{"id":106049,"plugin_id":"plugin_asdk_app_6af70961bf6881919829ad5625fb1d9d","kind":"skill","collection_source":"plugin_package","comparison_source":null,"observed_at":"2026-11-19T12:18:57.470Z","digest":"950f21eeb1a27c05e80fca5f39bbd205449bc20150b42e78e34869402706850e","against":null,"payload":{"description":"Find companies that are similar to a set of example companies, for example the user's best customers. Use when the user asks for lookalikes, \"more companies like these\", \"companies similar to our customers\" or to grow a target account list from examples.","included_files":[],"name":"find-lookalike-companies","skill_md_contents":"---\nname: find-lookalike-companies\ndescription: Find companies that are similar to a set of example companies, for example the user's best customers. Use when the user asks for lookalikes, \"more companies like these\", \"companies similar to our customers\" or to grow a target account list from examples.\n---\n\n# Find lookalike companies\n\nThe `similar_company_expansion` workflow starts from a dataset of example\ncompanies (the seed) and makes a new dataset of similar companies. It uses\ncredits. The result can have thousands of companies.\n\n## Steps\n\n1. **Preview the direction.** Call `search` with a request such as\n   \"companies similar to acme.com and example.com\". Show 10 rows with\n   `preview_dataset`. Ask the user if the companies are the correct type. If\n   they are not, ask the user for better examples.\n2. **Make the seed dataset.** Use one of these:\n   - A list from the user: use the `import-and-match` skill.\n   - An earlier search or dataset: use its dataset ID.\n\n   If the user has more than one account, pass the same `account_id` on every\n   call.\n3. **Write the guidance (optional).** If the seed companies are mixed (for\n   example different industries or sizes), write short instructions in\n   `firmographics_guidance`, for example \"only B2B SaaS companies in the US with\n   50-500 employees\".\n4. **Ask how many companies the user wants.** Tell the user that a full run can\n   return a large number of companies.\n5. **Get a quote.** Call `run_workflow` with\n   `workflow=\"similar_company_expansion\"`, the seed `dataset_id` and\n   `params={\"firmographics_guidance\": \"...\"}`, without `confirm`. Show the quote\n   to the user and ask for approval.\n6. **Run.** After the user agrees, call `run_workflow` again with the same\n   arguments and `confirm=true`. Call `get_workflow_run` until the status is\n   `SUCCEEDED`. The new companies are in the `output_dataset_id`.\n7. **Show the result.** Call `get_dataset` and `preview_dataset`. To keep only\n   the number that the user asked for, call `transform_dataset` with a `LIMIT`\n   or a `WHERE` clause.\n\n## Rules\n\n- Use an `output_dataset_id` only when its run status is `SUCCEEDED`.\n  `transform_dataset` can return while its run is `RUNNING`. Then call\n  `get_workflow_run` with its `workflow_run_id` until the run stops. If the\n  status is `FAILED` or `CANCELLED`, stop and tell the user the reason.\n- Do not start a paid run without a quote and the user's approval.\n- Keep the `workflow_run_id`. A timeout does not stop the run. Check the status\n  before you start the run again.\n"},"changes":[],"summary":"First saved snapshot. No earlier version is available for comparison.","summary_kind":"deterministic","summary_metadata":{}}