backend-architect

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

Quality

42%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./skills/backend-architect/SKILL.md

Quality

Content

35%

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

The body is an exhaustive but verbose knowledge inventory that largely restates backend concepts Claude already knows, with no executable examples, no bundle references, and duplicated/abstract workflow steps lacking validation. It is over-scoped for a SKILL.md overview and under-specified for direct execution.

Suggestions

Cut the Capabilities and Knowledge Base catalogs down to a concise overview and move the detailed enumeration into a bundled reference file (e.g. references/PATTERNS.md), linking to it once.

Replace abstract step lists with a single, concrete design workflow that includes validation checkpoints (e.g. 'Review against NFRs', 'Validate API contract against consumers') and merge the duplicated Instructions/Response Approach lists.

Add at least one concrete, copy-paste-ready artifact template (e.g. a Mermaid service-diagram skeleton or an OpenAPI snippet) so the skill produces actionable output rather than prose.

Dimension	Reasoning	Score
Conciseness	The ~200-line Capabilities catalog and Knowledge Base restate concepts Claude already knows (REST methods, OAuth flows, Kafka, circuit breakers) as padded bullet lists, matching the score-1 'verbose; explains concepts Claude knows; padded with unnecessary context' anchor.	1 / 3
Actionability	It offers a concrete 10-step 'Response Approach' and a concrete 'Output Examples' deliverable list, but provides no executable code, commands, templates, or schemas — it describes/instructs abstractly rather than giving copy-paste-ready guidance, fitting score-2 'some concrete guidance but incomplete'.	2 / 3
Workflow Clarity	There is a clear numbered sequence (the Instructions and Response Approach steps), but no validation checkpoints or feedback loops for what is ultimately risky, environment-specific design work, and the workflow is duplicated across two overlapping step lists, matching score-2 'steps listed but validation gaps'.	2 / 3
Progressive Disclosure	Headers are well-organized, but the body is a monolithic ~327-line catalog that should live in a separate reference file; there are no bundle files and the only navigation is the section list, fitting score-2 'some structure...content that should be separate is inline'.	2 / 3
	Total	7 / 12 Passed

Description

50%

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 conveys the role and domain but reads as a title-plus-buzzword list rather than action-oriented, trigger-equipped guidance. It lacks an explicit 'Use when...' clause and concrete actions, and does not disambiguate from sibling architect skills.

Suggestions

Rewrite as third-person actions with an explicit trigger, e.g. 'Designs scalable backend services and APIs... Use when designing new backend services, defining service boundaries, or planning microservices and distributed systems.'

Add natural user-facing trigger terms such as 'REST', 'gRPC', 'API contract', 'service boundaries', and 'event-driven' so it matches phrases users actually say.

Add a disambiguating clause distinguishing this from database/cloud architect skills directly in the description.

Dimension	Reasoning	Score
Specificity	It names the domain and sub-areas ("scalable API design, microservices architecture, and distributed systems") but lists no concrete actions like the score-3 anchor 'Extract text...fill forms, merge documents', only the role label "Expert backend architect specializing in...".	2 / 3
Completeness	It answers 'what this does' (scalable API design, microservices, distributed systems) but has no 'Use when...' trigger clause; per the rubric a missing explicit trigger caps completeness at 2, exactly like the anchor 'Extract text and tables from PDF files...' with no 'when'.	2 / 3
Trigger Term Quality	Natural terms a user might say are present ("backend", "API design", "microservices", "distributed systems"), but common variations a user would actually utter (e.g. "design an API", "REST", "gRPC", "services") are missing, matching the score-2 'some relevant keywords but missing common variations' anchor.	2 / 3
Distinctiveness Conflict Risk	The niche (backend/service architecture) is clear, but the phrase overlaps with sibling skills (database-architect, cloud-architect) that the body itself distinguishes; nothing in the description disambiguates, fitting the 'somewhat specific but could still overlap' anchor.	2 / 3
	Total	8 / 12 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: sickn33/antigravity-awesome-skills
Path: skills/backend-architect/SKILL.md
Commit: a3068b7

Reviewed: about 6 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.