Feedback on your senior-backend skill

[RichardHightower]

I noticed you're building something for senior backend engineers, but the grading suggests the skill might be trying to cover too much ground—hard to deliver deep value when you're targeting both architecture patterns and day-to-day tooling at once.

Links:

• GitHub
• Your agentic skill in the SkillzWave marketplace

The TL;DR

You're at 33/100, which puts you in F territory. This is based on Anthropic's Progressive Disclosure Architecture standards for agentic skills. Your strongest area is Spec Compliance (12/15)—the YAML frontmatter is clean and well-structured. The biggest drag is Utility (3/20)—the skill references fictional scripts and placeholder content that don't actually solve problems.

What's Working Well

• Clean frontmatter: Your YAML is valid with all required fields and good trigger terms (NodeJS, Express, GraphQL, Microservices)
• Metadata comprehensiveness: The description covers a good range of backend concerns and uses specific technology keywords for discoverability
• Structural compliance: You're following the skill format correctly—name conventions, file organization, reference structure

The Big One: Fictional Scripts Kill Utility

This is your main blocker. The skill references three Python scripts that don't exist:

• api_scaffolder.py
• database_migration_tool.py
• api_load_tester.py

These appear as placeholders with [options] parameters but no actual implementation or guidance on using real tools (npm, psql, curl, ab, etc.). Fix this by either:

1. Creating actual working scripts with real examples, or
2. Removing script references and teaching Claude to use standard backend tooling directly with specific commands and workflows

This alone could add +6 points to your score.

Other Things Worth Fixing

1. Reference files are identical templates — All three reference files (backend_security_practices.md, database_optimization_guide.md, api_design_patterns.md) contain the same placeholder pattern. Replace with actual content: API design patterns with REST/GraphQL examples, database indexing strategies, OWASP Top 10 mitigations. +8 points

2. Strip the marketing language — Phrases like "Complete toolkit," "Comprehensive guide," "Expert-level automation," and "Production-grade output" are fluff. Replace with specifics: "Generate Express API routes with OpenAPI specs," "Analyze query plans," "Load test with configurable concurrency." +4 points

3. Inconsistent terminology — You're mixing "Api" vs "API," "NodeJS" vs "Node.js," and inconsistent casing. Pick one standard and stick with it everywhere. +2 points

4. No actionable workflows — The "Development Workflow" section has generic steps like "Review recommendations" and "Apply fixes" with no sequencing. Add numbered, verifiable steps with clear validation at each stage. +3 points

Quick Wins

• Standardize all terminology (API, Node.js, etc.)
• Replace placeholder code examples with real input/output pairs
• Add numbered workflows instead of bullet-point steps
• Pick either actual scripts OR standard tooling—don't mix both
• Most impactful: Replace reference files with real backend-specific content

---

Checkout your skill here: [SkillzWave.ai](https://skillzwave.ai) | [SpillWave](https://spillwave.com) We have an agentic skill installer that install skills in 14+ coding agent platforms. Check out this guide on how to improve your agentic skills.

[alirezarezvani]

Implementation Complete

PR #93 addresses all feedback in this issue. Here's what was done:

All Issues Fixed

Issue	Before	After
Identical reference files	3 files × 104 lines (identical boilerplate)	3 unique files totaling 2,198 lines
Placeholder scripts	3 files × 115 lines (same template)	3 functional scripts totaling 2,110 lines
Marketing language	"Complete toolkit", "Comprehensive guide"	Factual descriptions only
Inconsistent terminology	"Api", "NodeJS"	"API", "Node.js" throughout
No actionable workflows	Generic steps	3 numbered workflows with commands

Content Summary

SKILL.md (434 lines)

• YAML frontmatter with trigger phrases
• Table of Contents with links
• 3 concrete workflows: API Design, Database Optimization, Security Hardening

Reference Files:

• api_design_patterns.md (530 lines): REST vs GraphQL, versioning, error handling, pagination, authentication, rate limiting, idempotency
• database_optimization_guide.md (593 lines): EXPLAIN, indexing, N+1, connection pooling, migrations, monitoring
• backend_security_practices.md (1,075 lines): OWASP Top 10 with code examples

Python Scripts:

• api_scaffolder.py (645 lines): OpenAPI → Express routes, TypeScript types, Zod validators
• database_migration_tool.py (858 lines): SQL parsing, schema analysis, migration generation
• api_load_tester.py (607 lines): Load testing with P50/P90/P95/P99 latency metrics

Total: 4,742 lines (5.5x increase from ~867 placeholder lines)

All scripts verified to compile without errors.

[alirezarezvani]

Closed via PR #93 - all feedback addressed with complete rewrite of senior-backend skill (4,742 lines of unique, actionable content).