backend-architect

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

Quality

17%

Does it follow best practices?

Impact

—

No eval scenarios have been run

Securityby

Passed

No known issues

Optimize this skill with Tessl

npx tessl skill review --optimize ./skills/backend-architect/SKILL.md

Quality

Discovery

22%

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

This description reads as a persona statement rather than a functional skill description. It lacks concrete actions (what it does), has no explicit trigger guidance (when to use it), and uses first/third-person role framing ('Expert backend architect') instead of describing capabilities. The domain keywords provide some value but are insufficient to make this a reliable skill selector.

Suggestions

Replace the persona framing with concrete action verbs: e.g., 'Designs REST/GraphQL APIs, architects microservices, plans distributed system topologies, reviews API contracts and service boundaries.'

Add an explicit 'Use when...' clause: e.g., 'Use when the user asks about API design, service decomposition, inter-service communication, scaling strategies, or distributed system patterns.'

Include more natural trigger terms users would say: 'REST API', 'GraphQL', 'service mesh', 'load balancing', 'database sharding', 'event-driven architecture', 'gRPC', 'API gateway'.

Dimension	Reasoning	Score
Specificity	The description uses vague, abstract language like 'specializing in' and 'scalable API design' without listing any concrete actions. It describes a persona rather than specific capabilities (no verbs like 'designs', 'builds', 'reviews').	1 / 3
Completeness	The 'what' is vague (no concrete actions listed) and there is no 'when' clause at all. There is no 'Use when...' or equivalent guidance for when Claude should select this skill.	1 / 3
Trigger Term Quality	Contains some relevant domain keywords like 'API design', 'microservices architecture', and 'distributed systems' that users might mention, but lacks common variations and practical trigger terms like 'REST', 'endpoints', 'service mesh', 'load balancing', etc.	2 / 3
Distinctiveness Conflict Risk	The terms 'API design', 'microservices', and 'distributed systems' provide some domain specificity, but 'backend architect' is broad enough to overlap with many development-related skills, and without concrete actions it's hard to distinguish from general coding skills.	2 / 3
	Total	6 / 12 Passed

Implementation

12%

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

This skill reads as a comprehensive but entirely abstract knowledge catalog of backend architecture topics rather than an actionable skill file. It enumerates hundreds of technologies and patterns Claude already knows without providing any concrete code, commands, schemas, or worked examples. The content would benefit enormously from being condensed to a focused overview with concrete guidance and splitting detailed references into separate files.

Suggestions

Replace the extensive capability bullet lists with 2-3 concrete, worked examples showing actual API design output (e.g., a sample OpenAPI spec, a Mermaid architecture diagram, a concrete service boundary definition).

Cut at least 80% of the enumerated technologies and patterns—Claude already knows what OAuth 2.0, JWT, Redis, and Kafka are. Focus only on project-specific conventions or opinionated choices.

Add validation checkpoints to the workflow, such as 'Verify API contract with consumer team before proceeding to implementation' or 'Run contract tests against schema before finalizing.'

Split detailed reference material (framework comparisons, pattern catalogs, testing strategies) into separate bundle files and reference them from a concise SKILL.md overview.

Dimension	Reasoning	Score
Conciseness	Extremely verbose and padded with extensive lists of technologies, patterns, and concepts that Claude already knows. The 'Capabilities' section alone is a massive enumeration of well-known backend concepts (OAuth 2.0, JWT, REST, GraphQL, etc.) with brief descriptions that add no actionable value. Most of this content is a knowledge dump rather than targeted instruction.	1 / 3
Actionability	Contains zero executable code, no concrete commands, no specific examples with inputs/outputs, and no copy-paste ready guidance. The entire skill is abstract descriptions and bullet-point lists of concepts. The 'Response Approach' is a high-level numbered list without any concrete implementation details. 'Example Interactions' are just prompt suggestions, not worked examples.	1 / 3
Workflow Clarity	The 'Instructions' section provides a 4-step sequence and 'Response Approach' gives a 10-step sequence, which provides some workflow structure. However, there are no validation checkpoints, no feedback loops, no error recovery steps, and no concrete verification criteria for any of the steps.	2 / 3
Progressive Disclosure	Monolithic wall of text with no references to external files and no bundle files to support it. All content is inline in a single massive document. The extensive capability lists, behavioral traits, testing strategies, and deployment sections could all be split into referenced files but are instead dumped into one enormous skill file.	1 / 3
	Total	5 / 12 Passed

Validation

90%

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 — 10 / 11 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	10 / 11 Passed

Repository: sickn33/antigravity-awesome-skills
Commit: 8854d4e

Reviewed: 2 days 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.