Better Auth Emails
To set up Better Auth Emails, fetch the recipe Markdown:
curl https://fullstackrecipes.com/recipes/better-auth-emails.mdAdd email verification, password reset, and account management emails to Better Auth using Resend.
Use this Skill: https://skilld.dev/gh/andrelandgraf/fullstackrecipes/better-auth-emails Nothing lands on disk. Nothing to clean up.
Edit a local copy. It keeps the author and licence.
≈30 tokens for metadata: the name and description. ≈39 when used: this file.
Before choosing a Skill, your Agent reads its name and description. All available Skills share that space.
In our Claude Code example, all Skill names and descriptions share 8,000 characters. This Skill uses ≈119 characters, or 1.5%.
The 1% threshold is a size suggestion. Longer descriptions can still fit.
Your model, settings, and other Skills decide how much text your Agent can read.
The example uses a 200k-token context and default Claude Code settings. The count includes the name, description, separators, and when_to_use when present. Codex also counts local file paths.
Skit's source and limits: Codex 0.160.1, Claude Code 2.1.292.
To set up Better Auth Emails, fetch the recipe Markdown:
curl https://fullstackrecipes.com/recipes/better-auth-emails.mdSource: SKILL.md on GitHub
Runs shell commands
Fetches URLs
skilld matched fixed text patterns in SKILL.md and file names. Patterns miss obfuscated code.
skilld run checks every file with the same patterns. It asks for approval before it loads a Skill with a behavior marked Needs approval.
The skill fetches external documentation from a third-party website, which could potentially contain instructions that influence the agent's behavior.
No alerts
Risk: MEDIUM · 1 issue
1/1 file flagged
Signed by skilld at 4449331. This ties the file your Agent reads to that commit on GitHub. It does not review the instructions.
Last checked against GitHub 3 weeks ago.