuit-breaker.py, etc.) do not exist in the bundle, so navigation is broken despite clearly signaled references. Scored against the actual bundle structure, this matches anchor 2's "content that clearly belongs in separate files is inlined"; good section headers keep it above the monolithic anchor 1.

2 / 5

Total

12

/

20

Passed

Description

83%Weight 40%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.

A well-formed description that explicitly covers both what the skill does and when to use it, with a clear niche and natural trigger phrases. Its main limitations are a single-verb action statement and slightly incomplete synonym coverage for triggers.

DimensionReasoningScore

Specificity

"Design microservices architectures with service boundaries, event-driven communication, and resilience patterns" names the domain plus three concrete focus areas, but rests on a single design verb rather than the multiple distinct actions of the anchor-5 example; it clearly exceeds the 1-2 actions of anchor 3.

4 / 5

Completeness

It explicitly answers 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 concrete trigger phrases, matching the anchor-5 example structure; anchor 4's weaker 'when' clause undersells the explicit trigger list here.

5 / 5

Trigger Term Quality

"distributed systems", "decomposing monoliths", "implementing microservices" are natural user phrases, but common synonyms like "splitting a monolith", "SOA", or "service boundaries" phrasing users would say are only partially covered, matching anchor 4 rather than comprehensive anchor 5.

4 / 5

Distinctiveness Conflict Risk

The microservices/decomposition niche has distinct triggers and minimal conflict with most skills, but "designing distributed systems" is broad enough to overlap with general architecture or system-design skills, so anchor 4 fits better than 5.

4 / 5

Total

17

/

20

Passed

Validation

87%

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

Validation — 14 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

skill_md_line_count

SKILL.md is long (596 lines); consider splitting into references/ and linking

Warning

referenced_paths_exist

Referenced path issues: 6 missing

Warning

Total

14

/

16

Passed

Repository
Dicklesworthstone/pi_agent_rust
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.