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.
Send LinkedIn connection requests (one or MANY), optional note per person.
{"items":"array of { slug, note? }; one request each (max 20 per run, the excess is reported in skipped)"}{"sent":"int (how many went out ok)","total":"int","results":"array of { slug, sent, status, urn, note, response, error? }","skipped":"int (trimmed by the cap of 20)"}Sends connection requests in bulk, takes the slug that linkedin-search-people returns. Resolves in a single bridge call. The extractor lives as text in the site's localStorage (key linkedin-connect) 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.
WRITE-IRREVERSIBLE. Every successful call performs the real action and it cannot be undone from here. Confirm the target and the copy before calling.
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 The call itself reports NEEDS_STORE when the extractor is missing or out of date, only then do you store it (step 2) and call again.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 (linkedin-connect and linkedin-connect:ver), overwritten each store, versions never accumulate.
await (() => {
const KEY = "linkedin-connect", VER = "1";
const s = localStorage.getItem(KEY);
if (!s || localStorage.getItem(KEY + ":ver") !== VER) return 'NEEDS_STORE';
const fn = eval('(' + s + ')');
return fn(document, { items: [{ slug: "felipegoulu", note: "Saw your work on browser agents - would love to connect." }] });
})()
Returns one result per request, with sent counting the ones that went out. 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; a pre-eval await trips LinkedIn's CSP and the call fails.
NEEDS_STORE; persists until localStorage is cleared)While logged in at https://www.linkedin.com/feed/ (the JSESSIONID cookie must be present), 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 = "linkedin-connect", 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.
note is capped by LinkedIn at 300 characters. Invitations are rate-limited per account on LinkedIn's side, this skill caps a single run at 20, but your weekly quota is a separate, account-level limit.
NEEDS_STORE → extractor missing or version-mismatched in this browser; run step 2 once, then retry step 1.results[].error per item → that one request failed; the others still went out.re-auth / no JSESSIONID → no LinkedIn session in this browser; log in once.tool-broken → LinkedIn changed the API shape; recapture the extractor.{ "type": "json", "jsonPath": "sent" }