Update to ACA

{
  "description": "Build lookalike lead lists in ACA from a winning customer, lead list, campaign, or contact segment. Use when the user asks for more leads like these, clones of a customer profile, or lookalike prospecting.",
  "included_files": [],
  "name": "aca-lookalike-leads",
  "skill_md_contents": "---\nname: aca-lookalike-leads\ndescription: \"Build lookalike lead lists in ACA from a winning customer, lead list, campaign, or contact segment. Use when the user asks for more leads like these, clones of a customer profile, or lookalike prospecting.\"\nlicense: MIT\ncompatibility: Requires the ACA connector (OAuth sign-in, no API key).\nmetadata:\n  author: ACA\n  version: \"1.1\"\n  homepage: https://www.automatedclientacquisition.com/mcp\n---\n\n# ACA lookalike leads\n\nUse an existing winning segment in ACA to define a new prospect audience. The connector reads the seed; the search for new lookalikes runs in the ACA app.\n\n## Rules\n\n- Use the ACA connector only. Never invent people, companies, or counts.\n- Derive traits only from data ACA returns or the user provides. State which traits are copied and which are excluded.\n- The connector cannot search ACA's lead database or run imports. Turn the traits into a search spec, then send the user to `/list-building` or `/leads/import`.\n- Ask before creating lists or adding contacts.\n- If a tool result includes `plan_note` or `plan.limitation`, relay it as a plain fact. Never promote plans, pricing, or upgrades.\n\n## Workflow\n\n### 1. Read the workspace\n\nCall `get_started` (fallback: `get_workspace`, `list_lead_lists`, `list_campaigns`).\n\n### 2. Identify the seed\n\n- A lead list: `list_lead_lists`, then `get_lead_list`\n- A set of contacts (customers, tagged winners, replied leads): `search_contacts`, then `get_contact` for detail on a sample\n- A winning campaign: `list_campaigns`, `get_campaign`, and `get_campaign_metrics` to confirm it actually performed; then use the lead list it targets if the result shows one\n\nWork from a sample of 20 to 50 seed contacts. If the seed is under 10 people, say the traits are directional.\n\n### 3. Extract shared traits\n\nLook for what most of the seed has in common:\n\n- Role and seniority\n- Industry and keywords\n- Geography\n- Company size\n- Channel availability (email, LinkedIn)\n- Tags and stage\n\nSeparate **copied traits** (shared by most of the seed) from **excluded traits** (noise, one-offs, or things the user wants to avoid, such as current customers or competitors).\n\n### 4. Write the lookalike spec\n\n```text\nLookalike spec: {list name}\nSeed: {list or segment, n contacts}\nWhere: /list-building (database) | /leads/import (LinkedIn)\nCopied traits: {roles, seniority, industry, geo, size, channel}\nExcluded: {traits, existing customers, seed companies}\nTarget count: {n}\n```\n\nSend the user to `/list-building` first; use `/leads/import` with a LinkedIn search when the database is thin or the seed is LinkedIn-native. Remind them to exclude seed companies so the new list is net new.\n\n### 5. Pick up and verify\n\nWhen the user says the list is built, find it with `list_lead_lists` and check it with `get_lead_list`. Compare the sample against the copied traits, then route to `aca-lead-quality`.\n\n## Output format\n\n```text\nLookalike list plan:\nSeed: {seed} ({n} contacts reviewed)\nCopied traits: {traits}\nExcluded traits: {exclusions}\nBuild at: {app page}\nBuilt list: {list_id, count | pending}\nNext: {aca-lead-quality | wait for build}\n```\n\n## Skill chaining\n\nPreserve the workspace, seed IDs, the lookalike spec, and approval state when continuing into another ACA skill. If the user asked for execution and a downstream condition is met, continue automatically; otherwise end with the handoff block.\n\n**Upstream**\n- Called when `aca-find-leads`, `aca-positive-reply-scoring`, or `aca-weekly-rhythm` finds a winning segment.\n\n**Auto-continue conditions**\n- Lookalike list exists in ACA: continue to `aca-lead-quality`.\n- Lookalike is based on reply winners: continue to `aca-experiment-design` after quality scoring.\n\n**Stop before chaining when**\n- The build or import still has to run in the ACA app.\n- Creating lists the user has not approved.\n\n**Downstream skills**\n- `aca-lead-quality` - validate lookalike quality.\n- `aca-experiment-design` - test the lookalike against the control audience.\n- `aca-launch-outreach` - launch when ready.\n\n**Handoff block**\n\n```text\nChain state: {continue|needs_approval|blocked|complete}\nNext skill: {aca-skill-name|none}\nReason: {why this handoff is or is not needed}\nCarry forward: {workspace, seed lead_list_id or campaign_id, lookalike spec, new lead_list_id, approvals, constraints}\n```\n\n## ACA tools used\n\n- `get_started`, `get_workspace`\n- `list_lead_lists`, `get_lead_list`\n- `search_contacts`, `get_contact`\n- `list_campaigns`, `get_campaign`, `get_campaign_metrics`\n\n## ACA app pages\n\n- Database search: `https://www.automatedclientacquisition.com/list-building`\n- LinkedIn or CSV import: `https://www.automatedclientacquisition.com/leads/import`\n"
}