Skillzwave Logo
Skillzwave

fastapi-auth-patterns

80.0
B

Implement and validate FastAPI authentication strategies including JWT tokens, OAuth2 password flows, OAuth2 scopes for permissions, and Supabase integration. Use when implementing authentication, securing endpoints, handling user login/signup, managing permissions, integrating OAuth providers, or when user mentions JWT, OAuth2, Supabase auth, protected routes, access control, role-based permissions, or authentication errors.

Marketplace

Third-Party Agent Skill: Review the code before installing. Agent skills execute in your AI assistant's environment and can access your files. Learn more about security

Installation for Agentic Skill

View all platforms →
skilz install vanman2024/ai-dev-marketplace/fastapi-auth-patterns
skilz install vanman2024/ai-dev-marketplace/fastapi-auth-patterns --agent opencode
skilz install vanman2024/ai-dev-marketplace/fastapi-auth-patterns --agent codex
skilz install vanman2024/ai-dev-marketplace/fastapi-auth-patterns --agent gemini

First time? Install Skilz: pip install skilz

Works with 22+ AI coding agents

Cursor, Aider, Copilot, Windsurf, Qwen, Kimi, and more...

View All Agents
Download Agent Skill ZIP

Extract and copy to ~/.claude/skills/ then restart Claude Desktop

1. Clone the repository:
git clone https://github.com/vanman2024/ai-dev-marketplace
2. Copy the agent skill directory:
cp -r ai-dev-marketplace/plugins/fastapi-backend/skills/fastapi-auth-patterns ~/.claude/skills/

Need detailed installation help? Check our platform-specific guides:

Related Agentic Skills

mexican-cuisine-specialist

by sandraschi

Authentic Mexican cooking expert covering moles, salsas, tacos, and regional Mexican dishes

85
B
security
+ci cd

network-engineer

by zenobi-us

Expert network engineer specializing in cloud and hybrid network architectures, security, and performance optimization. Masters network design, troubl...

76
C
TECHsecurity

flow-nexus-platform

by ruvnet

Comprehensive Flow Nexus platform management - authentication, sandboxes, app deployment, payments, and challenges

54
TECHsecurity
Marketplace
+kubernetes

pair-programming

by ruvnet

AI-assisted pair programming with multiple modes (driver/navigator/switch), real-time verification, quality monitoring, and comprehensive testing. Sup...

54
TECHsecurity
Marketplace
+monitoring

Agentic Skill Details

Type
Technical
Meta-Domain
web api
Primary Domain
security
Market Score
80.0

Agent Skill Grade

B
Score: 80/100 Click to see breakdown

Score Breakdown

Spec Compliance
12/15
PDA Architecture
19/30
Ease of Use
23/25
Writing Style
8/10
Utility
17/20
Modifiers: +1

Areas to Improve

  • All referenced scripts, templates, and examples do not exist
  • 376-line file violates layered structure principle
  • Missing TOC for navigation in long file

Recommendations

  • Address 2 high-severity issues first
  • Add trigger phrases to description for discoverability
  • Add table of contents for files over 100 lines

Graded: 1/19/2026

Developer Feedback

I took a look at your fastapi-auth-patterns skill and wanted to share some thoughts.

Links:

The TL;DR

You're at 80/100 — solid B-grade territory. This is based on Anthropic's skill best practices. Your strongest area is Ease of Use (23/25) — the metadata and trigger terms are solid. The weakest is Progressive Disclosure Architecture (19/30) — the file structure needs work.

What's Working Well

  • Trigger terms are specific — "Implement user authentication in FastAPI", "Configure OAuth2 flows", "Debug authentication errors" — these are exactly the kinds of activations Claude needs to recognize
  • Good metadata overall — Skill name follows convention, description is actionable, not marketing fluff
  • Practical examples — You've got JWT, OAuth2, and Supabase patterns covered, which addresses real developer pain points
  • Clear authentication strategies section — The breakdown of when to use JWT vs OAuth2 vs Supabase shows you understand the trade-offs

The Big One: Missing Reference Files

Here's what's killing your PDA score: You reference scripts and templates that don't exist. The README talks about scripts/setup-jwt.sh, templates/jwt_auth.py, templates/oauth2_flow.py, but they're not actually in the repo. This is a major credibility issue because developers will try to use them and hit 404s.

Fix: Either create these files or inline the critical ones directly in SKILL.md. A 376-line SKILL.md isn't ideal, but it's better than broken references. If you go the inline route:

  1. Move JWT implementation into a ## JWT Implementation section with full code
  2. Add OAuth2 and Supabase implementations inline
  3. Keep the templates directory reference but only if files actually exist

This alone could add +8 points to your PDA score.

Other Things Worth Fixing

  1. No table of contents — Your file is 376 lines. Add a TOC at the top so developers can jump to what they need. Even just 5-6 major sections helps. (+1 point)

  2. Validation workflow is weak — You reference validate-auth.sh but there's no strong run→check→fix feedback loop. Add actual validation output examples or error messages so developers know what success looks like. (+1 point)

  3. Trigger phrase count is light — You've got the major ones, but could add 2-3 more specific scenarios like "Integrate JWT with FastAPI dependencies" or "Implement role-based access control". (+1 point)

  4. Some sections are verbose — The "Authentication Strategies" section has extended explanations. Tighten these up to essential info only. Keep the density high. (+1 point)

Quick Wins

  • Create the referenced script and template files (biggest impact)
  • Add table of contents to SKILL.md
  • Expand trigger phrases in the description
  • Tighten up verbose sections

These fixes could realistically push you to 88-90 territory, moving you solidly into A-grade range.


Checkout your skill here: SkillzWave.ai | SpillWave We have an agentic skill installer that installs skills in 14+ coding agent platforms. Check out this guide on how to improve your agentic skills.

Report Security Issue

Found a security vulnerability in this agent skill?