agent-dev-backend-api

Agent skill for dev-backend-api - invoke with $agent-dev-backend-api

1.08x

Quality

Does it follow best practices?

Impact

85%

1.08x

Average score across 3 eval scenarios

Securityby

Passed

No known issues

Optimize this skill with Tessl

npx tessl skill review --optimize ./.agents/skills/agent-dev-backend-api/SKILL.md

Quality

Discovery

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 is essentially a label and invocation instruction with no substantive content. It fails on every dimension: it does not describe capabilities, includes no natural trigger terms, answers neither 'what' nor 'when', and is indistinguishable from any other backend-related skill.

Suggestions

Add specific concrete actions the skill performs, e.g., 'Creates REST API endpoints, configures route handlers, sets up middleware, and manages database connections for backend services.'

Add an explicit 'Use when...' clause with natural trigger terms, e.g., 'Use when the user asks about building APIs, creating endpoints, backend development, REST services, Express/FastAPI routes, or server-side logic.'

Remove the invocation instruction ('invoke with $agent-dev-backend-api') from the description and replace it with functional content that helps Claude distinguish this skill from others.

Dimension	Reasoning	Score
Specificity	The description contains no concrete actions whatsoever. 'Agent skill for dev-backend-api' is entirely vague and does not describe what the skill actually does.	1 / 3
Completeness	Neither 'what does this do' nor 'when should Claude use it' is answered. The description only states it is an 'agent skill' and how to invoke it, providing no functional or contextual information.	1 / 3
Trigger Term Quality	There are no natural keywords a user would say. 'dev-backend-api' is an internal identifier, not a term users would naturally use in requests. No actionable trigger terms like 'API', 'backend', 'endpoint', 'REST', etc. are meaningfully surfaced.	1 / 3
Distinctiveness Conflict Risk	The description is so generic that it could overlap with any backend or API-related skill. There is nothing distinguishing it from other potential agent skills or backend tools.	1 / 3
	Total	4 / 12 Passed

Implementation

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

This skill is fundamentally flawed: it describes a hypothetical 'self-learning' framework (Agentic-Flow v2.0.0-alpha) with non-existent APIs rather than providing actionable guidance for backend API development. The content is extremely verbose, filled with non-executable TypeScript examples for imaginary tools (reasoningBank, GNN-enhanced search, flash attention), and the actual backend development guidance is limited to generic bullet-point best practices that Claude already knows. The enormous YAML frontmatter contains extensive non-functional metadata that wastes tokens.

Suggestions

Remove all references to the non-existent Agentic-Flow framework (reasoningBank, agentDB, GNN search, flash attention) and replace with actual executable code examples for building APIs (e.g., Express.js route handlers, middleware setup, database queries).

Drastically reduce the YAML frontmatter to only essential fields and move the actual skill instructions to focus on concrete, copy-paste-ready code patterns for common API tasks.

Add a clear multi-step workflow with validation checkpoints for API development (e.g., 1. Analyze existing routes → 2. Create controller → 3. Add validation middleware → 4. Write tests → 5. Verify tests pass).

Remove generic best practices Claude already knows (proper HTTP status codes, input validation, REST conventions) and replace with project-specific patterns, file naming conventions, and concrete examples of the expected code structure.

Dimension	Reasoning	Score
Conciseness	Extremely verbose with massive amounts of unnecessary content. The YAML frontmatter alone is enormous and most of it is non-functional metadata. The body contains extensive TypeScript code examples for a hypothetical 'Agentic-Flow v2.0.0-alpha' framework (reasoningBank, agentDB, GNN, flash attention) that are not executable in any real Claude Code context. It explains concepts Claude already knows (REST conventions, CRUD patterns, HTTP status codes) and pads with marketing-style feature descriptions.	1 / 3
Actionability	The TypeScript code examples reference non-existent APIs (reasoningBank.searchPatterns, agentDB.gnnEnhancedSearch, agentDB.flashAttention) that cannot be executed. The shell scripts in hooks reference 'npx claude-flow@alpha' commands that don't exist. There are no concrete, copy-paste-ready instructions for actually building backend APIs - just abstract framework code that describes a hypothetical self-learning system.	1 / 3
Workflow Clarity	While there is a loose sequence (before/during/after implementation), the steps are abstract descriptions of a non-existent framework rather than actionable workflow steps. There are no validation checkpoints for the actual API development work. The 'Key responsibilities' and 'Best practices' sections are generic bullet lists without clear sequencing or verification steps.	1 / 3
Progressive Disclosure	The content is a monolithic wall of text with no references to external files and no bundle files provided. All content is inline regardless of complexity. The massive YAML frontmatter (which should arguably be separate configuration) is mixed with the skill body. There's no clear hierarchy or navigation structure - just sequential sections dumped together.	1 / 3
	Total	4 / 12 Passed

Validation

100%

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 — 11 / 11 Passed

Validation for skill structure

No warnings or errors.

Repository: ruvnet/claude-flow
Commit: d29d87f

Reviewed: 4 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.