backend-architect

Expert backend architect specializing in scalable API design, microservices architecture, and distributed systems.

1.17x

Quality

40%

Does it follow best practices?

Impact

89%

1.17x

Average score across 3 eval scenarios

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./plugins/AI-Agents-Safe-Coding-Skills/skills/backend-architect/SKILL.md

The canonical home for this skill is backend-architect in rmyndharis/antigravity-skills

Quality

Content

35%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 persona-and-capability glossary rather than actionable skill instruction: it enumerates backend concepts Claude already knows, offers no executable code or concrete decision frameworks, and inlines a massive capabilities catalog that belongs in reference files. A sequenced Response Approach gives it some workflow structure, but checkpoints and progressive disclosure are weak.

Suggestions

Replace the enumerated Capabilities catalog with a concise decision-oriented methodology (when to choose REST vs gRPC vs GraphQL, when to use saga vs 2PC, circuit-breaker selection heuristics) that adds knowledge Claude would not already apply correctly.

Move the technology/pattern listings into references/ files (e.g. references/api-patterns.md, references/resilience.md) and keep SKILL.md as a lean overview with one-level-deep links, since no bundle files currently exist.

Add validation/feedback checkpoints to the Response Approach (e.g. 'Validate the API contract with a consumer-driven contract test before proceeding to inter-service communication design') and concrete output templates for the items listed in Output Examples.

Dimension	Reasoning	Score
Conciseness	The ~322-line body is a large catalog enumerating concepts Claude already knows (every API type, auth mechanism, resilience pattern, framework), plus redundant Purpose/Core Philosophy/Knowledge Base sections that restate the same persona, fitting 'noticeably verbose; several unnecessary explanations or padded sections.'	2 / 5
Actionability	The Instructions and Response Approach are high-level hints ('Design API contracts: REST/GraphQL/gRPC, versioning, documentation') with no executable code, commands, templates, or concrete decision criteria, matching 'minimal concrete guidance; high-level hints but missing the specific steps to execute.'	2 / 5
Workflow Clarity	The Response Approach provides a clear 10-step sequence, but there are no validation checkpoints or feedback loops anywhere, matching 'steps listed but validation gaps; sequence present but checkpoints missing or implicit.'	3 / 5
Progressive Disclosure	Section headers give some structure, but ~150 lines of the Capabilities catalog clearly belong in separate reference files and no bundle files (references/scripts/assets) exist, matching 'some structure but could be better organized; content that should be separate is inline.'	3 / 5
	Total	10 / 20 Passed

Description

45%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 clearly states the persona and its specialty areas but is a 'who you are' statement rather than a 'what you do and when to use it' one: no concrete action verbs and no 'Use when' trigger clause, which caps completeness. It is a reasonable but generic persona description with overlap risk against sibling architect skills.

Suggestions

Rewrite the description as concrete actions, e.g. 'Designs scalable backend APIs, defines microservices boundaries, and plans distributed-system resilience' rather than 'specializing in'.

Add an explicit 'Use when...' clause naming natural trigger phrases users would say (e.g. 'Use when designing a new backend service or API, defining service boundaries, or planning microservices/distributed-system architecture').

Include distinguishing triggers that separate it from cloud-architect and database-architect (e.g. mention service/API focus, defer infrastructure and schema design) to reduce conflict risk.

Dimension	Reasoning	Score
Specificity	The description names the domain ('backend architect') and specialty areas ('scalable API design, microservices architecture, and distributed systems') but contains no concrete action verbs describing what it does, matching the 'names the domain but actions are minimal or generic' anchor rather than the action-listing anchors above.	2 / 5
Completeness	It gives a clear 'what' (an expert backend architect specializing in three areas) but provides no 'Use when...' clause or equivalent trigger guidance, so per the rubric completeness is capped at 3 for a clear 'what' with 'when' missing.	3 / 5
Trigger Term Quality	Terms like 'API design', 'microservices architecture', and 'distributed systems' are keywords a user might say, but common variations and synonyms (REST, gRPC, services, event-driven, backend services) are missing, fitting 'some relevant keywords but missing common variations or synonyms.'	3 / 5
Distinctiveness Conflict Risk	The backend-services niche is somewhat specific, but it overlaps noticeably with the broader architect family (cloud-architect, database-architect, security-auditor) named in the body and lacks distinct trigger phrases, matching 'somewhat specific but could still overlap with similar skills.'	3 / 5
	Total	11 / 20 Passed

Validation

93%

Warnings & errors only

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

Validation — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
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
Path: plugins/AI-Agents-Safe-Coding-Skills/skills/backend-architect/SKILL.md
Commit: 57c135b

Reviewed: 21 hours ago

Table of Contents

Discovery Implementation Validation

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.