CtrlK
BlogDocsLog inGet started
Tessl Logo

software-architecture

Guide for quality focused software architecture. This skill should be used when users want to write code, design architecture, analyze code, in any case that relates to software development.

52

Quality

58%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./plugins/AI-Agents-Safe-Coding-Skills-claude/skills/software-architecture/SKILL.md

The canonical home for this skill is software-architecture in sickn33/agentic-awesome-skills

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 is a well-organized catalog of architecture and code-style rules with several concrete thresholds and named examples, but it restates textbook Clean Architecture/DDD concepts Claude already knows, lacks code examples, and defines no real workflow despite a 'When to Use' section that references one. It is a competent rules sheet that would benefit from tighter prose and executable illustration.

Suggestions

Trim textbook restatements of Clean Architecture/DDD principles and the 'every line of code is a liability' platitude to assume Claude's existing knowledge.

Add a short executable code example contrasting a generic 'utils.js' dump against a domain-named module to make the naming guidance concrete.

Either describe an actual review workflow with sequenced steps and a validation checkpoint (e.g. 'list violations → propose refactor → confirm no behavior change'), or remove the circular 'When to Use' reference to a non-existent workflow.

DimensionReasoningScore

Conciseness

Mostly efficient bullet form, but sections re-explain textbook concepts Claude already knows (Clean Architecture/DDD tenets like 'Separate domain entities from infrastructure concerns', NIH syndrome, and the platitude 'Every line of custom code is a liability'); not a 2 because it is organized bullets rather than padded prose, not a 4 because the principle restatements are unnecessary.

3 / 5

Actionability

Some concrete, specific guidance is present (line thresholds '80 lines', '200 lines', '50 lines', 'max 3 levels', named library 'cockatiel', example class 'OrderCalculator'), but there are no code examples and much is abstract directive ('Follow domain-driven design', 'Define use cases clearly'); not a 4 because key execution detail and examples are missing for an instruction skill.

3 / 5

Workflow Clarity

There is no multi-step workflow — the body is a rules/principles catalog organized by topic, and 'When to Use' circularly references 'the workflow or actions described in the overview' which does not exist; not a 2 because the rule sections are clearly organized, not a 4 because no sequence or checkpoints are provided and the 'When to Use' pointer is hollow.

3 / 5

Progressive Disclosure

Good structure with clear headers (General Principles, Best Practices, Architecture and Design, Anti-Patterns, Code Quality, When to Use) and self-contained content with no nested or buried references; not a 5 because at ~73 lines it exceeds the simple-skill threshold and some anti-pattern examples could live in a reference file, not a 3 because organization is solid and nothing is mis-placed.

4 / 5

Total

13

/

20

Passed

Description

62%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.

The description provides explicit 'when' trigger guidance and natural keywords, but its 'what' is vague and the catch-all 'any case that relates to software development' creates high overlap with other coding skills. It is decent but generic rather than distinctively scoped.

Suggestions

Replace 'Guide for quality focused software architecture' with concrete capabilities, e.g. 'Reviews code for Clean Architecture/DDD compliance, suggests domain-driven naming, and flags Not-Invented-Here anti-patterns.'

Narrow the catch-all 'in any case that relates to software development' to specific triggers like 'Use when designing module boundaries, reviewing architectural layering, or choosing between a library and custom code.'

Add natural synonyms users say ('refactor', 'code review', 'module design', 'layered architecture') to improve trigger-term coverage.

DimensionReasoningScore

Specificity

Quotes 'write code, design architecture, analyze code' name the domain and several actions, but the actions and their objects ('code', 'architecture') are generic rather than concrete, matching the anchor that lists 1-2 actions without comprehensive coverage; not a 4 because the verbs lack specific objects like the anchor's 'fills forms, converts pages'.

3 / 5

Completeness

It states a 'what' ('Guide for quality focused software architecture') and an explicit 'when' ('This skill should be used when users want to write code, design architecture, analyze code...'), so both are present; not a 5 because the 'what' is a vague 'guide' rather than a concrete capability list.

4 / 5

Trigger Term Quality

Phrases 'write code', 'design architecture', 'analyze code', 'software development' are natural terms users actually say, giving good keyword coverage; not a 5 because common synonyms and file/tech extensions are absent and the broad catch-all dilutes specificity.

4 / 5

Distinctiveness Conflict Risk

The clause 'in any case that relates to software development' is extremely broad with high overlap risk against virtually any coding skill, matching the 'very broad; high overlap risk' anchor; not a 3 because the catch-all overwhelms the somewhat-specific 'software architecture' framing.

2 / 5

Total

13

/

20

Passed

Validation

93%

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

Validation15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

frontmatter_unknown_keys

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

Warning

Total

15

/

16

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.