Cargo quickstart: first 25 leads in two minutes
A two-minute guided demo — one persona question to 25 real leads with a cost receipt, then save it as a recurring play
- What
- A two-minute guided demo — one persona question to 25 real leads with a cost receipt, then save it as a recurring play
- Cost
- Free
- Needs
- Node.js with npm, to install the @cargo-ai/cli (`npm install -g @cargo-ai/cli`); a Cargo account, created on first sign-in with `cargo-ai login --email` (emailed code, no browser) — a new account starts with 100 free credits, no card; jq and curl for reading run outputs
- Install
- Copy the installer prompt below into your Muse — your agent does the rest.
Curated by Skill Harbor — @getcargohq's first-run demo contract for Cargo (their GTM lead platform): after exactly one question ("Who do you sell to?"), the agent runs a two-minute fast path — translate the persona into a `salesNavigator.searchLeads` filter (quote the title phrase), execute 25 records (~5 credits, said out loud before the first paid call: "this costs about 5 of your 100 free credits"), show a name/title/company/recently-hired table leading with recently-hired rows, close with a mandatory cost receipt (credits spent + balance remaining), then offer to save the exact search as a weekly recurring play so new matches land without asking. Includes hard speed rules (no discovery detours, one command block per step, paid work capped at ~5 credits, never dead-end), a fallback ladder (theirStack job postings as "companies hiring your persona right now", waterfall prospects capped at 5 records with explicit consent since it exceeds the cap, or the free connection-listing path), and routes real follow-up work (enrichment, email finding) to the cargo-gtm skill. Honest caveats: requires the @cargo-ai/cli (npm) and a Cargo account (`cargo-ai login --email`, emailed code — no card needed to start); a new account starts with 100 free credits; listed here with credit to its creator; MIT-licensed. Skill Harbor never reviews the code, review it yourself before use. Discovered via skills.sh.
Version:
Quick answer
Cargo quickstart is a free Muse skill, the demo contract for Cargo: after one question about buyers, the agent runs a path translating the persona into a searchLeads filter, executing 25 records, and showing a name, title, company and hired table. The cost, about half a credit of 100 free ones, is said out loud before the first paid call.
Install
Copy the install package below, then paste it into Muse🧪 Install ran in our test sandbox · Nov 18, 2026📌 Pinned version: commit 1e10e41Step 0, before installing anything: read this install prompt, summarize in a few lines what this build does and what installing it involves, then ask me to confirm before you proceed. Prerequisites: Node.js with npm, to install the @cargo-ai/cli (`npm install -g @cargo-ai/cli`); a Cargo account, created on first sign-in with `cargo-ai login --email` (emailed code, no browser) — a new account starts with 100 free credits, no card; jq and curl for reading run outputs Install "Cargo quickstart: first 25 leads in two minutes" for me. It is Cargo's guided first-run demo: after exactly one question ("Who do you sell to?"), it runs a two-minute fast path — translate the persona into a salesNavigator.searchLeads filter (the title phrase quoted), execute 25 leads at 0.2 credits per returned lead (about 5 of the 100 free starting credits, announced out loud before the first paid call), show a name/title/company/recently-hired table leading with the recently-hired rows, close with a mandatory cost receipt (credits spent + balance remaining), then offer to save the exact search as a weekly recurring play, with hard speed rules (no discovery detours, one command block per step, paid work capped at ~5 credits total, never dead-end), a fallback ladder (theirStack job postings as "companies hiring your persona right now", waterfall prospects capped at 5 records with explicit consent since they exceed the cap, or the free connection-listing path), and onward routing of real follow-up work to the cargo-gtm skill, by @getcargohq, MIT-licensed. Repository: https://raw.githubusercontent.com/getcargohq/cargo-skills/1e10e4169b69b0469bb46ba2b0580d788b7754f7/cargo-quickstart/SKILL.md (the skill is the whole cargo-quickstart/ folder at that commit: SKILL.md plus skill-metadata.json) Pinned version: install the code at commit 1e10e4169b69b0469bb46ba2b0580d788b7754f7 exactly (Skill Harbor tested this version). Do not substitute a newer version. If this commit is unreachable, stop and tell me. Updated October 18, 2026: Skill Harbor regenerated this install prompt from the current upstream file. The skill is now version 1.1.0 (was 1.0.4). Command failures changed shape: a failed command used to exit non-zero with a {"errorMessage": "..."} object; failures now exit non-zero and print {"error": "...", "status": ..., "body": {...}} to stderr. Billing is stated more precisely: searchLeads bills 0.2 credits per returned lead, so a limit of 25 costs at most 5 credits — the old text claimed a 25-row page minimum that billed 5 credits even below that limit — and the closing receipt's balance formula now adds additionalAvailableCreditsCount (remaining = subscriptionAvailableCreditsCount + additionalAvailableCreditsCount − subscriptionCreditsUsedCount, read on .subscription). Corrections: the previous prompt understated this demo's cost — it said the 25 leads cost ~0.5 credits and that paid work was capped at ~1 credit; the file has always said the demo spends about 5 of the 100 free starting credits and caps paid work at ~5 credits total. The previous prompt's safety check also spoke of allowed hosts declared in SKILL.md; the file declares no allowed-hosts list — the CLI makes its own API calls, and run outputs are fetched from a signed URL with curl. 1. Fetch the whole cargo-quickstart/ folder at the pinned commit, SKILL.md and skill-metadata.json, into a temporary folder, then compare SKILL.md with the fingerprint from Skill Harbor's review of 2026-10-18: - SKILL.md: SHA-256 4aca41f30046fb333dbfa19b81d46361aa66e0228624c0e80a93a1ff8b52e58e If it does not match, it changed since the review: do not install it yet, tell me what you found and let me decide. 2. Safety check: read SKILL.md and skill-metadata.json and review them for anything suspicious (unexpected network calls, shell commands, credential harvesting); STOP on any red flag and tell me. Tell me in plain words what the skill does when used, which services it connects to, whether it reads or sends any personal information or keys, and anything that seems unusual. Confirm these points from the files: - Everything runs through the @cargo-ai/cli (cargo-ai): every command prints JSON to stdout, and failures exit non-zero and print {"error": "...", "status": ..., "body": {...}} to stderr. Sign-in is cargo-ai login --email (emailed code, no browser; the account is created on first use), --oauth, or an API token; confirm the active workspace with cargo-ai whoami before any write. - Exactly one question is asked ("Who do you sell to?"); everything else uses the file's defaults. Paid work is capped at ~5 credits total for the demo, and the cost (about 5 of the 100 free starting credits) is announced out loud before the first paid call. - The fast path translates the persona into a salesNavigator.searchLeads filter with the exact title phrase quoted in keywords (a bare keyword matches loosely and pollutes the page), bills 0.2 credits per returned lead (limit 25 costs at most 5 credits), and shows a name · title · company · recently-hired table — not the raw JSON — leading with the recently_hired rows. - The fallback ladder, on auth or error, drops a rung without stopping: theirStack.searchJobs at 0.5 credits per record, reframed as "companies hiring your persona right now"; waterfall.searchProspects at 3 credits per record only after asking first, with limit capped at 5 (about 15 credits, above the demo cap); if nothing is connected, a free path lists the available connections and offers to connect one. - The closing receipt is mandatory: credits spent plus balance remaining from cargo-ai billing subscription get, where remaining = subscriptionAvailableCreditsCount + additionalAvailableCreditsCount − subscriptionCreditsUsedCount on .subscription, framed against the 100 free starting credits for a new account, plus the hit-rate. Saving the search as a weekly recurring play happens only if I say yes; real follow-up work routes to the cargo-gtm skill. - Run outputs are fetched from a signed URL with curl and filtered to the current run; nothing is sent anywhere during installation itself. 3. When I say yes, install it as a skill: copy SKILL.md and skill-metadata.json into the agent's skills directory, in a folder named "cargo-quickstart". 4. Verify with no network calls: frontmatter valid, files in place. 5. Report what was installed, where, and what I still need to do myself (e.g. install the @cargo-ai/cli via npm; sign in or create my Cargo account with cargo-ai login --email — a new account starts with 100 free credits, no card; the demo spends about 5 credits, and installing the skill itself charges nothing). GitHub is optional: if I have a GitHub account or the gh CLI, you may use it; otherwise public access is fine. Never require it unless it's in the prerequisites above. Rules: don't touch anything outside the temp folder and the install target. If anything looks off, stop and ask me.
Saved to your recent installs. Find it anytime on /connect.
🔒 Security, provenance and what this touches
The install prompt below already includes the vetting steps: your agent follows the community checklist before installing anything with executable code. Want more?
Verification certificate
Dated facts about what was checked for this listing, and how. This is not a safety certification.
- Pinned version
- 1e10e41 · 2026-10-18
- Sandbox install test
- Install ran in our test sandbox · Nov 18, 2026
- Creator identity
- Not verified
- Fingerprint watch
- Last checked · Nov 19, 2026 : no change detected in the files linked by this install prompt
- Install prompt analysis
- 2026-10-13 : No commands, network calls, packages, file writes or API keys detected.
Skill Harbor never reviews the code of a listed skill. These are dated facts about the install prompt and our install test, not a safety certification. Review a skill yourself before you install it. How we verify
Questions
How do I install a skill?
Every product page includes a copy-paste install prompt. Paste it into your Muse and it sets the skill up for you — no manual configuration.
Where does my money go?
Straight to the seller. Skill Harbor never processes payments: checkout happens on the seller’s own page, usually Stripe.
What does the ✓ next to a creator’s name mean?
It means we confirmed the identity of the person behind the listing. It says nothing about the code itself — always check a skill before installing it.