better-auth
Better Auth library patterns. Only for projects using better-auth package.
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 settlemint/agent-marketplace/better-auth skilz install settlemint/agent-marketplace/better-auth --agent opencode skilz install settlemint/agent-marketplace/better-auth --agent codex skilz install settlemint/agent-marketplace/better-auth --agent gemini
First time? Install Skilz: pip install skilz
Works with 22+ AI coding agents
Cursor, Aider, Copilot, Windsurf, Qwen, Kimi, and more...
Extract and copy to ~/.claude/skills/ then restart Claude Desktop
git clone https://github.com/settlemint/agent-marketplace cp -r agent-marketplace/devtools/skills/better-auth ~/.claude/skills/ Need detailed installation help? Check our platform-specific guides:
Related Agentic Skills
automating-mail
by SpillwaveSolutionsAutomates Apple Mail via JXA with AppleScript dictionary discovery. Use when asked to "automate email", "send mail via script", "JXA Mail automation",...
automating-reminders
by SpillwaveSolutionsAutomates Apple Reminders using JavaScript for Automation (JXA). Use when asked to "create reminders programmatically", "automate reminder lists", "JX...
mastering-postgresql
by SpillwaveSolutionsPostgreSQL development for Python with full-text search (tsvector, tsquery, BM25 via pg_search), vector similarity (pgvector with HNSW/IVFFlat), JSONB...
automating-contacts
by SpillwaveSolutionsAutomates macOS Contacts via JXA with AppleScript dictionary discovery. Use when asked to "automate contacts", "JXA contacts automation", "macOS addre...
Agentic Skill Details
- Owner
- settlemint (GitHub)
- Repository
- agent-marketplace
- Type
- Other
- Meta-Domain
- N/A
- Primary Domain
- N/A
- Market Score
- 76.0
Agent Skill Grade
C
Score: 76/100
Click to see breakdown
Score Breakdown
Areas to Improve
- Two sections show similar OctoCode search patterns, wasting tokens
- File exceeds 100-line threshold without table of contents
- Plugins table is minimal; no deeper documentation for passkey/organization setup
Recommendations
- Add trigger phrases to description for discoverability
- Add table of contents for files over 100 lines
Graded: 1/18/2026
Developer Feedback
I took a look at your better-auth skill and wanted to share some thoughts.
Links:
The TL;DR
You're at 76/100, solidly in C territory. This is based on Anthropic's skill best practices rubric. Your strongest area is Spec Compliance (14/15) — the frontmatter and naming conventions are tight. The weakest is Utility (15/20) — you've got good setup examples, but missing troubleshooting, verification loops, and templates that would make this genuinely useful for developers trying to integrate Better Auth.
What's Working Well
- Excellent metadata and triggers — Your frontmatter covers library names, API patterns, hooks, and specific user intents like "passkey", "social", "2fa". This is going to surface the skill in the right contexts.
- Clean terminology consistency — You clearly distinguish between server-side
betterAuthand client-sideauthClientAPIs throughout. That's exactly what developers need. - Solid quick-start structure — The 5-step workflow is logical and gets someone from zero to a working integration pretty quickly.
The Big One: Missing Verification & Troubleshooting
Why it matters: Developers will follow your setup steps, but they need feedback that it actually worked. Right now, your workflow has no validation between steps — step 3 is "install packages" and then you jump to "create handler" with zero confirmation.
Concrete fix:
- After Step 3 (install packages), add:
Verify: npm run build && npm startwith expected output - Add a new section
<troubleshooting>with common errors:- "BETTER_AUTH_SECRET not found" → "Generate with:
openssl rand -hex 32" - "Port 3000 in use" → "Use a different port in config"
- "BETTER_AUTH_SECRET not found" → "Generate with:
- Create
references/env-template.mdwith a complete.env.examplefile
Impact: This alone gets you +3-4 points by addressing the "feedback loops" and "verification patterns" gaps.
Other Things Worth Fixing
Redundant MCP examples — Your
<mcp_first>and<research>sections both show similar OctoCode search patterns. Consolidate to one section with 2 essential examples. Saves tokens, gains clarity.No table of contents for a 279-line file — Add a brief TOC after the frontmatter listing your XML sections. At this length, navigation matters.
Missing plugin reference docs — Your plugins table is 5 rows with one-word descriptions. Create
references/plugins.mdwith actual configuration examples for passkey setup and organization plugins. That's where the real depth lives.Marketing language in the evolution section — "TypeScript-first patterns that evolve with the ecosystem" reads like promotional copy. Reframe as: "Compatible patterns as the TypeScript ecosystem evolves."
Quick Wins
- Add 1 verification step between setup phases (+2 pts)
- Create
.env.exampletemplate (+1 pt) - Consolidate MCP examples to remove redundancy (+2 pts)
- Add brief TOC for navigation (+1 pt)
- Rewrite one marketing phrase in evolution section (+1 pt)
Do those five and you're easily at 85+. The skill has good bones — it just needs some developer-facing scaffolding that helps people verify they got it right.
Checkout your skill here: SkillzWave.ai | SpillWave 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.
AI-Detected Topics
Extracted using NLP analysis
Report Security Issue
Found a security vulnerability in this agent skill?