{"id":"060a7e91-a5a6-432e-9e6d-edbb5e7804e8","entityType":"agent","slug":"clawhub-cargo-ai-cargo-quickstart","name":"cargo-quickstart","canonicalUrl":"https://www.xpersona.co/agent/clawhub-cargo-ai-cargo-quickstart","canonicalPath":"/agent/clawhub-cargo-ai-cargo-quickstart","generatedAt":"2026-10-12T18:25:37.666Z","source":"CLAWHUB","claimStatus":"UNCLAIMED","verificationTier":"NONE","summary":{"evidence":{"source":"editorial-content","verified":true,"confidence":"high","updatedAt":"2026-10-11T22:02:19.829Z","emptyReason":null},"description":"Guided first-run demo for Cargo — one persona question to 25 real leads with a cost receipt in under two minutes, ending by saving the pull as a recurring play. Triggers: \"show me what Cargo can do\", \"give me a demo\", \"take me on a tour\", \"quickstart\", \"getting started with Cargo\", \"I just installed Cargo\", \"my workspace is empty\", \"does this actually work\". Skip when: the user has a real job to run (build a list, enrich a CSV, find emails) — use cargo-gtm; when they want CLI reference or routing — use the cargo router skill. Skill: cargo-quickstart Owner: cargo-ai Summary: Guided first-run demo for Cargo — one persona question to 25 real leads with a cost receipt in under two minutes, ending by saving the pull as a recurring play. Triggers: \"show me what Cargo can do\", \"give me a demo\", \"take me on a tour\", \"quickstart\", \"getting started with Cargo\", \"I just installed Cargo\", \"my workspace is empty\", \"does this actually work\". Skip when:","descriptionLabel":"Technical summary","evidenceSummary":"Capability contract not published. No trust telemetry is available yet. 987 downloads reported by the source. Last updated 10/11/2026.","installCommand":"clawhub skill install s178dcd9wkfn0a2fqrygmt3jzn87j9e1:cargo-quickstart","sourceUrl":"https://clawhub.ai/cargo-ai/cargo-quickstart","homepage":"https://clawhub.ai/cargo-ai/skills/cargo-quickstart","primaryLinks":[{"label":"View on ClawHub","url":"https://clawhub.ai/cargo-ai/cargo-quickstart","kind":"source"},{"label":"Homepage","url":"https://clawhub.ai/cargo-ai/skills/cargo-quickstart","kind":"homepage"}],"safetyScore":84,"overallRank":62,"popularityScore":60,"trustScore":null,"claimedByName":null,"isOwner":false,"seoDescription":"Guided first-run demo for Cargo — one persona question to 25 real leads with a cost receipt in under two minutes, ending by saving the pull as a recurring play."},"coverage":{"evidence":{"source":"public-profile","verified":false,"confidence":"medium","updatedAt":"2026-10-11T22:02:19.829Z","emptyReason":null},"protocols":[{"protocol":"OPENCLEW","label":"OpenClaw","status":"self-declared","notes":"Declared in the public agent profile."}],"capabilities":[],"verifiedCount":0,"selfDeclaredCount":1,"capabilityMatrix":{"rows":[{"key":"OPENCLEW","type":"protocol","support":"unknown","confidenceSource":"profile","notes":"Listed on profile"}],"flattenedTokens":"protocol:OPENCLEW|unknown|profile"}},"adoption":{"evidence":{"source":"CLAWHUB","verified":false,"confidence":"medium","updatedAt":"2026-10-11T22:02:19.829Z","emptyReason":null},"stars":null,"forks":null,"downloads":987,"likes":null,"task":null,"library":null,"packageName":null,"latestVersion":"1.0.4","tractionLabel":"987 downloads"},"release":{"evidence":{"source":"CLAWHUB","verified":false,"confidence":"medium","updatedAt":"2026-10-11T22:02:19.763Z","emptyReason":null},"lastUpdatedAt":"2026-10-11T22:02:19.829Z","lastCrawledAt":"2026-10-11T22:02:19.763Z","lastIndexedAt":null,"nextCrawlAt":"2026-10-12T22:02:19.763Z","lastVerifiedAt":null,"highlights":[{"version":"1.0.4","createdAt":"2026-10-02T18:35:17.726Z","changelog":"- Updated demo pricing to reflect new cost: now spends about 5 credits for 25 leads (was 0.5 credits). - Adjusted per-lead cost in documentation: salesNavigator.searchLeads now bills 0.2 credits per record (was 0.02 credits). - Raised overall demo credit cap from ~1 to ~5 credits; updated fallback ladder and copy accordingly. - SKILL.md and metadata refreshed to match new pricing and usage guidance. - Removed outdated skill-card.md file.","fileCount":4,"zipByteSize":5547},{"version":"1.0.3","createdAt":"2026-09-02T23:42:23.266Z","changelog":"- Bumped version to 1.0.3. - Removed skill-card.md file. - Minor metadata and maintenance updates; no changes to usage or UX.","fileCount":4,"zipByteSize":5745},{"version":"1.0.2","createdAt":"2026-08-27T23:45:00.245Z","changelog":"- New users are now explicitly told about the 100 free credits on signup, and the demo’s cost (~0.5 credits) is communicated before running. - Added CLI bootstrap steps for new accounts, with alternative login options and notes on global install. - Cost receipt now frames the balance as \"of your 100 free credits left\" to improve clarity and user trust. - Updated triggers and skip conditions in the description for improved activation and routing clarity. - Removed the file skill-card.md.","fileCount":4,"zipByteSize":5626},{"version":"1.0.1","createdAt":"2026-08-11T21:42:36.990Z","changelog":"- Added skill-metadata.json for improved metadata handling. - Removed outdated skill-card.md. - Updated SKILL.md to clarify sign-in options: users can now sign in (or create an account) using cargo-ai login --email, --oauth, or an API token; browser sign-in is no longer required. - Minor version bump to 1.0.1 for these documentation and onboarding improvements.","fileCount":4,"zipByteSize":5047},{"version":"1.0.0","createdAt":"2026-07-10T00:54:22.038Z","changelog":"cargo-quickstart 1.0.0 - Launches a guided first-run demo of the Cargo CLI, rapidly sourcing ~25 buyer-persona-matched leads including a cost receipt. - Demo is tightly timed (<2 minutes), asks only one user question (\"Who do you sell to?\"), and auto-selects all other parameters. - Follows a strict fallback ladder to ensure the demo always completes, even if some data sources are unavailable. - Concludes by offering to save the pull as an automated recurring play, immediately demonstrating value beyond a one-off result. - Provides a clear receipt of credits spent and leads returned, with direct suggestions for next steps.","fileCount":3,"zipByteSize":4510}]},"execution":{"evidence":{"source":"CLAWHUB","verified":false,"confidence":"low","updatedAt":null,"emptyReason":"No published capability contract is available yet."},"installCommand":"clawhub skill install s178dcd9wkfn0a2fqrygmt3jzn87j9e1:cargo-quickstart","setupComplexity":"low","setupSteps":["Setup complexity is LOW. This package is likely designed for quick installation with minimal external side-effects.","Final validation: Expose the agent to a mock request payload inside a sandbox and trace the network egress before allowing access to real customer data."],"contract":{"contractStatus":"missing","authModes":[],"requires":[],"forbidden":[],"supportsMcp":false,"supportsA2a":false,"supportsStreaming":false,"inputSchemaRef":null,"outputSchemaRef":null,"dataRegion":null,"contractUpdatedAt":null,"sourceUpdatedAt":null,"freshnessSeconds":null},"invocationGuide":{"preferredApi":{"snapshotUrl":"https://www.xpersona.co/api/v1/agents/clawhub-cargo-ai-cargo-quickstart/snapshot","contractUrl":"https://www.xpersona.co/api/v1/agents/clawhub-cargo-ai-cargo-quickstart/contract","trustUrl":"https://www.xpersona.co/api/v1/agents/clawhub-cargo-ai-cargo-quickstart/trust"},"curlExamples":["curl -s \"https://www.xpersona.co/api/v1/agents/clawhub-cargo-ai-cargo-quickstart/snapshot\"","curl -s \"https://www.xpersona.co/api/v1/agents/clawhub-cargo-ai-cargo-quickstart/contract\"","curl -s \"https://www.xpersona.co/api/v1/agents/clawhub-cargo-ai-cargo-quickstart/trust\""],"jsonRequestTemplate":{"query":"summarize this repo","constraints":{"maxLatencyMs":2000,"protocolPreference":["OPENCLEW"]}},"jsonResponseTemplate":{"ok":true,"result":{"summary":"...","confidence":0.9},"meta":{"source":"CLAWHUB","generatedAt":"2026-10-12T18:25:37.665Z"}},"retryPolicy":{"maxAttempts":3,"backoffMs":[500,1500,3500],"retryableConditions":["HTTP_429","HTTP_503","NETWORK_TIMEOUT"]}},"endpoints":{"dossierUrl":"https://www.xpersona.co/api/v1/agents/clawhub-cargo-ai-cargo-quickstart/dossier","snapshotUrl":"https://www.xpersona.co/api/v1/agents/clawhub-cargo-ai-cargo-quickstart/snapshot","contractUrl":"https://www.xpersona.co/api/v1/agents/clawhub-cargo-ai-cargo-quickstart/contract","trustUrl":"https://www.xpersona.co/api/v1/agents/clawhub-cargo-ai-cargo-quickstart/trust"}},"reliability":{"evidence":{"source":"runtime-metrics","verified":false,"confidence":"low","updatedAt":null,"emptyReason":"No trust, reliability, or runtime telemetry is available."},"trust":{"status":"unavailable","handshakeStatus":"UNKNOWN","verificationFreshnessHours":null,"reputationScore":null,"p95LatencyMs":null,"successRate30d":null,"fallbackRate":null,"attempts30d":null,"trustUpdatedAt":null,"trustConfidence":"unknown","sourceUpdatedAt":null,"freshnessSeconds":null},"decisionGuardrails":{"doNotUseIf":["Contract metadata is missing or unavailable for deterministic execution."],"safeUseWhen":[],"riskFlags":["missing_or_unavailable_contract","trust_data_unavailable","schema_references_missing"],"operationalConfidence":"low"},"executionMetrics":{"observedLatencyMsP50":null,"observedLatencyMsP95":null,"estimatedCostUsd":null,"uptime30d":null,"rateLimitRpm":null,"rateLimitBurst":null,"lastVerifiedAt":null,"verificationSource":null},"runtimeMetrics":{"successRate":null,"avgLatencyMs":null,"avgCostUsd":null,"hallucinationRate":null,"retryRate":null,"disputeRate":null,"p50Latency":null,"p95Latency":null,"lastUpdated":null}},"benchmarks":{"evidence":{"source":"no-benchmark-data","verified":false,"confidence":"low","updatedAt":null,"emptyReason":"No benchmark suites or observed failure patterns are available."},"suites":[],"failurePatterns":[]},"artifacts":{"evidence":{"source":"CLAWHUB","verified":false,"confidence":"high","updatedAt":"2026-10-11T22:02:19.829Z","emptyReason":null},"readme":"Skill: cargo-quickstart\n\nOwner: cargo-ai\n\nSummary: Guided first-run demo for Cargo — one persona question to 25 real leads with a cost receipt in under two minutes, ending by saving the pull as a recurring play. Triggers: \"show me what Cargo can do\", \"give me a demo\", \"take me on a tour\", \"quickstart\", \"getting started with Cargo\", \"I just installed Cargo\", \"my workspace is empty\", \"does this actually work\". Skip when: the user has a real job to run (build a list, enrich a CSV, find emails) — use cargo-gtm; when they want CLI reference or routing — use the cargo router skill.\n\nTags: latest:1.0.4\n\nVersion history:\n\nv1.0.4 | 2026-10-02T18:35:17.726Z | auto\n\n- Updated demo pricing to reflect new cost: now spends about 5 credits for 25 leads (was 0.5 credits).\n- Adjusted per-lead cost in documentation: salesNavigator.searchLeads now bills 0.2 credits per record (was 0.02 credits).\n- Raised overall demo credit cap from ~1 to ~5 credits; updated fallback ladder and copy accordingly.\n- SKILL.md and metadata refreshed to match new pricing and usage guidance.\n- Removed outdated skill-card.md file.\n\nv1.0.3 | 2026-09-02T23:42:23.266Z | auto\n\n- Bumped version to 1.0.3.\n- Removed skill-card.md file.\n- Minor metadata and maintenance updates; no changes to usage or UX.\n\nv1.0.2 | 2026-08-27T23:45:00.245Z | auto\n\n- New users are now explicitly told about the 100 free credits on signup, and the demo’s cost (~0.5 credits) is communicated before running.\n- Added CLI bootstrap steps for new accounts, with alternative login options and notes on global install.\n- Cost receipt now frames the balance as \"of your 100 free credits left\" to improve clarity and user trust.\n- Updated triggers and skip conditions in the description for improved activation and routing clarity.\n- Removed the file skill-card.md.\n\nv1.0.1 | 2026-08-11T21:42:36.990Z | auto\n\n- Added skill-metadata.json for improved metadata handling.\n- Removed outdated skill-card.md.\n- Updated SKILL.md to clarify sign-in options: users can now sign in (or create an account) using cargo-ai login --email, --oauth, or an API token; browser sign-in is no longer required.\n- Minor version bump to 1.0.1 for these documentation and onboarding improvements.\n\nv1.0.0 | 2026-07-10T00:54:22.038Z | auto\n\ncargo-quickstart 1.0.0\n\n- Launches a guided first-run demo of the Cargo CLI, rapidly sourcing ~25 buyer-persona-matched leads including a cost receipt.\n- Demo is tightly timed (<2 minutes), asks only one user question (\"Who do you sell to?\"), and auto-selects all other parameters.\n- Follows a strict fallback ladder to ensure the demo always completes, even if some data sources are unavailable.\n- Concludes by offering to save the pull as an automated recurring play, immediately demonstrating value beyond a one-off result.\n- Provides a clear receipt of credits spent and leads returned, with direct suggestions for next steps.\n\nArchive index:\n\nArchive v1.0.4: 4 files, 5547 bytes\n\nFiles: skill-card.md (2039b), skill-metadata.json (449b), SKILL.md (7621b), _meta.json (135b)\n\nFile v1.0.4:SKILL.md\n\n---\nname: cargo-quickstart\ndescription: \"Guided first-run demo for Cargo — one persona question to 25 real leads with a cost receipt in under two minutes, ending by saving the pull as a recurring play. Triggers: \\\"show me what Cargo can do\\\", \\\"give me a demo\\\", \\\"take me on a tour\\\", \\\"quickstart\\\", \\\"getting started with Cargo\\\", \\\"I just installed Cargo\\\", \\\"my workspace is empty\\\", \\\"does this actually work\\\". Skip when: the user has a real job to run (build a list, enrich a CSV, find emails) — use cargo-gtm; when they want CLI reference or routing — use the cargo router skill.\"\nversion: \"1.0.4\"\ncompatibility: Requires @cargo-ai/cli (npm). Sign in or create an account with `cargo-ai login --email` (emailed code, no browser), `--oauth`, or an API token\nhomepage: https://github.com/getcargohq/cargo-skills\nmetadata:\n  author: getcargo\n  openclaw:\n    requires:\n      bins:\n        - cargo-ai\n    install:\n      - kind: node\n        package: \"@cargo-ai/cli@latest\"\n        bins:\n          - cargo-ai\n    homepage: https://github.com/getcargohq/cargo-skills\n---\n\n# Cargo Quickstart — first value in two minutes\n\nOne guided demo: pull ~25 fresh leads matching a buyer persona the user picks, show the cost receipt, then save the pull as a recurring play. The point is not the list — it's that in minute 3 the user owns a running system, not a one-off result.\n\n**A new account starts with 100 free credits — no card.** This demo spends about **5** of them. Say that out loud before the first paid call (\"this costs about 5 of your 100 free credits\"): it converts the moment from *a purchase decision* into *a look around*, which is the whole job of a quickstart. Never let a new user think the demo is why they'd run out.\n\n## Bootstrap\n\nAlready signed in (`cargo-ai whoami` returns a workspace)? Skip to the next section.\n\n```bash\nnpm install -g @cargo-ai/cli            # no global install? prefix every command with `npx @cargo-ai/cli`\ncargo-ai login --email you@company.com  # emailed code, no browser; creates the account on first use\n                                        # alternatives: --oauth (browser) · --token <api-token> (CI)\ncargo-ai whoami                         # confirm the active workspace before any write\n```\n\nEvery command prints JSON to stdout; failures exit non-zero with `{\"errorMessage\": \"...\"}`. Anything that creates a run or a batch is async — pass `--wait-until-finished` or poll the matching `get`. When the full skill bundle is installed, [`../cargo/references/prerequisites.md`](../cargo/references/prerequisites.md) adds the CLI version pin, token scopes, and the admin-only surface.\n\n## The one question\n\nAsk exactly **one** question before doing anything:\n\n> **\"Who do you sell to?\"** (a persona in a few words — e.g. \"Heads of RevOps at mid-market SaaS\")\n\nEverything else — provider, filters, limits — you decide. Don't ask about output format, volume, or providers; defaults below.\n\n## Speed budget — HARD RULES\n\nThe demo has a two-minute budget from answer to deliverable. On the fast path:\n\n- **No discovery detours.** Do not run `cargo-ai --version`, `cargo-ai whoami`, `connection connector list`, or any exploratory command first. Auth problems will surface as errors on the first real call — handle them then.\n- **One command block per step**, no narration between commands.\n- **Paid work is capped at ~5 credits total.** The demo uses LinkedIn-native people search (`salesNavigator.searchLeads`, 0.2/record → 25 records ≈ 5 credits). Nothing else paid runs without asking.\n- **Never dead-end.** Every step has a fallback (ladder below). If a rung fails, drop one rung silently and keep moving.\n\n## Fast path\n\nTranslate the persona into a `searchLeads` filter (quote the exact title phrase in `keywords`; a bare keyword matches loosely and pollutes the page) and run:\n\n```bash\n# 1. Execute — returns a run object; note run.uuid and run.workflowUuid.\n#    searchLeads returns a 25-row page minimum (limit below 25 still bills 25 × 0.2 = 5 credits).\ncargo-ai orchestration action execute \\\n  --action '{\"kind\":\"connector\",\"integrationSlug\":\"salesNavigator\",\"actionSlug\":\"searchLeads\"}' \\\n  --data '{\"keywords\": \"\\\"<persona title phrase>\\\"\", \"limit\": 25}' \\\n  --wait-until-finished > /tmp/quickstart-run.json\n\n# 2. Fetch the output data (NOT in the execute stdout) — signed URL, then filter to THIS run\nRUN_UUID=$(jq -r '.run.uuid' /tmp/quickstart-run.json)\nWF_UUID=$(jq -r '.run.workflowUuid' /tmp/quickstart-run.json)\ncurl -s \"$(cargo-ai orchestration run download-outputs \\\n  --workflow-uuid \"$WF_UUID\" --output-node-slug action --format json | jq -r '.url')\" \\\n  > /tmp/quickstart-outputs.json\n\n# 3. Show the table (the file holds ALL of the workflow's runs — filter by _uuid;\n#    each row's .output is the leads array directly, fields are snake_case)\njq -r --arg u \"$RUN_UUID\" \\\n  '[.[] | select(._uuid==$u)][0].output[] | [.full_name, .job_title, .company_name, (.recently_hired // false)] | @tsv' \\\n  /tmp/quickstart-outputs.json | head -25\n```\n\nShow the table (name · title · company · recently-hired), not the raw JSON. `recently_hired: true` rows are the demo's headline — lead with them (\"6 of these 25 just started the job — the exact moment to reach out\").\n\n### Fallback ladder (on auth/error, drop a rung — don't stop)\n\n1. `salesNavigator.searchLeads` (0.2/record) — primary.\n2. `theirStack.searchJobs` (0.5) — reframe as \"companies hiring your persona right now\" (job postings for the persona's title). Same wow, different angle.\n3. `waterfall.searchProspects` (3/record) — **exceeds the ~5-credit demo cap, so this rung asks first**: \"The two cheap sources aren't connected; I can pull 5 matches via waterfall for ~15 credits instead — run it, or connect Sales Navigator first (free)?\" Run only on an explicit yes, with `limit` capped at 5.\n4. Nothing connected at all → run the free path: `cargo-ai connection integration list | head`, show what *could* be wired, and offer to connect one (browser auth) — the demo resumes after.\n\n## The receipt (mandatory, verbatim discipline)\n\nThe demo is itself the pilot from [`../cargo-gtm/references/cost-discipline.md`](../cargo-gtm/references/cost-discipline.md). Close it with a receipt:\n\n- Credits spent + balance remaining (`cargo-ai billing subscription get` — remaining = `subscriptionAvailableCreditsCount − subscriptionCreditsUsedCount`). For a brand-new account, frame it against the **100 free starting credits** rather than as a bare number — \"5 spent, 95 of your 100 free credits left\" lands very differently from \"95 credits remaining\".\n- Hit-rate: \"25 of 25 returned\" (or what actually came back, and which rows look off).\n\n## Minute 3 — save it as a play\n\nImmediately offer to make the pull recurring — this is the step that shows what Cargo *is*:\n\n> \"Want this to run by itself? I can save this exact search as a play that runs weekly and writes new matches into a model — new `<persona>` leads land without you asking.\"\n\nOn yes, follow [`../cargo-gtm/recipes/save-as-play.md`](../cargo-gtm/recipes/save-as-play.md) with the demo's action + filter as the workflow body and a weekly cron.\n\n## After the demo — route onward\n\nPropose 2–3 next steps grounded in the rows just pulled, per the next-step spec in [`../cargo-gtm/SKILL.md`](../cargo-gtm/SKILL.md) (§4): e.g. \"enrich these 25 with firmographics (~0.5 cr each)\", \"find + verify emails for the best 10 (~1.4 cr each)\", or something else entirely. From here, real GTM work belongs to [`cargo-gtm`](../cargo-gtm/SKILL.md) — read it before anything beyond the demo.\n\nFile v1.0.4:_meta.json\n\n{\n  \"ownerId\": \"kn7by8t6yt9yghbxtxz6hv0bts87k6bq\",\n  \"slug\": \"cargo-quickstart\",\n  \"version\": \"1.0.4\",\n  \"publishedAt\": 1790966117726\n}\n\nFile v1.0.4:skill-card.md\n\n## Description:\n\nGuides a new Cargo user from a buyer persona to a short lead list and credit receipt, with an option to save the search as a recurring play.\n\nThis skill is ready for commercial/non-commercial use.\n\n## Publisher:\n\n[cargo-ai](https://clawhub.ai/user/cargo-ai)\n\n### License/Terms of Use:\n\nMIT-0\n\n## Use Case:\n\nSales and go-to-market users can try Cargo by searching for leads matching a chosen buyer persona, reviewing a credit receipt, and optionally saving the search as a weekly play.\n\n### Deployment Geography for Use:\n\nGlobal\n\n## Known Risks and Mitigations:\n\nRisk: A short demo request may trigger a paid lead search and spend Cargo credits without clear approval.\n\nMitigation: Confirm the active workspace, provider, lead limit, and expected credit cost before the first paid search.\n\nRisk: Fallback searches can use a different provider or cost more than the initial search.\n\nMitigation: Confirm the replacement provider and its cost before running any fallback, especially the higher-cost prospect search.\n\nRisk: A weekly saved play can generate future searches and charges.\n\nMitigation: Require separate explicit confirmation before enabling the recurring play.\n\n## Reference(s):\n\n- [Cargo skills homepage](https://github.com/getcargohq/cargo-skills)\n- [Cargo Quickstart on ClawHub](https://clawhub.ai/cargo-ai/skills/cargo-quickstart)\n\n## Skill Output:\n\n**Output Type(s):** [Text, Markdown, Shell commands, Guidance]\n\n**Output Format:** [Markdown lead table, credit receipt, and optional CLI instructions]\n\n**Output Parameters:** [1D]\n\n**Other Properties Related to Output:** [Lead count and credit use depend on connected providers; a recurring play is offered separately.]\n\n## Skill Version(s):\n\n1.0.4 (source: frontmatter and release evidence)\n\n## Ethical Considerations:\n\nUsers should evaluate whether this skill is appropriate for their environment, review any generated or modified files before relying on them, and apply their organization's safety, security, and compliance requirements before deployment.\n\nFile v1.0.4:skill-metadata.json\n\n{\n  \"$comment\": \"Generated by .github/scripts/skills-metadata.mjs — do not hand-edit. Regenerate with: node .github/scripts/skills-metadata.mjs --write .\",\n  \"name\": \"cargo-quickstart\",\n  \"version\": \"1.0.4\",\n  \"documents\": [\n    {\n      \"path\": \"SKILL.md\",\n      \"kind\": \"entrypoint\",\n      \"title\": \"Cargo Quickstart — first value in two minutes\"\n    }\n  ],\n  \"contentHash\": \"1d8b0525e2cf4e310892cae8d12354f32111b134d38d3b3307cb74221857cee7\"\n}\n\nArchive v1.0.3: 4 files, 5745 bytes\n\nFiles: skill-card.md (2370b), skill-metadata.json (449b), SKILL.md (7658b), _meta.json (135b)\n\nFile v1.0.3:SKILL.md\n\n---\nname: cargo-quickstart\ndescription: \"Guided first-run demo for Cargo — one persona question to 25 real leads with a cost receipt in under two minutes, ending by saving the pull as a recurring play. Triggers: \\\"show me what Cargo can do\\\", \\\"give me a demo\\\", \\\"take me on a tour\\\", \\\"quickstart\\\", \\\"getting started with Cargo\\\", \\\"I just installed Cargo\\\", \\\"my workspace is empty\\\", \\\"does this actually work\\\". Skip when: the user has a real job to run (build a list, enrich a CSV, find emails) — use cargo-gtm; when they want CLI reference or routing — use the cargo router skill.\"\nversion: \"1.0.3\"\ncompatibility: Requires @cargo-ai/cli (npm). Sign in or create an account with `cargo-ai login --email` (emailed code, no browser), `--oauth`, or an API token\nhomepage: https://github.com/getcargohq/cargo-skills\nmetadata:\n  author: getcargo\n  openclaw:\n    requires:\n      bins:\n        - cargo-ai\n    install:\n      - kind: node\n        package: \"@cargo-ai/cli@latest\"\n        bins:\n          - cargo-ai\n    homepage: https://github.com/getcargohq/cargo-skills\n---\n\n# Cargo Quickstart — first value in two minutes\n\nOne guided demo: pull ~25 fresh leads matching a buyer persona the user picks, show the cost receipt, then save the pull as a recurring play. The point is not the list — it's that in minute 3 the user owns a running system, not a one-off result.\n\n**A new account starts with 100 free credits — no card.** This demo spends about **0.5** of them. Say that out loud before the first paid call (\"this costs about half a credit of your 100 free ones\"): it converts the moment from *a purchase decision* into *a look around*, which is the whole job of a quickstart. Never let a new user think the demo is why they'd run out.\n\n## Bootstrap\n\nAlready signed in (`cargo-ai whoami` returns a workspace)? Skip to the next section.\n\n```bash\nnpm install -g @cargo-ai/cli            # no global install? prefix every command with `npx @cargo-ai/cli`\ncargo-ai login --email you@company.com  # emailed code, no browser; creates the account on first use\n                                        # alternatives: --oauth (browser) · --token <api-token> (CI)\ncargo-ai whoami                         # confirm the active workspace before any write\n```\n\nEvery command prints JSON to stdout; failures exit non-zero with `{\"errorMessage\": \"...\"}`. Anything that creates a run or a batch is async — pass `--wait-until-finished` or poll the matching `get`. When the full skill bundle is installed, [`../cargo/references/prerequisites.md`](../cargo/references/prerequisites.md) adds the CLI version pin, token scopes, and the admin-only surface.\n\n## The one question\n\nAsk exactly **one** question before doing anything:\n\n> **\"Who do you sell to?\"** (a persona in a few words — e.g. \"Heads of RevOps at mid-market SaaS\")\n\nEverything else — provider, filters, limits — you decide. Don't ask about output format, volume, or providers; defaults below.\n\n## Speed budget — HARD RULES\n\nThe demo has a two-minute budget from answer to deliverable. On the fast path:\n\n- **No discovery detours.** Do not run `cargo-ai --version`, `cargo-ai whoami`, `connection connector list`, or any exploratory command first. Auth problems will surface as errors on the first real call — handle them then.\n- **One command block per step**, no narration between commands.\n- **Paid work is capped at ~1 credit total.** The demo uses the cheapest sourcing action in the catalog (`salesNavigator.searchLeads`, 0.02/record → 25 records ≈ 0.5 credits). Nothing else paid runs without asking.\n- **Never dead-end.** Every step has a fallback (ladder below). If a rung fails, drop one rung silently and keep moving.\n\n## Fast path\n\nTranslate the persona into a `searchLeads` filter (quote the exact title phrase in `keywords`; a bare keyword matches loosely and pollutes the page) and run:\n\n```bash\n# 1. Execute — returns a run object; note run.uuid and run.workflowUuid.\n#    searchLeads returns a 25-row page minimum (limit below 25 still bills 25 × 0.02 = 0.5 credits).\ncargo-ai orchestration action execute \\\n  --action '{\"kind\":\"connector\",\"integrationSlug\":\"salesNavigator\",\"actionSlug\":\"searchLeads\"}' \\\n  --data '{\"keywords\": \"\\\"<persona title phrase>\\\"\", \"limit\": 25}' \\\n  --wait-until-finished > /tmp/quickstart-run.json\n\n# 2. Fetch the output data (NOT in the execute stdout) — signed URL, then filter to THIS run\nRUN_UUID=$(jq -r '.run.uuid' /tmp/quickstart-run.json)\nWF_UUID=$(jq -r '.run.workflowUuid' /tmp/quickstart-run.json)\ncurl -s \"$(cargo-ai orchestration run download-outputs \\\n  --workflow-uuid \"$WF_UUID\" --output-node-slug action --format json | jq -r '.url')\" \\\n  > /tmp/quickstart-outputs.json\n\n# 3. Show the table (the file holds ALL of the workflow's runs — filter by _uuid;\n#    each row's .output is the leads array directly, fields are snake_case)\njq -r --arg u \"$RUN_UUID\" \\\n  '[.[] | select(._uuid==$u)][0].output[] | [.full_name, .job_title, .company_name, (.recently_hired // false)] | @tsv' \\\n  /tmp/quickstart-outputs.json | head -25\n```\n\nShow the table (name · title · company · recently-hired), not the raw JSON. `recently_hired: true` rows are the demo's headline — lead with them (\"6 of these 25 just started the job — the exact moment to reach out\").\n\n### Fallback ladder (on auth/error, drop a rung — don't stop)\n\n1. `salesNavigator.searchLeads` (0.02/record) — primary.\n2. `theirStack.searchJobs` (0.5) — reframe as \"companies hiring your persona right now\" (job postings for the persona's title). Same wow, different angle.\n3. `waterfall.searchProspects` (3/record) — **exceeds the ~1-credit demo cap, so this rung asks first**: \"The two cheap sources aren't connected; I can pull 5 matches via waterfall for ~15 credits instead — run it, or connect Sales Navigator first (free)?\" Run only on an explicit yes, with `limit` capped at 5.\n4. Nothing connected at all → run the free path: `cargo-ai connection integration list | head`, show what *could* be wired, and offer to connect one (browser auth) — the demo resumes after.\n\n## The receipt (mandatory, verbatim discipline)\n\nThe demo is itself the pilot from [`../cargo-gtm/references/cost-discipline.md`](../cargo-gtm/references/cost-discipline.md). Close it with a receipt:\n\n- Credits spent + balance remaining (`cargo-ai billing subscription get` — remaining = `subscriptionAvailableCreditsCount − subscriptionCreditsUsedCount`). For a brand-new account, frame it against the **100 free starting credits** rather than as a bare number — \"0.5 spent, 99.5 of your 100 free credits left\" lands very differently from \"99.5 credits remaining\".\n- Hit-rate: \"25 of 25 returned\" (or what actually came back, and which rows look off).\n\n## Minute 3 — save it as a play\n\nImmediately offer to make the pull recurring — this is the step that shows what Cargo *is*:\n\n> \"Want this to run by itself? I can save this exact search as a play that runs weekly and writes new matches into a model — new `<persona>` leads land without you asking.\"\n\nOn yes, follow [`../cargo-gtm/recipes/save-as-play.md`](../cargo-gtm/recipes/save-as-play.md) with the demo's action + filter as the workflow body and a weekly cron.\n\n## After the demo — route onward\n\nPropose 2–3 next steps grounded in the rows just pulled, per the next-step spec in [`../cargo-gtm/SKILL.md`](../cargo-gtm/SKILL.md) (§4): e.g. \"enrich these 25 with firmographics (~0.5 cr each)\", \"find + verify emails for the best 10 (~1.4 cr each)\", or something else entirely. From here, real GTM work belongs to [`cargo-gtm`](../cargo-gtm/SKILL.md) — read it before anything beyond the demo.\n\nFile v1.0.3:_meta.json\n\n{\n  \"ownerId\": \"kn7by8t6yt9yghbxtxz6hv0bts87k6bq\",\n  \"slug\": \"cargo-quickstart\",\n  \"version\": \"1.0.3\",\n  \"publishedAt\": 1788392543266\n}\n\nFile v1.0.3:skill-card.md\n\n## Description:\n\nGuides a first-run Cargo demo that asks for one buyer persona, pulls about 25 matching leads, shows a credit receipt, and offers to save the search as a recurring play.\n\nThis skill is ready for commercial/non-commercial use.\n\n## Publisher:\n\n[cargo-ai](https://clawhub.ai/user/cargo-ai)\n\n### License/Terms of Use:\n\nMIT-0\n\n## Use Case:\n\nDevelopers, revenue operators, and go-to-market teams use this skill to try Cargo quickly by sourcing a small lead list, checking spend, and turning the same search into recurring automation.\n\n### Deployment Geography for Use:\n\nGlobal\n\n## Known Risks and Mitigations:\n\nRisk: The workflow can run external lead searches and spend account credits.\n\nMitigation: Confirm the active workspace and expected credit cost before paid calls, and require explicit approval before fallback actions that exceed the stated demo cap.\n\nRisk: The workflow downloads lead data to local temporary files.\n\nMitigation: Treat downloaded lead data as sensitive, keep it in an appropriate workspace, and remove temporary outputs when the demo is complete.\n\nRisk: Persona text is interpolated into shell and JSON command examples.\n\nMitigation: Encode or quote user-provided persona text safely before placing it in CLI commands.\n\nRisk: The demo can create recurring automation if the user accepts the play setup.\n\nMitigation: Disclose the recurrence, destination model, and expected ongoing cost before saving a play.\n\n## Reference(s):\n\n- [Cargo skills homepage](https://github.com/getcargohq/cargo-skills)\n- [Cargo Quickstart on ClawHub](https://clawhub.ai/cargo-ai/skills/cargo-quickstart)\n\n## Skill Output:\n\n**Output Type(s):** [text, markdown, shell commands, configuration, guidance]\n\n**Output Format:** [Markdown with bash command blocks and short user-facing prompts]\n\n**Output Parameters:** [1D]\n\n**Other Properties Related to Output:** [Produces Cargo CLI commands, lead-table presentation guidance, cost receipt guidance, fallback choices, and recurring-play setup guidance.]\n\n## Skill Version(s):\n\n1.0.3 (source: frontmatter, skill-metadata.json, release evidence)\n\n## Ethical Considerations:\n\nUsers should evaluate whether this skill is appropriate for their environment, review any generated or modified files before relying on them, and apply their organization's safety, security, and compliance requirements before deployment.\n\nFile v1.0.3:skill-metadata.json\n\n{\n  \"$comment\": \"Generated by .github/scripts/skills-metadata.mjs — do not hand-edit. Regenerate with: node .github/scripts/skills-metadata.mjs --write .\",\n  \"name\": \"cargo-quickstart\",\n  \"version\": \"1.0.3\",\n  \"documents\": [\n    {\n      \"path\": \"SKILL.md\",\n      \"kind\": \"entrypoint\",\n      \"title\": \"Cargo Quickstart — first value in two minutes\"\n    }\n  ],\n  \"contentHash\": \"26fd74f6bf37a62f4d508525f157b0e12e23358dd81487a59646857b47f58c54\"\n}\n\nArchive v1.0.2: 4 files, 5626 bytes\n\nFiles: skill-card.md (2136b), skill-metadata.json (449b), SKILL.md (7658b), _meta.json (135b)\n\nFile v1.0.2:SKILL.md\n\n---\nname: cargo-quickstart\ndescription: \"Guided first-run demo for Cargo — one persona question to 25 real leads with a cost receipt in under two minutes, ending by saving the pull as a recurring play. Triggers: \\\"show me what Cargo can do\\\", \\\"give me a demo\\\", \\\"take me on a tour\\\", \\\"quickstart\\\", \\\"getting started with Cargo\\\", \\\"I just installed Cargo\\\", \\\"my workspace is empty\\\", \\\"does this actually work\\\". Skip when: the user has a real job to run (build a list, enrich a CSV, find emails) — use cargo-gtm; when they want CLI reference or routing — use the cargo router skill.\"\nversion: \"1.0.2\"\ncompatibility: Requires @cargo-ai/cli (npm). Sign in or create an account with `cargo-ai login --email` (emailed code, no browser), `--oauth`, or an API token\nhomepage: https://github.com/getcargohq/cargo-skills\nmetadata:\n  author: getcargo\n  openclaw:\n    requires:\n      bins:\n        - cargo-ai\n    install:\n      - kind: node\n        package: \"@cargo-ai/cli@latest\"\n        bins:\n          - cargo-ai\n    homepage: https://github.com/getcargohq/cargo-skills\n---\n\n# Cargo Quickstart — first value in two minutes\n\nOne guided demo: pull ~25 fresh leads matching a buyer persona the user picks, show the cost receipt, then save the pull as a recurring play. The point is not the list — it's that in minute 3 the user owns a running system, not a one-off result.\n\n**A new account starts with 100 free credits — no card.** This demo spends about **0.5** of them. Say that out loud before the first paid call (\"this costs about half a credit of your 100 free ones\"): it converts the moment from *a purchase decision* into *a look around*, which is the whole job of a quickstart. Never let a new user think the demo is why they'd run out.\n\n## Bootstrap\n\nAlready signed in (`cargo-ai whoami` returns a workspace)? Skip to the next section.\n\n```bash\nnpm install -g @cargo-ai/cli            # no global install? prefix every command with `npx @cargo-ai/cli`\ncargo-ai login --email you@company.com  # emailed code, no browser; creates the account on first use\n                                        # alternatives: --oauth (browser) · --token <api-token> (CI)\ncargo-ai whoami                         # confirm the active workspace before any write\n```\n\nEvery command prints JSON to stdout; failures exit non-zero with `{\"errorMessage\": \"...\"}`. Anything that creates a run or a batch is async — pass `--wait-until-finished` or poll the matching `get`. When the full skill bundle is installed, [`../cargo/references/prerequisites.md`](../cargo/references/prerequisites.md) adds the CLI version pin, token scopes, and the admin-only surface.\n\n## The one question\n\nAsk exactly **one** question before doing anything:\n\n> **\"Who do you sell to?\"** (a persona in a few words — e.g. \"Heads of RevOps at mid-market SaaS\")\n\nEverything else — provider, filters, limits — you decide. Don't ask about output format, volume, or providers; defaults below.\n\n## Speed budget — HARD RULES\n\nThe demo has a two-minute budget from answer to deliverable. On the fast path:\n\n- **No discovery detours.** Do not run `cargo-ai --version`, `cargo-ai whoami`, `connection connector list`, or any exploratory command first. Auth problems will surface as errors on the first real call — handle them then.\n- **One command block per step**, no narration between commands.\n- **Paid work is capped at ~1 credit total.** The demo uses the cheapest sourcing action in the catalog (`salesNavigator.searchLeads`, 0.02/record → 25 records ≈ 0.5 credits). Nothing else paid runs without asking.\n- **Never dead-end.** Every step has a fallback (ladder below). If a rung fails, drop one rung silently and keep moving.\n\n## Fast path\n\nTranslate the persona into a `searchLeads` filter (quote the exact title phrase in `keywords`; a bare keyword matches loosely and pollutes the page) and run:\n\n```bash\n# 1. Execute — returns a run object; note run.uuid and run.workflowUuid.\n#    searchLeads returns a 25-row page minimum (limit below 25 still bills 25 × 0.02 = 0.5 credits).\ncargo-ai orchestration action execute \\\n  --action '{\"kind\":\"connector\",\"integrationSlug\":\"salesNavigator\",\"actionSlug\":\"searchLeads\"}' \\\n  --data '{\"keywords\": \"\\\"<persona title phrase>\\\"\", \"limit\": 25}' \\\n  --wait-until-finished > /tmp/quickstart-run.json\n\n# 2. Fetch the output data (NOT in the execute stdout) — signed URL, then filter to THIS run\nRUN_UUID=$(jq -r '.run.uuid' /tmp/quickstart-run.json)\nWF_UUID=$(jq -r '.run.workflowUuid' /tmp/quickstart-run.json)\ncurl -s \"$(cargo-ai orchestration run download-outputs \\\n  --workflow-uuid \"$WF_UUID\" --output-node-slug action --format json | jq -r '.url')\" \\\n  > /tmp/quickstart-outputs.json\n\n# 3. Show the table (the file holds ALL of the workflow's runs — filter by _uuid;\n#    each row's .output is the leads array directly, fields are snake_case)\njq -r --arg u \"$RUN_UUID\" \\\n  '[.[] | select(._uuid==$u)][0].output[] | [.full_name, .job_title, .company_name, (.recently_hired // false)] | @tsv' \\\n  /tmp/quickstart-outputs.json | head -25\n```\n\nShow the table (name · title · company · recently-hired), not the raw JSON. `recently_hired: true` rows are the demo's headline — lead with them (\"6 of these 25 just started the job — the exact moment to reach out\").\n\n### Fallback ladder (on auth/error, drop a rung — don't stop)\n\n1. `salesNavigator.searchLeads` (0.02/record) — primary.\n2. `theirStack.searchJobs` (0.5) — reframe as \"companies hiring your persona right now\" (job postings for the persona's title). Same wow, different angle.\n3. `waterfall.searchProspects` (3/record) — **exceeds the ~1-credit demo cap, so this rung asks first**: \"The two cheap sources aren't connected; I can pull 5 matches via waterfall for ~15 credits instead — run it, or connect Sales Navigator first (free)?\" Run only on an explicit yes, with `limit` capped at 5.\n4. Nothing connected at all → run the free path: `cargo-ai connection integration list | head`, show what *could* be wired, and offer to connect one (browser auth) — the demo resumes after.\n\n## The receipt (mandatory, verbatim discipline)\n\nThe demo is itself the pilot from [`../cargo-gtm/references/cost-discipline.md`](../cargo-gtm/references/cost-discipline.md). Close it with a receipt:\n\n- Credits spent + balance remaining (`cargo-ai billing subscription get` — remaining = `subscriptionAvailableCreditsCount − subscriptionCreditsUsedCount`). For a brand-new account, frame it against the **100 free starting credits** rather than as a bare number — \"0.5 spent, 99.5 of your 100 free credits left\" lands very differently from \"99.5 credits remaining\".\n- Hit-rate: \"25 of 25 returned\" (or what actually came back, and which rows look off).\n\n## Minute 3 — save it as a play\n\nImmediately offer to make the pull recurring — this is the step that shows what Cargo *is*:\n\n> \"Want this to run by itself? I can save this exact search as a play that runs weekly and writes new matches into a model — new `<persona>` leads land without you asking.\"\n\nOn yes, follow [`../cargo-gtm/recipes/save-as-play.md`](../cargo-gtm/recipes/save-as-play.md) with the demo's action + filter as the workflow body and a weekly cron.\n\n## After the demo — route onward\n\nPropose 2–3 next steps grounded in the rows just pulled, per the next-step spec in [`../cargo-gtm/SKILL.md`](../cargo-gtm/SKILL.md) (§4): e.g. \"enrich these 25 with firmographics (~0.5 cr each)\", \"find + verify emails for the best 10 (~1.4 cr each)\", or something else entirely. From here, real GTM work belongs to [`cargo-gtm`](../cargo-gtm/SKILL.md) — read it before anything beyond the demo.\n\nFile v1.0.2:_meta.json\n\n{\n  \"ownerId\": \"kn7by8t6yt9yghbxtxz6hv0bts87k6bq\",\n  \"slug\": \"cargo-quickstart\",\n  \"version\": \"1.0.2\",\n  \"publishedAt\": 1787874300245\n}\n\nFile v1.0.2:skill-card.md\n\n## Description:\n\nGuided first-run demo for Cargo: one persona question to 25 real leads with a cost receipt in under two minutes, ending by saving the pull as a recurring play.\n\nThis skill is ready for commercial/non-commercial use.\n\n## Publisher:\n\n[cargo-ai](https://clawhub.ai/user/cargo-ai)\n\n### License/Terms of Use:\n\nMIT-0\n\n## Use Case:\n\nExternal Cargo users and go-to-market teams use this skill for a guided first-run Cargo demo that sources a small lead set, shows the credit cost, and offers to save the same search as a weekly play.\n\n### Deployment Geography for Use:\n\nGlobal\n\n## Known Risks and Mitigations:\n\nRisk: The skill can spend Cargo credits and download lead data while running lead-sourcing actions.\n\nMitigation: Confirm the expected credit cost before paid work, keep the normal demo near the documented low-cost path, and review any downloaded lead data before sharing or retaining it.\n\nRisk: The demo can transition into a weekly automated play with ongoing lead collection and recurring credit usage.\n\nMitigation: Before enabling recurrence, confirm the schedule, destination model, expected recurring cost, and how to pause or delete the play.\n\n## Reference(s):\n\n- [Cargo Quickstart on ClawHub](https://clawhub.ai/cargo-ai/skills/cargo-quickstart)\n- [Cargo Skills Repository](https://github.com/getcargohq/cargo-skills)\n- [Cargo Publisher Profile](https://clawhub.ai/user/cargo-ai)\n\n## Skill Output:\n\n**Output Type(s):** [text, markdown, shell commands, guidance]\n\n**Output Format:** [Markdown guidance with inline shell commands and concise result summaries]\n\n**Output Parameters:** [1D]\n\n**Other Properties Related to Output:** [May direct the agent to run Cargo CLI commands, show lead tables, report credit usage, and propose follow-up GTM actions.]\n\n## Skill Version(s):\n\n1.0.2 (source: frontmatter, skill-metadata.json, release evidence)\n\n## Ethical Considerations:\n\nUsers should evaluate whether this skill is appropriate for their environment, review any generated or modified files before relying on them, and apply their organization's safety, security, and compliance requirements before deployment.\n\nFile v1.0.2:skill-metadata.json\n\n{\n  \"$comment\": \"Generated by .github/scripts/skills-metadata.mjs — do not hand-edit. Regenerate with: node .github/scripts/skills-metadata.mjs --write .\",\n  \"name\": \"cargo-quickstart\",\n  \"version\": \"1.0.2\",\n  \"documents\": [\n    {\n      \"path\": \"SKILL.md\",\n      \"kind\": \"entrypoint\",\n      \"title\": \"Cargo Quickstart — first value in two minutes\"\n    }\n  ],\n  \"contentHash\": \"cee20ba589d58cce9e65cf3e7c0ea67d15496e063f50633e1d86c102987a80fb\"\n}\n\nArchive v1.0.1: 4 files, 5047 bytes\n\nFiles: skill-card.md (2370b), skill-metadata.json (449b), SKILL.md (6040b), _meta.json (135b)\n\nFile v1.0.1:SKILL.md\n\n---\nname: cargo-quickstart\ndescription: \"Guided first-run demo for the Cargo CLI — from a fresh workspace to a real deliverable (25 leads matching the user's buyer persona, with a cost receipt) in under two minutes, ending by saving the demo as a recurring play. Use when the user is new to Cargo, asks for a demo/tour/quickstart, or has an empty workspace and wants to see what the CLI can do. For real GTM work beyond the demo, route to cargo-gtm.\"\nversion: \"1.0.1\"\ncompatibility: Requires @cargo-ai/cli (npm). Sign in or create an account with `cargo-ai login --email` (emailed code, no browser), `--oauth`, or an API token\nhomepage: https://github.com/getcargohq/cargo-skills\nmetadata:\n  author: getcargo\n  openclaw:\n    requires:\n      bins:\n        - cargo-ai\n    install:\n      - kind: node\n        package: \"@cargo-ai/cli@latest\"\n        bins:\n          - cargo-ai\n    homepage: https://github.com/getcargohq/cargo-skills\n---\n\n# Cargo Quickstart — first value in two minutes\n\nOne guided demo: pull ~25 fresh leads matching a buyer persona the user picks, show the cost receipt, then save the pull as a recurring play. The point is not the list — it's that in minute 3 the user owns a running system, not a one-off result.\n\n## The one question\n\nAsk exactly **one** question before doing anything:\n\n> **\"Who do you sell to?\"** (a persona in a few words — e.g. \"Heads of RevOps at mid-market SaaS\")\n\nEverything else — provider, filters, limits — you decide. Don't ask about output format, volume, or providers; defaults below.\n\n## Speed budget — HARD RULES\n\nThe demo has a two-minute budget from answer to deliverable. On the fast path:\n\n- **No discovery detours.** Do not run `cargo-ai --version`, `cargo-ai whoami`, `connection connector list`, or any exploratory command first. Auth problems will surface as errors on the first real call — handle them then.\n- **One command block per step**, no narration between commands.\n- **Paid work is capped at ~1 credit total.** The demo uses the cheapest sourcing action in the catalog (`salesNavigator.searchLeads`, 0.02/record → 25 records ≈ 0.5 credits). Nothing else paid runs without asking.\n- **Never dead-end.** Every step has a fallback (ladder below). If a rung fails, drop one rung silently and keep moving.\n\n## Fast path\n\nTranslate the persona into a `searchLeads` filter (quote the exact title phrase in `keywords`; a bare keyword matches loosely and pollutes the page) and run:\n\n```bash\n# 1. Execute — returns a run object; note run.uuid and run.workflowUuid.\n#    searchLeads returns a 25-row page minimum (limit below 25 still bills 25 × 0.02 = 0.5 credits).\ncargo-ai orchestration action execute \\\n  --action '{\"kind\":\"connector\",\"integrationSlug\":\"salesNavigator\",\"actionSlug\":\"searchLeads\",\"config\":{}}' \\\n  --data '{\"keywords\": \"\\\"<persona title phrase>\\\"\", \"limit\": 25}' \\\n  --wait-until-finished > /tmp/quickstart-run.json\n\n# 2. Fetch the output data (NOT in the execute stdout) — signed URL, then filter to THIS run\nRUN_UUID=$(jq -r '.run.uuid' /tmp/quickstart-run.json)\nWF_UUID=$(jq -r '.run.workflowUuid' /tmp/quickstart-run.json)\ncurl -s \"$(cargo-ai orchestration run download-outputs \\\n  --workflow-uuid \"$WF_UUID\" --output-node-slug action --format json | jq -r '.url')\" \\\n  > /tmp/quickstart-outputs.json\n\n# 3. Show the table (the file holds ALL of the workflow's runs — filter by _uuid;\n#    each row's .output is the leads array directly, fields are snake_case)\njq -r --arg u \"$RUN_UUID\" \\\n  '[.[] | select(._uuid==$u)][0].output[] | [.full_name, .job_title, .company_name, (.recently_hired // false)] | @tsv' \\\n  /tmp/quickstart-outputs.json | head -25\n```\n\nShow the table (name · title · company · recently-hired), not the raw JSON. `recently_hired: true` rows are the demo's headline — lead with them (\"6 of these 25 just started the job — the exact moment to reach out\").\n\n### Fallback ladder (on auth/error, drop a rung — don't stop)\n\n1. `salesNavigator.searchLeads` (0.02/record) — primary.\n2. `theirStack.searchJobs` (0.5) — reframe as \"companies hiring your persona right now\" (job postings for the persona's title). Same wow, different angle.\n3. `waterfall.searchProspects` (3/record) — **exceeds the ~1-credit demo cap, so this rung asks first**: \"The two cheap sources aren't connected; I can pull 5 matches via waterfall for ~15 credits instead — run it, or connect Sales Navigator first (free)?\" Run only on an explicit yes, with `limit` capped at 5.\n4. Nothing connected at all → run the free path: `cargo-ai connection integration list | head`, show what *could* be wired, and offer to connect one (browser auth) — the demo resumes after.\n\n## The receipt (mandatory, verbatim discipline)\n\nThe demo is itself the pilot from [`../cargo-gtm/references/cost-discipline.md`](../cargo-gtm/references/cost-discipline.md). Close it with a receipt:\n\n- Credits spent + balance remaining (`cargo-ai billing subscription get` — remaining = `subscriptionAvailableCreditsCount − subscriptionCreditsUsedCount`).\n- Hit-rate: \"25 of 25 returned\" (or what actually came back, and which rows look off).\n\n## Minute 3 — save it as a play\n\nImmediately offer to make the pull recurring — this is the step that shows what Cargo *is*:\n\n> \"Want this to run by itself? I can save this exact search as a play that runs weekly and writes new matches into a model — new `<persona>` leads land without you asking.\"\n\nOn yes, follow [`../cargo-gtm/recipes/save-as-play.md`](../cargo-gtm/recipes/save-as-play.md) with the demo's action + filter as the workflow body and a weekly cron.\n\n## After the demo — route onward\n\nPropose 2–3 next steps grounded in the rows just pulled, per the next-step spec in [`../cargo-gtm/SKILL.md`](../cargo-gtm/SKILL.md) (§4): e.g. \"enrich these 25 with firmographics (~0.5 cr each)\", \"find + verify emails for the best 10 (~1.4 cr each)\", or something else entirely. From here, real GTM work belongs to [`cargo-gtm`](../cargo-gtm/SKILL.md) — read it before anything beyond the demo.\n\nFile v1.0.1:_meta.json\n\n{\n  \"ownerId\": \"kn7by8t6yt9yghbxtxz6hv0bts87k6bq\",\n  \"slug\": \"cargo-quickstart\",\n  \"version\": \"1.0.1\",\n  \"publishedAt\": 1786484556990\n}\n\nFile v1.0.1:skill-card.md\n\n## Description:\n\nGuided first-run demo for the Cargo CLI - from a fresh workspace to a real deliverable of 25 leads matching the user's buyer persona, with a cost receipt, in under two minutes and ending by saving the demo as a recurring play.\n\nThis skill is ready for commercial/non-commercial use.\n\n## Publisher:\n\n[cargo-ai](https://clawhub.ai/user/cargo-ai)\n\n### License/Terms of Use:\n\nMIT-0\n\n## Use Case:\n\nDevelopers, sales operators, and go-to-market teams use this skill to run a guided first Cargo CLI demo that sources a small buyer-persona lead set, shows spending and hit-rate, and offers to convert the search into a recurring play.\n\n### Deployment Geography for Use:\n\nGlobal\n\n## Known Risks and Mitigations:\n\nRisk: The skill can spend Cargo account credits during the demo.\n\nMitigation: Keep the normal demo path near the documented one-credit cap, require explicit confirmation before higher-cost fallback actions, and review the receipt after execution.\n\nRisk: The buyer persona may be sent to external lead providers and resulting lead data may be temporarily stored on the local machine.\n\nMitigation: Avoid sensitive persona inputs, confirm before networked or paid actions when needed, and delete temporary output files after the demo.\n\nRisk: A recurring play can continue running after the initial demo.\n\nMitigation: Confirm the schedule, destination, and cost expectations before enabling recurrence, and monitor or disable the play when it is no longer needed.\n\n## Reference(s):\n\n- [Cargo Skills Homepage](https://github.com/getcargohq/cargo-skills)\n- [Cargo Quickstart on ClawHub](https://clawhub.ai/cargo-ai/skills/cargo-quickstart)\n\n## Skill Output:\n\n**Output Type(s):** [text, markdown, shell commands, configuration, guidance]\n\n**Output Format:** [Markdown with inline shell commands and concise tabular lead summaries]\n\n**Output Parameters:** [1D]\n\n**Other Properties Related to Output:** [May create temporary local JSON files for run metadata and lead outputs during the demo.]\n\n## Skill Version(s):\n\n1.0.1 (source: frontmatter, skill-metadata.json, server release metadata)\n\n## Ethical Considerations:\n\nUsers should evaluate whether this skill is appropriate for their environment, review any generated or modified files before relying on them, and apply their organization's safety, security, and compliance requirements before deployment.\n\nFile v1.0.1:skill-metadata.json\n\n{\n  \"$comment\": \"Generated by .github/scripts/skills-metadata.mjs — do not hand-edit. Regenerate with: node .github/scripts/skills-metadata.mjs --write .\",\n  \"name\": \"cargo-quickstart\",\n  \"version\": \"1.0.1\",\n  \"documents\": [\n    {\n      \"path\": \"SKILL.md\",\n      \"kind\": \"entrypoint\",\n      \"title\": \"Cargo Quickstart — first value in two minutes\"\n    }\n  ],\n  \"contentHash\": \"c2c5905ec9eb706265e40e39fc7c5ce2e4c9b3a53f505b7e12b478707c9fe9af\"\n}\n\nArchive v1.0.0: 3 files, 4510 bytes\n\nFiles: skill-card.md (2318b), SKILL.md (5992b), _meta.json (135b)\n\nFile v1.0.0:SKILL.md\n\n---\nname: cargo-quickstart\ndescription: \"Guided first-run demo for the Cargo CLI — from a fresh workspace to a real deliverable (25 leads matching the user's buyer persona, with a cost receipt) in under two minutes, ending by saving the demo as a recurring play. Use when the user is new to Cargo, asks for a demo/tour/quickstart, or has an empty workspace and wants to see what the CLI can do. For real GTM work beyond the demo, route to cargo-gtm.\"\nversion: \"1.0.0\"\ncompatibility: Requires @cargo-ai/cli (npm) and a Cargo account (browser sign-in via --oauth, or an API token)\nhomepage: https://github.com/getcargohq/cargo-skills\nmetadata:\n  author: getcargo\n  openclaw:\n    requires:\n      bins:\n        - cargo-ai\n    install:\n      - kind: node\n        package: \"@cargo-ai/cli@latest\"\n        bins:\n          - cargo-ai\n    homepage: https://github.com/getcargohq/cargo-skills\n---\n\n# Cargo Quickstart — first value in two minutes\n\nOne guided demo: pull ~25 fresh leads matching a buyer persona the user picks, show the cost receipt, then save the pull as a recurring play. The point is not the list — it's that in minute 3 the user owns a running system, not a one-off result.\n\n## The one question\n\nAsk exactly **one** question before doing anything:\n\n> **\"Who do you sell to?\"** (a persona in a few words — e.g. \"Heads of RevOps at mid-market SaaS\")\n\nEverything else — provider, filters, limits — you decide. Don't ask about output format, volume, or providers; defaults below.\n\n## Speed budget — HARD RULES\n\nThe demo has a two-minute budget from answer to deliverable. On the fast path:\n\n- **No discovery detours.** Do not run `cargo-ai --version`, `cargo-ai whoami`, `connection connector list`, or any exploratory command first. Auth problems will surface as errors on the first real call — handle them then.\n- **One command block per step**, no narration between commands.\n- **Paid work is capped at ~1 credit total.** The demo uses the cheapest sourcing action in the catalog (`salesNavigator.searchLeads`, 0.02/record → 25 records ≈ 0.5 credits). Nothing else paid runs without asking.\n- **Never dead-end.** Every step has a fallback (ladder below). If a rung fails, drop one rung silently and keep moving.\n\n## Fast path\n\nTranslate the persona into a `searchLeads` filter (quote the exact title phrase in `keywords`; a bare keyword matches loosely and pollutes the page) and run:\n\n```bash\n# 1. Execute — returns a run object; note run.uuid and run.workflowUuid.\n#    searchLeads returns a 25-row page minimum (limit below 25 still bills 25 × 0.02 = 0.5 credits).\ncargo-ai orchestration action execute \\\n  --action '{\"kind\":\"connector\",\"integrationSlug\":\"salesNavigator\",\"actionSlug\":\"searchLeads\",\"config\":{}}' \\\n  --data '{\"keywords\": \"\\\"<persona title phrase>\\\"\", \"limit\": 25}' \\\n  --wait-until-finished > /tmp/quickstart-run.json\n\n# 2. Fetch the output data (NOT in the execute stdout) — signed URL, then filter to THIS run\nRUN_UUID=$(jq -r '.run.uuid' /tmp/quickstart-run.json)\nWF_UUID=$(jq -r '.run.workflowUuid' /tmp/quickstart-run.json)\ncurl -s \"$(cargo-ai orchestration run download-outputs \\\n  --workflow-uuid \"$WF_UUID\" --output-node-slug action --format json | jq -r '.url')\" \\\n  > /tmp/quickstart-outputs.json\n\n# 3. Show the table (the file holds ALL of the workflow's runs — filter by _uuid;\n#    each row's .output is the leads array directly, fields are snake_case)\njq -r --arg u \"$RUN_UUID\" \\\n  '[.[] | select(._uuid==$u)][0].output[] | [.full_name, .job_title, .company_name, (.recently_hired // false)] | @tsv' \\\n  /tmp/quickstart-outputs.json | head -25\n```\n\nShow the table (name · title · company · recently-hired), not the raw JSON. `recently_hired: true` rows are the demo's headline — lead with them (\"6 of these 25 just started the job — the exact moment to reach out\").\n\n### Fallback ladder (on auth/error, drop a rung — don't stop)\n\n1. `salesNavigator.searchLeads` (0.02/record) — primary.\n2. `theirStack.searchJobs` (0.5) — reframe as \"companies hiring your persona right now\" (job postings for the persona's title). Same wow, different angle.\n3. `waterfall.searchProspects` (3/record) — **exceeds the ~1-credit demo cap, so this rung asks first**: \"The two cheap sources aren't connected; I can pull 5 matches via waterfall for ~15 credits instead — run it, or connect Sales Navigator first (free)?\" Run only on an explicit yes, with `limit` capped at 5.\n4. Nothing connected at all → run the free path: `cargo-ai connection integration list | head`, show what *could* be wired, and offer to connect one (browser auth) — the demo resumes after.\n\n## The receipt (mandatory, verbatim discipline)\n\nThe demo is itself the pilot from [`../cargo-gtm/references/cost-discipline.md`](../cargo-gtm/references/cost-discipline.md). Close it with a receipt:\n\n- Credits spent + balance remaining (`cargo-ai billing subscription get` — remaining = `subscriptionAvailableCreditsCount − subscriptionCreditsUsedCount`).\n- Hit-rate: \"25 of 25 returned\" (or what actually came back, and which rows look off).\n\n## Minute 3 — save it as a play\n\nImmediately offer to make the pull recurring — this is the step that shows what Cargo *is*:\n\n> \"Want this to run by itself? I can save this exact search as a play that runs weekly and writes new matches into a model — new `<persona>` leads land without you asking.\"\n\nOn yes, follow [`../cargo-gtm/recipes/save-as-play.md`](../cargo-gtm/recipes/save-as-play.md) with the demo's action + filter as the workflow body and a weekly cron.\n\n## After the demo — route onward\n\nPropose 2–3 next steps grounded in the rows just pulled, per the next-step spec in [`../cargo-gtm/SKILL.md`](../cargo-gtm/SKILL.md) (§4): e.g. \"enrich these 25 with firmographics (~0.5 cr each)\", \"find + verify emails for the best 10 (~1.4 cr each)\", or something else entirely. From here, real GTM work belongs to [`cargo-gtm`](../cargo-gtm/SKILL.md) — read it before anything beyond the demo.\n\nFile v1.0.0:_meta.json\n\n{\n  \"ownerId\": \"kn7by8t6yt9yghbxtxz6hv0bts87k6bq\",\n  \"slug\": \"cargo-quickstart\",\n  \"version\": \"1.0.0\",\n  \"publishedAt\": 1783644862038\n}\n\nFile v1.0.0:skill-card.md\n\n## Description: <br>\nGuided first-run demo for the Cargo CLI that takes a fresh workspace to about 25 buyer-persona-matched leads with a cost receipt in under two minutes, then offers to save the search as a recurring play. <br>\n\nThis skill is ready for commercial/non-commercial use. <br>\n\n## Publisher: <br>\n[cargo-ai](https://clawhub.ai/user/cargo-ai) <br>\n\n### License/Terms of Use: <br>\nMIT-0 <br>\n\n\n## Use Case: <br>\nDevelopers, sales operators, and GTM teams use this skill to demonstrate Cargo from a new workspace by sourcing buyer-persona-matched leads, showing a spend receipt, and optionally saving the search as a weekly play. <br>\n\n### Deployment Geography for Use: <br>\nGlobal <br>\n\n## Known Risks and Mitigations: <br>\nRisk: The skill can use connected lead providers and spend credits while retrieving prospect data. <br>\nMitigation: Keep the quickstart on the capped low-cost path and require explicit user approval before any higher-cost fallback runs. <br>\nRisk: Demo lead output is temporarily written under /tmp. <br>\nMitigation: Treat the temporary files as prospect data and remove or protect them when the demo is complete. <br>\nRisk: Saving the search as a weekly play can continue using provider data and credits. <br>\nMitigation: Create the recurring play only after explicit user consent, and review or disable the schedule when it is no longer needed. <br>\n\n\n## Reference(s): <br>\n- [Cargo Quickstart on ClawHub](https://clawhub.ai/cargo-ai/skills/cargo-quickstart) <br>\n- [Cargo skills homepage](https://github.com/getcargohq/cargo-skills) <br>\n\n\n## Skill Output: <br>\n**Output Type(s):** [text, markdown, shell commands, configuration, guidance] <br>\n**Output Format:** [Markdown with inline bash commands, lead tables, receipts, and next-step guidance] <br>\n**Output Parameters:** [1D] <br>\n**Other Properties Related to Output:** [Requires the Cargo CLI and a Cargo account; may use connected lead providers and credits.] <br>\n\n## Skill Version(s): <br>\n1.0.0 (source: frontmatter and release evidence) <br>\n\n## Ethical Considerations: <br>\nUsers should evaluate whether this skill is appropriate for their environment, review any generated or modified files before relying on them, and apply their organization's safety, security, and compliance requirements before deployment. <br>","readmeExcerpt":"Skill: cargo-quickstart Owner: cargo-ai Summary: Guided first-run demo for Cargo — one persona question to 25 real leads with a cost receipt in under two minutes, ending by saving the pull as a recurring play. Triggers: \"show me what Cargo can do\", \"give me a demo\", \"take me on a tour\", \"quickstart\", \"getting started with Cargo\", \"I just installed Cargo\", \"my workspace is empty\", \"does this actually work\". Skip when:","codeSnippets":[],"executableExamples":[{"language":"bash","snippet":"npm install -g @cargo-ai/cli            # no global install? prefix every command with `npx @cargo-ai/cli`\ncargo-ai login --email you@company.com  # emailed code, no browser; creates the account on first use\n                                        # alternatives: --oauth (browser) · --token <api-token> (CI)\ncargo-ai whoami                         # confirm the active workspace before any write"},{"language":"bash","snippet":"curl -s \"$(cargo-ai orchestration run download-outputs \\\n  --workflow-uuid \"$WF_UUID\" --output-node-slug action --format json | jq -r '.url')\" \\"},{"language":"bash","snippet":"# 1. Execute — returns a run object; note run.uuid and run.workflowUuid.\n#    searchLeads returns a 25-row page minimum (limit below 25 still bills 25 × 0.2 = 5 credits).\ncargo-ai orchestration action execute \\\n  --action '{\"kind\":\"connector\",\"integrationSlug\":\"salesNavigator\",\"actionSlug\":\"searchLeads\"}' \\\n  --data '{\"keywords\": \"\\\"<persona title phrase>\\\"\", \"limit\": 25}' \\\n  --wait-until-finished > /tmp/quickstart-run.json\n\n# 2. Fetch the output data (NOT in the execute stdout) — signed URL, then filter to THIS run\nRUN_UUID=$(jq -r '.run.uuid' /tmp/quickstart-run.json)\nWF_UUID=$(jq -r '.run.workflowUuid' /tmp/quickstart-run.json)\ncurl -s \"$(cargo-ai orchestration run download-outputs \\\n  --workflow-uuid \"$WF_UUID\" --output-node-slug action --format json | jq -r '.url')\" \\\n  > /tmp/quickstart-outputs.json\n\n# 3. Show the table (the file holds ALL of the workflow's runs — filter by _uuid;\n#    each row's .output is the leads array directly, fields are snake_case)\njq -r --arg u \"$RUN_UUID\" \\\n  '[.[] | select(._uuid==$u)][0].output[] | [.full_name, .job_title, .company_name, (.recently_hired // false)] | @tsv' \\\n  /tmp/quickstart-outputs.json | head -25"},{"language":"bash","snippet":"npm install -g @cargo-ai/cli            # no global install? prefix every command with `npx @cargo-ai/cli`\ncargo-ai login --email you@company.com  # emailed code, no browser; creates the account on first use\n                                        # alternatives: --oauth (browser) · --token <api-token> (CI)\ncargo-ai whoami                         # confirm the active workspace before any write"},{"language":"bash","snippet":"curl -s \"$(cargo-ai orchestration run download-outputs \\\n  --workflow-uuid \"$WF_UUID\" --output-node-slug action --format json | jq -r '.url')\" \\"},{"language":"bash","snippet":"# 1. Execute — returns a run object; note run.uuid and run.workflowUuid.\n#    searchLeads returns a 25-row page minimum (limit below 25 still bills 25 × 0.02 = 0.5 credits).\ncargo-ai orchestration action execute \\\n  --action '{\"kind\":\"connector\",\"integrationSlug\":\"salesNavigator\",\"actionSlug\":\"searchLeads\"}' \\\n  --data '{\"keywords\": \"\\\"<persona title phrase>\\\"\", \"limit\": 25}' \\\n  --wait-until-finished > /tmp/quickstart-run.json\n\n# 2. Fetch the output data (NOT in the execute stdout) — signed URL, then filter to THIS run\nRUN_UUID=$(jq -r '.run.uuid' /tmp/quickstart-run.json)\nWF_UUID=$(jq -r '.run.workflowUuid' /tmp/quickstart-run.json)\ncurl -s \"$(cargo-ai orchestration run download-outputs \\\n  --workflow-uuid \"$WF_UUID\" --output-node-slug action --format json | jq -r '.url')\" \\\n  > /tmp/quickstart-outputs.json\n\n# 3. Show the table (the file holds ALL of the workflow's runs — filter by _uuid;\n#    each row's .output is the leads array directly, fields are snake_case)\njq -r --arg u \"$RUN_UUID\" \\\n  '[.[] | select(._uuid==$u)][0].output[] | [.full_name, .job_title, .company_name, (.recently_hired // false)] | @tsv' \\\n  /tmp/quickstart-outputs.json | head -25"}],"parameters":null,"dependencies":[],"permissions":[],"extractedFiles":[{"path":"SKILL.md","content":"---\nname: cargo-quickstart\ndescription: \"Guided first-run demo for Cargo — one persona question to 25 real leads with a cost receipt in under two minutes, ending by saving the pull as a recurring play. Triggers: \\\"show me what Cargo can do\\\", \\\"give me a demo\\\", \\\"take me on a tour\\\", \\\"quickstart\\\", \\\"getting started with Cargo\\\", \\\"I just installed Cargo\\\", \\\"my workspace is empty\\\", \\\"does this actually work\\\". Skip when: the user has a real job to run (build a list, enrich a CSV, find emails) — use cargo-gtm; when they want CLI reference or routing — use the cargo router skill.\"\nversion: \"1.0.4\"\ncompatibility: Requires @cargo-ai/cli (npm). Sign in or create an account with `cargo-ai login --email` (emailed code, no browser), `--oauth`, or an API token\nhomepage: https://github.com/getcargohq/cargo-skills\nmetadata:\n  author: getcargo\n  openclaw:\n    requires:\n      bins:\n        - cargo-ai\n    install:\n      - kind: node\n        package: \"@cargo-ai/cli@latest\"\n        bins:\n          - cargo-ai\n    homepage: https://github.com/getcargohq/cargo-skills\n---\n\n# Cargo Quickstart — first value in two minutes\n\nOne guided demo: pull ~25 fresh leads matching a buyer persona the user picks, show the cost receipt, then save the pull as a recurring play. The point is not the list — it's that in minute 3 the user owns a running system, not a one-off result.\n\n**A new account starts with 100 free credits — no card.** This demo spends about **5** of them. Say that out loud before the first paid call (\"this costs about 5 of your 100 free credits\"): it converts the moment from *a purchase decision* into *a look around*, which is the whole job of a quickstart. Never let a new user think the demo is why they'd run out.\n\n## Bootstrap\n\nAlready signed in (`cargo-ai whoami` returns a workspace)? Skip to the next section.\n\n```bash\nnpm install -g @cargo-ai/cli            # no global install? prefix every command with `npx @cargo-ai/cli`\ncargo-ai login --email you@company.com  # emailed code, no browser; creates the account on first use\n                                        # alternatives: --oauth (browser) · --token <api-token> (CI)\ncargo-ai whoami                         # confirm the active workspace before any write\n```\n\nEvery command prints JSON to stdout; failures exit non-zero with `{\"errorMessage\": \"...\"}`. Anything that creates a run or a batch is async — pass `--wait-until-finished` or poll the matching `get`. When the full skill bundle is installed, [`../cargo/references/prerequisites.md`](../cargo/references/prerequisites.md) adds the CLI version pin, token scopes, and the admin-only surface.\n\n## The one question\n\nAsk exactly **one** question before doing anything:\n\n> **\"Who do you sell to?\"** (a persona in a few words — e.g. \"Heads of RevOps at mid-market SaaS\")\n\nEverything else — provider, filters, limits — you decide. Don't ask about output format, volume, or providers; defaults below.\n\n## Speed budget — HARD RULES\n\nThe demo has a two-minute budget from "},{"path":"_meta.json","content":"{\n  \"ownerId\": \"kn7by8t6yt9yghbxtxz6hv0bts87k6bq\",\n  \"slug\": \"cargo-quickstart\",\n  \"version\": \"1.0.4\",\n  \"publishedAt\": 1790966117726\n}"},{"path":"skill-card.md","content":"## Description:\n\nGuides a new Cargo user from a buyer persona to a short lead list and credit receipt, with an option to save the search as a recurring play.\n\nThis skill is ready for commercial/non-commercial use.\n\n## Publisher:\n\n[cargo-ai](https://clawhub.ai/user/cargo-ai)\n\n### License/Terms of Use:\n\nMIT-0\n\n## Use Case:\n\nSales and go-to-market users can try Cargo by searching for leads matching a chosen buyer persona, reviewing a credit receipt, and optionally saving the search as a weekly play.\n\n### Deployment Geography for Use:\n\nGlobal\n\n## Known Risks and Mitigations:\n\nRisk: A short demo request may trigger a paid lead search and spend Cargo credits without clear approval.\n\nMitigation: Confirm the active workspace, provider, lead limit, and expected credit cost before the first paid search.\n\nRisk: Fallback searches can use a different provider or cost more than the initial search.\n\nMitigation: Confirm the replacement provider and its cost before running any fallback, especially the higher-cost prospect search.\n\nRisk: A weekly saved play can generate future searches and charges.\n\nMitigation: Require separate explicit confirmation before enabling the recurring play.\n\n## Reference(s):\n\n- [Cargo skills homepage](https://github.com/getcargohq/cargo-skills)\n- [Cargo Quickstart on ClawHub](https://clawhub.ai/cargo-ai/skills/cargo-quickstart)\n\n## Skill Output:\n\n**Output Type(s):** [Text, Markdown, Shell commands, Guidance]\n\n**Output Format:** [Markdown lead table, credit receipt, and optional CLI instructions]\n\n**Output Parameters:** [1D]\n\n**Other Properties Related to Output:** [Lead count and credit use depend on connected providers; a recurring play is offered separately.]\n\n## Skill Version(s):\n\n1.0.4 (source: frontmatter and release evidence)\n\n## Ethical Considerations:\n\nUsers should evaluate whether this skill is appropriate for their environment, review any generated or modified files before relying on them, and apply their organization's safety, security, and compliance requirements before deployment."},{"path":"skill-metadata.json","content":"{\n  \"$comment\": \"Generated by .github/scripts/skills-metadata.mjs — do not hand-edit. Regenerate with: node .github/scripts/skills-metadata.mjs --write .\",\n  \"name\": \"cargo-quickstart\",\n  \"version\": \"1.0.4\",\n  \"documents\": [\n    {\n      \"path\": \"SKILL.md\",\n      \"kind\": \"entrypoint\",\n      \"title\": \"Cargo Quickstart — first value in two minutes\"\n    }\n  ],\n  \"contentHash\": \"1d8b0525e2cf4e310892cae8d12354f32111b134d38d3b3307cb74221857cee7\"\n}"}],"languages":[],"docsSourceLabel":"CLAWHUB","editorialOverview":"Guided first-run demo for Cargo — one persona question to 25 real leads with a cost receipt in under two minutes, ending by saving the pull as a recurring play. Triggers: \"show me what Cargo can do\", \"give me a demo\", \"take me on a tour\", \"quickstart\", \"getting started with Cargo\", \"I just installed Cargo\", \"my workspace is empty\", \"does this actually work\". Skip when: the user has a real job to run (build a list, enrich a CSV, find emails) — use cargo-gtm; when they want CLI reference or routing — use the cargo router skill. Skill: cargo-quickstart Owner: cargo-ai Summary: Guided first-run demo for Cargo — one persona question to 25 real leads with a cost receipt in under two minutes, ending by saving the pull as a recurring play. Triggers: \"show me what Cargo can do\", \"give me a demo\", \"take me on a tour\", \"quickstart\", \"getting started with Cargo\", \"I just installed Cargo\", \"my workspace is empty\", \"does this actually work\". Skip when:","editorialQuality":{"score":100,"threshold":65,"status":"ready","wordCount":1458,"uniquenessScore":46,"reasons":[]}},"media":{"evidence":{"source":"no-media","verified":false,"confidence":"low","updatedAt":"2026-10-11T22:02:19.829Z","emptyReason":"No screenshots, media assets, or demo links are available."},"primaryImageUrl":null,"mediaAssetCount":0,"assets":[],"demoUrl":null},"ownerResources":{"evidence":{"source":"unclaimed","verified":false,"confidence":"low","updatedAt":"2026-10-11T22:02:19.829Z","emptyReason":"This page has not been claimed by the agent owner."},"hasCustomPage":false,"customPageUpdatedAt":null,"customLinks":[],"structuredLinks":{"docsUrl":null,"demoUrl":null,"supportUrl":null,"pricingUrl":null,"statusUrl":null},"customPage":null},"relatedAgents":{"evidence":{"source":"protocol-neighbors","verified":false,"confidence":"medium","updatedAt":"2026-10-12T18:25:37.666Z","emptyReason":null},"items":[{"id":"8ebccd8e-3863-4187-8355-c3f14e1f9edf","entityType":"agent","canonicalPath":"/agent/iofficeai-aionui","slug":"iofficeai-aionui","name":"AionUi","description":"Free, local, open-source 24/7 Cowork app and OpenClaw for Gemini CLI, Claude Code, Codex, OpenCode, Qwen Code, Goose CLI, Auggie, and more | 🌟 Star if you like it!","url":"https://github.com/iOfficeAI/AionUi","homepage":"https://www.aionui.com","source":"GITHUB_REPOS","protocols":["MCP","OPENCLAW"],"capabilities":[],"safetyScore":100,"overallRank":70,"updatedAt":"2026-10-09T19:11:12.944Z","createdAt":"2026-02-25T03:38:16.584Z","downloads":null},{"id":"b917f68a-ebff-438e-84f8-3f4b2494c0bc","entityType":"agent","canonicalPath":"/agent/activepieces-activepieces","slug":"activepieces-activepieces","name":"activepieces","description":"AI Agents & MCPs & AI Workflow Automation • (~400 MCP servers for AI agents) • AI Automation / AI Agent with MCPs • AI Workflows & AI Agents • MCPs for AI Agents","url":"https://github.com/activepieces/activepieces","homepage":"https://www.activepieces.com","source":"GITHUB_REPOS","protocols":["OPENCLAW"],"capabilities":[],"safetyScore":100,"overallRank":70,"updatedAt":"2026-04-15T02:22:12.426Z","createdAt":"2026-02-25T03:38:12.412Z","downloads":null},{"id":"5cb26759-3a39-483f-94cf-276a98c13bb8","entityType":"agent","canonicalPath":"/agent/cherryhq-cherry-studio","slug":"cherryhq-cherry-studio","name":"cherry-studio","description":"AI productivity studio with smart chat, autonomous agents, and 300+ assistants. Unified access to frontier LLMs","url":"https://github.com/CherryHQ/cherry-studio","homepage":"https://cherry-ai.com","source":"GITHUB_REPOS","protocols":["MCP","OPENCLAW"],"capabilities":[],"safetyScore":100,"overallRank":70,"updatedAt":"2026-04-11T14:38:40.986Z","createdAt":"2026-02-25T03:38:19.379Z","downloads":null},{"id":"6f6582d0-5d76-4f0f-b81d-86520247950b","entityType":"agent","canonicalPath":"/agent/copilotkit-copilotkit","slug":"copilotkit-copilotkit","name":"CopilotKit","description":"The Frontend for Agents & Generative UI. React + Angular","url":"https://github.com/CopilotKit/CopilotKit","homepage":"https://docs.copilotkit.ai","source":"GITHUB_REPOS","protocols":["OPENCLAW"],"capabilities":[],"safetyScore":100,"overallRank":70,"updatedAt":"2026-03-25T09:50:57.846Z","createdAt":"2026-02-25T03:39:14.617Z","downloads":null}],"links":{"hub":"/agent","source":"/agent/source/clawhub","protocols":[{"label":"OpenClaw","href":"/agent/protocol/openclew"}]}}}