DoorDash Order Playbooks
SkillCloud & infradoordash-order-playbooks is a skill that stores named, context-bound saved DoorDash orders such as "post-gym" or "late-night deploy" and recalls them through the DoorDash CLI (dd-cli). When someone says "order my post-gym bowl" or "the usual", the agent pulls up the matching playbook, shows a cart-diff, and only then hands over a checkout link.
Use DoorDash Order Playbooks in Claude, ChatGPT or Ahel Desktop
Free. Sign in, add DoorDash Order Playbooks and connect your AI. About a minute.
Also: Claude Code · Cursor · Codex
Then ask your AI: use the DoorDash Order Playbooks skill
Details
Instructions available. Your AI can read the instructions. Execution depends on the setup they require.
Account requirements not reviewed. Check the skill instructions before use; ahel provides instructions and does not run this skill.
No other account needed.
Have the DoorDash CLI (dd-cli) available so the skill can recall orders through it.
What your AI can do with it
- Save named DoorDash orders bound to a context, like "post-gym" or "Friday ramen"
- Recall a saved order from casual phrases such as "the usual"
- Recall orders through the DoorDash CLI (dd-cli)
- Show a mandatory cart-diff before any checkout link is produced
- Hand over a checkout link only after the cart-diff is confirmed
Getting started
- Have the DoorDash CLI (dd-cli) available so the skill can recall orders through it.
- Add the doordash-order-playbooks skill to your agent.
- Save an order by giving it a name and a context, for example "post-gym" or "late-night deploy".
- Ask for it in plain language, like "order my post-gym bowl" or "the usual", and review the cart-diff before using the checkout link.
What this skill tells your AI
The instructions your AI receives, as published by davila7/claude-code-templates in cli-tool/components/skills/doordash/doordash-order-playbooks/SKILL.md and read by ahel’s review.
Saved orders with names and contexts, recalled safely. A playbook maps a
human name ("post-gym", "late-night deploy", "Friday ramen") to a concrete
DoorDash order that can be rebuilt with dd-cli order reorder — plus enough
stored detail to detect drift (menu changes, price hikes, substitutions)
before the user is ever handed a checkout link.
Unofficial community skill built on DoorDash's
doordash-oss/doordash-cli.dd-climust be installed, on PATH, and logged in (dd-cli login).
Why this exists
dd-cli order history already lists past orders — but Claude has no
cross-session memory of which order is "the post-gym one", and plain
reordering silently accepts whatever the restaurant's menu says today:
substituted items, missing items, higher prices. This skill stores the
mapping AND makes a cart-diff against the stored baseline mandatory
before emitting any checkout URL. Silent drift becomes a caught event.
State
Single JSON file: ~/.claude/dd-cli/playbooks.json
{
"playbooks": {
"post-gym": {
"order_uuid": "<uuid from dd-cli order history>",
"restaurant": "Sweetgreen",
"items_summary": [
{ "name": "Harvest Bowl", "qty": 1, "price": 13.95 },
{ "name": "Lemonade", "qty": 1, "price": 3.5 }
],
"baseline_total": 17.45,
"tolerance_pct": 10,
"contexts": ["post-gym", "gym", "workout"],
"last_used": "2026-07-19",
"times_used": 4
}
},
"preflight": { "verified": false, "notes": "" }
}
Create the directory and file on first use (mkdir -p ~/.claude/dd-cli).
Prices are pre-fee subtotals — say so when presenting totals.
Preflight (first use only — REQUIRED)
This skill assumes dd-cli order reorder --order-uuid Y returns a cart-uuid
that cart show and order checkout-url accept. That handoff is
load-bearing and must be verified empirically once per install:
- Run
dd-cli order reorder --helpanddd-cli order checkout-url --helpto confirm flags. - On the first real recall, after running
reorder, confirm the output contains a cart-uuid and thatdd-cli cart show --cart-uuid <it>works. - Record the outcome in
preflight.verified(+ any format notes inpreflight.notes) so future sessions skip this step.
If the handoff does NOT work as assumed, fall back to rebuilding the cart
manually (dd-cli search → cart add-items) and record that in
preflight.notes.
Flow 1 — Recall (the main flow)
User says something like "order my post-gym bowl" / "the usual after the gym":
-
Match: fuzzy-match the request against playbook names and
contexts. Ambiguous → ask. No match → offer Flow 2 (capture) instead. -
Rebuild:
dd-cli order reorder --order-uuid <stored uuid>. Capture the cart-uuid from the output. -
MANDATORY diff: run
dd-cli cart show --cart-uuid <cart-uuid>and compare against the storeditems_summary+baseline_total:Stored Current Harvest Bowl $13.95 $14.95 ⬆ Lemonade $3.50 ❌ missing Subtotal $17.45 $14.95 Present the diff table to the user. Never skip this step, even when everything matches — say "matches your baseline" explicitly.
-
Gate: if items are missing/substituted, or the subtotal exceeds
baseline_totalby more thantolerance_pct, STOP and ask the user how to proceed (accept, edit cart viacart remove-item/cart add-items, or abort). Do NOT hand over a checkout link silently. -
Checkout: only after the diff is shown (and approved when the gate tripped):
dd-cli order checkout-url --cart-uuid <cart-uuid>. Hand the URL to the user — payment always happens on the DoorDash page, by the human. -
Update: bump
last_used/times_used; if the user accepted new prices, offer to refreshitems_summaryandbaseline_total.
Flow 2 — Capture
After ANY completed order (via playbook or bespoke), offer once — don't nag: "Want to save this as a playbook?" If yes:
dd-cli order history— take the most recent order's uuid.- Ask for a name and optional context words ("when should I suggest this?").
- Write the entry with
items_summaryandbaseline_totalfrom the cart that was just built (or from the history entry if it shows detail). - Default
tolerance_pct: 10.
Flow 3 — Staleness / self-heal
When order reorder fails or the diff shows the restaurant no longer offers
the stored items:
- Tell the user the playbook is stale and why.
dd-cli search --query "<restaurant name>"— confirm the restaurant still exists on DoorDash. Gone → offer to retire the playbook or find a replacement.- Rebuild an equivalent cart (
cart add-items, navigating with--helpas needed), confirm with the user, and after a successful checkout-url handoff refresh the playbook'sorder_uuidfromdd-cli order history.
Rules
- Never emit a checkout URL without showing the diff first. This is the contract of the skill.
- Read uuids from real command output; never fabricate or guess them.
- One capture offer per order, max. Respect a "no".
- Totals you can verify are pre-fee subtotals; final totals (fees, tip, tax) appear only on the DoorDash payment page. Say so.
- If
dd-clireports auth/waitlist errors, stop and tell the user to rundd-cli login— don't retry in a loop.
Signals
- GitHub stars
- 32k
- Forks
- 4k
- Last commit
- Oct 2026
Questions
- How do I reorder something I order often?
- Save it once as a named playbook, then say the name or a casual phrase like "the usual". The agent recalls the order, shows a cart-diff, and gives you a checkout link after you review it.
- Can I skip the cart-diff?
- No. The cart-diff is mandatory before any checkout link is handed over, so you always see what changed in the cart first.
- What counts as a saved order name?
- Any short, context-bound label you choose, such as "post-gym", "late-night deploy", or "my Friday ramen".
- Does it place the order for me?
- It hands over a checkout link after the cart-diff; the item does not describe completing the order automatically.
Advanced
- Item type
- skill
- Key
doordash-order-playbooks- Source
- github.com/davila7/claude-code-templates
github.com/davila7/claude-code-templates
More in Cloud & infra
Skill · vercel-labs
More in Cloud & infravercel-react-best-practices
Skill · vercel-labs
More in Cloud & infraturborepo
Skill · vercel
More in Cloud & inframicrosoft-foundry
Skill · microsoft
More in Cloud & infraazure-diagnostics
Skill · microsoft
More in Cloud & infrauncloud
Skill · affaan-m
More in Cloud & infra