CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

evolutionary-modular-architecture

Guides design and implementation of evolutionary modular-monolith platforms with DDD (strategic + tactical), flat-by-aggregate organization, an Anti-Corruption Layer for vendor independence, a transactional outbox for events, smart resilience (backoff with jitter, circuit breakers, idempotency), and a polished architecture HTML document with elegant SVG diagrams. Use when designing a platform or backend, defining bounded contexts, organizing modules and folders, choosing monolith vs microservices, decoupling from an external service (ERP, storage, AI), making calls resilient, adding real-time push, picking a 2026 TypeScript stack (Nx, NestJS, React), or producing an architecture document or diagram. Also triggers on 'modular monolith', 'bounded contexts', 'flat-by-aggregate', 'ports and adapters', 'architecture diagram'. Do NOT use for simple CRUD, NestJS-only deep implementation (use nestjs-modular-monolith), or pure domain-model review (use tactical-ddd).

Quality

94%

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

SKILL.md
Quality
Evals
Security

Quality

Content

85%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.

A well-structured, actionable architecture skill with a phased workflow and explicit exit checkpoints, supported by real reference and script files. The only weaknesses are minor verbosity (metaphor + cheat-sheet restatement) and the lack of copy-paste code scaffolding.

Suggestions

Tighten conciseness by removing or shrinking the house metaphor and merging the 'Decision rules' cheat sheet into the relevant phases instead of restating them.

Improve actionability by adding a small copy-paste scaffolding snippet (e.g., a sample module folder tree with the suffix conventions) so the flat-by-aggregate layout can be reproduced without consulting the reference.

Consider adding one concrete before/after example of an ACL port + adapter interface signature in the body, so the core vendor-decoupling action is immediately executable.

DimensionReasoningScore

Conciseness

Largely efficient and assumes Claude's competence (no basic explanations of DDD or circuit breakers), but the house metaphor and the 'Decision rules' cheat sheet restate content already covered in the phases and could be trimmed. It sits above the 'mostly efficient' anchor but not fully lean.

4 / 5

Actionability

Gives concrete, executable guidance — validation commands (`node scripts/validate-structure.mjs [root]`), concrete folder layouts (`billing/subscription/`), file suffixes (`.entity.ts`), naming conventions (`module.aggregate.action`), and quantified thresholds (~10% retry budget). It is a design/instruction skill rather than a code skill, so the absence of full scaffolding code is the minor gap keeping it below 5.

4 / 5

Workflow Clarity

A clear Phase 0–7 sequence where every phase has an explicit 'Exit:' checkpoint, plus an automated-checks section providing a validate→fix loop ('exit non-zero on violation and print the offending paths', blocking on structural failures).

5 / 5

Progressive Disclosure

The body is an overview that points to one-level-deep references via two clear tables ('Core model' and 'Reference guide'); every referenced path (references/*.md, assets/architecture-template.html, scripts/*.mjs) resolves to a real bundle file, and the skill explicitly says to load references only when the current phase needs them.

5 / 5

Total

18

/

20

Passed

Description

100%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 strong, third-person description that concretely states capabilities, gives comprehensive natural trigger terms, answers both what and when, and explicitly disambiguates from related skills. No first/second-person voice or padding issues.

DimensionReasoningScore

Specificity

Lists multiple concrete capabilities — DDD strategic + tactical, flat-by-aggregate organization, Anti-Corruption Layer for vendor independence, transactional outbox, resilience (backoff with jitter, circuit breakers, idempotency), and an architecture HTML document with SVG diagrams — giving comprehensive coverage.

5 / 5

Completeness

Explicitly answers both 'what' (design and implementation of evolutionary modular-monolith platforms with the listed techniques) and 'when' ('Use when designing a platform or backend, defining bounded contexts...'), with concrete trigger phrases and negative 'Do NOT use' guidance.

5 / 5

Trigger Term Quality

Includes natural phrases users would say ('designing a platform or backend', 'decoupling from an external service', 'adding real-time push') plus an explicit 'Also triggers on' list with synonyms like 'modular monolith', 'bounded contexts', 'ports and adapters'.

5 / 5

Distinctiveness Conflict Risk

Occupies a clear niche (evolutionary modular monolith) and actively disambiguates from sibling skills via 'Do NOT use for simple CRUD, NestJS-only deep implementation (use nestjs-modular-monolith), or pure domain-model review (use tactical-ddd)', minimizing conflict risk.

5 / 5

Total

20

/

20

Passed

Validation

100%

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

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository

tech-leads-club/agent-skills

Path

packages/skills-catalog/skills/(architecture)/evolutionary-modular-architecture/SKILL.md

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.