One .zip per skill. Inside: SKILL.md with the intent and the frontmatter, and the code that runs in the page.
Settings → Personalize → Skills. This is Cowork's own skill library, shared across every chat.
Click Add and choose the file you just downloaded. Cowork installs it once; no CLAUDE.md, no per-project setup.
The skill stays available in every session. Cowork runs it in your own Chrome, riding the session you are already signed into.
Search DoorDash for restaurants and stores by keyword, with rating, ETA and delivery fee.
{"query":"string (what to search, e.g. \"pizza\", \"chinese food\", \"tacos\")"}{"count":"int","query":"string","results":"array of { id, name, url, rating, reviews, distance (miles), eta (minutes), deliveryFee, deal, category ('restaurant'|'grocery/retail') }"}Searches stores by keyword. Each result's id is what doordash-get-menu takes as its storeId, the first step of the chain. Resolves in a single bridge call. The extractor lives as text in the site's localStorage (key doordash-search-stores) and is rebuilt on each call with synchronous eval. It is stored once and then persists across navigation and browser restarts, so on every run except the first it is already there.
Default action: just call (step 1). The call itself reports NEEDS_STORE when the extractor is missing or out of date, only then do you store it (step 2) and call again.
Versioning. The stored extractor is gated by VER (must match the version in the frontmatter above). Both snippets carry VER = "1", keep them in sync with the frontmatter. When evaluate.js changes, bump version and VER in both snippets: the next call sees the mismatch, returns NEEDS_STORE, and re-stores automatically. Storage stays at two keys (doordash-search-stores and doordash-search-stores:ver), overwritten each store, versions never accumulate.
await (() => {
const KEY = "doordash-search-stores", VER = "1";
const s = localStorage.getItem(KEY);
if (!s || localStorage.getItem(KEY + ":ver") !== VER) return 'NEEDS_STORE';
const fn = eval('(' + s + ')');
return fn(document, { query: "pizza" });
})()
Returns the matching stores. If it returns the string 'NEEDS_STORE', the extractor is missing or stale in this browser → do step 2 once, then run this exact call again.
Run this snippet verbatim. Never add an await before the eval, only the outer await is allowed.
Any doordash.com tab works, the extractor fetches everything itself and never reads the open page, so no navigation is needed. The tab only supplies the origin and session.
NEEDS_STORE; persists until localStorage is cleared)From any doordash.com tab, evaluate the following with the bridge, replacing <FN> with the contents of evaluate.js (the ( async (root, params) => { ... } ) function). Keep VER equal to the call snippet's:
(() => {
const KEY = "doordash-search-stores", VER = "1";
const fn = (<FN>);
localStorage.setItem(KEY, String(fn));
localStorage.setItem(KEY + ":ver", VER);
return 'stored';
})()
Returns "stored". The extractor passes through the model only here, once. Then go back to step 1.
Results are localised to the address on the session, so the same query returns different stores for different accounts. Roughly 10-15 stores per search; there is no pagination param.
NEEDS_STORE → extractor missing or version-mismatched in this browser; run step 2 once, then retry step 1.results with a live tab → DoorDash changed the search markup, or the query matched nothing at the session address.{ "type": "json", "jsonPath": "count" }