agent-dev-backend-api
Agent skill for dev-backend-api - invoke with $agent-dev-backend-api
33
0%
Does it follow best practices?
Impact
85%
1.08xAverage score across 3 eval scenarios
Passed
No known issues
Optimize this skill with Tessl
npx tessl skill review --optimize ./.agents/skills/agent-dev-backend-api/SKILL.mdQuality
Discovery
0%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 with an invocation command rather than a functional description. It fails on every dimension: it provides no concrete actions, no trigger terms, no guidance on when to use it, and nothing to distinguish it from other skills. It would be nearly impossible for Claude to correctly select this skill from a pool of available options.
Suggestions
Describe the specific actions this skill performs (e.g., 'Creates REST API endpoints, configures database models, sets up authentication middleware for backend services').
Add an explicit 'Use when...' clause with natural trigger terms users would say (e.g., 'Use when the user asks to build API routes, create backend endpoints, set up server-side logic, or work with REST APIs').
Specify the technology stack or domain to improve distinctiveness (e.g., mention specific frameworks like Express, Django, or specific backend concerns like routing, middleware, database integration).
| 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's 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 domain-specific trigger terms are present. | 1 / 3 |
Distinctiveness Conflict Risk | The description is extremely generic. 'Agent skill for dev-backend-api' could overlap with any backend or API-related skill, and provides no distinguishing characteristics. | 1 / 3 |
Total | 4 / 12 Passed |
Implementation
0%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 fictional 'self-learning' framework (Agentic-Flow v2.0.0-alpha) with non-existent APIs rather than providing actionable guidance for backend API development. The extensive TypeScript code blocks are non-executable pseudocode referencing imaginary services like reasoningBank and agentDB. The actual backend development guidance is limited to generic bullet-point best practices that Claude already knows.
Suggestions
Remove all fictional framework code (reasoningBank, agentDB, GNN search, flash attention) and replace with actual executable patterns for API development—e.g., real Express.js route setup, real database query examples, real test commands.
Replace the generic best practices bullet lists with concrete, copy-paste-ready code examples showing specific patterns like authentication middleware, input validation with a real library (e.g., Joi/Zod), and error handling middleware.
Add a clear multi-step workflow for API endpoint creation with validation checkpoints, e.g.: 1) Check existing routes, 2) Create controller with specific template, 3) Add route registration, 4) Run `npm test` to validate, 5) Fix failures before proceeding.
Reduce the massive YAML frontmatter to only fields that Claude Code actually uses, and split advanced reference material (if any) into separate linked files rather than one monolithic document.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Extremely verbose with massive amounts of unnecessary content. The TypeScript code blocks are illustrative pseudocode for a hypothetical 'Agentic-Flow v2.0.0-alpha' framework that Claude cannot actually execute. Explains concepts like CRUD endpoints, success rate tracking, and pattern storage at length without adding actionable value. The YAML frontmatter alone is enormous and most of it is non-functional metadata. | 1 / 3 |
Actionability | Despite containing many code blocks, none are executable or copy-paste ready. They reference non-existent APIs (reasoningBank.searchPatterns, agentDB.gnnEnhancedSearch, agentDB.flashAttention) and fictional frameworks. The 'best practices' and 'patterns to follow' sections are vague bullet points without concrete implementation guidance. There are no real commands or actual code Claude could use. | 1 / 3 |
Workflow Clarity | While there's a loose before/during/after structure, the workflow steps are not actionable sequences—they're aspirational descriptions of a non-existent system. No validation checkpoints exist for actual API development tasks. The 'Key responsibilities' list is generic and lacks sequencing. No feedback loops for error recovery in actual development work. | 1 / 3 |
Progressive Disclosure | Monolithic wall of content with no references to external files. Everything is dumped into a single document with poor organization—mixing framework-specific pseudocode, generic best practices, and YAML configuration. The sections don't build on each other logically, and there's no clear navigation or separation of concerns. | 1 / 3 |
Total | 4 / 12 Passed |
Validation
100%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
01070ed
- 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.