New to Claude Skills? Learn how to install them →

davila7 on GitHub

DoorDash Allergy Shield

Free

Ensure safe food ordering with dietary restrictions.

Get this skill

Free · Opens the source repo

What DoorDash Allergy Shield does

The DoorDash Allergy Shield skill provides a safety net for users ordering food through the DoorDash CLI (dd-cli) by managing personal dietary profiles and vetting cart contents against allergens. This skill allows users to store information about allergens, dietary preferences, and dislikes, ensuring that every order is checked for potential conflicts before checkout. By implementing a deterministic vetting process, it saves a vetted cart dump and performs a final check against the highest-severity allergens, providing an additional layer of safety for those with dietary restrictions.

This skill is particularly useful for individuals who have allergies or dietary preferences that require careful consideration when ordering food. Users can define their dietary profile, including allergens with severity levels, and the skill will automatically vet each item in the cart against this profile. The vetting process is mandatory, meaning that users will be alerted to any potential issues before they can proceed to checkout, thus reducing the risk of accidentally ordering food that could trigger an allergic reaction.

While the skill is designed to help users make safer food choices, it is important to note that it is not a medical device and should not be relied upon as the sole means of ensuring food safety. The matching process is heuristic, relying on item names and descriptions, which means it may not catch all potential allergens, especially those hidden in ingredient lists or due to cross-contamination. Users are still responsible for reviewing their orders on the DoorDash checkout page, where the final decision is made.

Overall, the DoorDash Allergy Shield skill is an essential tool for anyone who frequently orders food and needs to manage dietary restrictions, providing peace of mind and reducing the likelihood of mistakes during the ordering process.

When to use it

Use this skill when ordering food for yourself or others with known allergies or dietary restrictions.

When not to use it

This skill may not be suitable for casual users without dietary restrictions, or for those who do not use the DoorDash CLI.

What you can build with it

Ordering for a Family Member

When ordering food for someone with allergies, use this skill to ensure their dietary restrictions are respected.

Regular Food Orders

If you frequently order food and have specific dietary needs, this skill will help automate the vetting process.

Managing Allergens in a Group Order

When ordering for a group, you can manage multiple dietary profiles to accommodate everyone’s restrictions effectively.

How to install DoorDash Allergy Shield

View source

1. Install with the skills CLI

npx skills add davila7/claude-code-templates/doordash-allergy-shield --agent claude-code

2. Or install it manually

Download the skill folder and drop it into ~/.claude/skills/ for all projects, or .claude/skills/ to scope it to one repo. Restart Claude Code so it picks up the new skill.

Anthropic's agentic coding CLI, and the reference implementation of Agent Skills. Drop a skill folder into ~/.claude/skills and Claude Code loads it automatically whenever a task matches the skill's description. Claude Code docs

Inside SKILL.md

Written by davila7

DoorDash Allergy Shield

Claude has no cross-session memory: tell it "I'm allergic to peanuts" today and tomorrow it happily adds pad thai. This skill persists a dietary profile and makes cart vetting mandatory — with a deterministic hook double-checking the highest-severity allergens before any checkout URL is emitted.

Unofficial community skill built on DoorDash's doordash-oss/doordash-cli.

Honest limits (state these to the user on first use)

  • Matching is heuristic, against item names/descriptions from cart show output plus a synonyms table. It cannot see full ingredient lists and knows nothing about cross-contamination in the kitchen.
  • It is a tripwire against agent mistakes, not a medical device. The DoorDash payment page — where the human reviews the real order — is the documented final check.
  • False positives are accepted by design: blocking a safe ponzu bowl is cheap; the reverse is not. Hook matching is substring-based (short allergen names like "oat" can match inside "goat cheese") — annoying, never dangerous.
  • The references/allergen-synonyms.md table is intentionally broader than the compact synonym subset hardcoded in the checkout-gate hooks; adding a synonym to the reference doc alone does not change what the hooks enforce.

Components in this bundle

PieceRole
this skillvetting protocol + profile management
references/allergen-synonyms.mdhidden-allergen lookup table
hook doordash/doordash-allergy-checkout-gatedeterministic re-check at checkout
command /doordash-profilemanage the dietary profile interactively

State

  • ~/.claude/doordash-profile/dietary.json — the profile. Structure:
{
  "people": {
    "me": {
      "allergens": [
        { "name": "peanut", "severity": "anaphylaxis" },
        { "name": "shellfish", "severity": "avoid" }
      ],
      "diets": ["vegetarian"],
      "dislikes": ["cilantro"]
    },
    "sam": { "allergens": [{ "name": "egg", "severity": "avoid" }], "diets": [], "dislikes": [] }
  }
}

Severity tiers: anaphylaxis (hook-enforced, never overridable in-session), avoid (requires explicit human acknowledgment to keep the item), preference (mention it, don't gate on it).

  • ~/.claude/doordash-profile/vetted/<cart-uuid>.json — one dump per vetted cart: the full raw cart show output plus your verdict and a timestamp. The checkout hook greps this artifact — it trusts the dump, not your claim.

Protocol

Session start

Read dietary.json. Missing → offer to create it interactively (or via /doordash-profile). If the user is ordering for others ("lunch for me and Sam"), make sure each eater exists in the profile or ask for their restrictions.

After EVERY cart mutation (add-items / remove-item / reorder)

  1. Run dd-cli cart show --cart-uuid <X> and capture the full output.
  2. Check every line against each relevant eater's profile — direct matches AND hidden sources from references/allergen-synonyms.md (satay→peanut, aioli→egg, ponzu→soy+fish, …).
  3. On a conflict:
    • anaphylaxis → remove the item (dd-cli cart remove-item) and tell the user why. Do not offer to keep it.
    • avoid → present the conflict; keep only with explicit acknowledgment.
    • preference → mention it in passing.
  4. Items whose name is too opaque to judge ("Chef's Special #3") → mark UNVERIFIED and require the user's explicit sign-off for eaters with anaphylaxis entries.
  5. Write the vetted dump: full cart show output + verdict + ISO timestamp to ~/.claude/doordash-profile/vetted/<cart-uuid>.json. Without this file the checkout hook blocks — vetting is not optional.

At checkout

Just run dd-cli order checkout-url --cart-uuid <X> (or the dd-guard wrapper when doordash-spend-guard is installed — the two gates compose). The hook independently verifies: dump exists, is newer than the last cart mutation it saw, and contains no anaphylaxis-tier keyword. If it blocks, do NOT try to work around it — fix the cart, re-vet, and explain to the user what tripped.

Rules

  • Never edit dietary.json from the shell; profile changes go through /doordash-profile (interactive, confirmed).
  • Never write a vetted dump without actually running cart show fresh — the dump IS the audit artifact.
  • When in doubt about an ingredient, doubt is a conflict.

Frequently asked questions about DoorDash Allergy Shield

Similar skills