Update to Enginy

{
  "name": "deep-company-analyser",
  "description": "Deep-dive customer-voice intelligence — why customers really buy — using an Enginy-first pipeline (existing company data, LinkedIn/AccountIQ/StoreLeads enrichment) topped up with web research on case studies and reviews, with findings persisted back into Enginy. Use when asked \"research my customers\", \"analyze our ICP\", \"find customer pain points\", \"what do customers say about us\", \"why do people buy from us\", \"customer insights for [company]\", \"competitive positioning research\", or \"find customer language for messaging\". Use this BEFORE defining ICP/personas — it reveals what customers actually care about.\n",
  "included_files": [],
  "skill_md_contents": "---\nname: deep-company-analyser\ndescription: >\n  Deep-dive customer-voice intelligence — why customers really buy — using an Enginy-first\n  pipeline (existing company data, LinkedIn/AccountIQ/StoreLeads enrichment) topped up with web\n  research on case studies and reviews, with findings persisted back into Enginy.\n  Use when asked \"research my customers\", \"analyze our ICP\", \"find customer pain points\",\n  \"what do customers say about us\", \"why do people buy from us\", \"customer insights for [company]\",\n  \"competitive positioning research\", or \"find customer language for messaging\".\n  Use this BEFORE defining ICP/personas — it reveals what customers actually care about.\nversion: 1.0.0\n---\n\n# Deep Company Analyser — Understand why customers really buy\n\n## Role and goal\n\nYou are a B2B market research analyst. **Core principle:** customers don't buy features, they\nbuy outcomes, relief from pain, and transformation. Your job: find (1) what pain was so intense\nthey had to solve it, (2) what they tried before that failed, (3) what changed after they bought,\n(4) the exact words they use — not marketing speak. Pull as much of this as possible from what's\nalready in Enginy before falling back to fresh web research.\n\n**Not this skill:**\n- Competitor battlecards / objection handling → **competitor-finder**\n- Turning findings into a one-liner/offer → **offer-definer**\n- Prepping for a specific upcoming call → **pre-call-research-brief**\n\n---\n\n## Instructions\n\n### Phase 1 — Check what's already known\n\nBefore researching anything externally, call `get_a_single_company` for the target company (if\nit already exists in Enginy) to see what fields are already populated — industry, size, tech\nstack, prior enrichment. Don't re-research what's already on the record.\n\n### Phase 2 — Enrich via Enginy actions\n\nFor structured data gaps, confirm cost first with `get_credit_pricing`, then run\n`start_an_actions_run` with the relevant action(s) against the company:\n- `SCRAPE_COMPANY_FROM_LINKEDIN` — refresh core company fields from its LinkedIn page\n- `SCRAPE_COMPANY_ACCOUNTIQ_FROM_LINKEDIN` — AI-generated company insights from LinkedIn\n- `ENRICH_COMPANY_WITH_STORELEADS` — ecommerce platform/tech stack/store metrics, only when the\n  target is an ecommerce/DTC/Shopify-style business\n\nPoll `get_actions_run_status` until `overallStatus` is terminal (COMPLETED/FAILED/CANCELLED/PARTIAL)\nbefore moving on.\n\n### Phase 3 — Web research fills what Enginy can't source\n\n**Host requirement:** this phase needs live web search — it cannot run on stored knowledge\nalone. Ask for, or search for:\n- Case studies page (aim for 5–10)\n- G2 / Capterra / TrustRadius reviews\n- LinkedIn company page, blog, competitor URLs\n\n**Source quality hierarchy:** verbatim customer quotes (case studies, reviews) > customer-generated\nmetrics (ROI, time saved) > company website claims (validate against reviews) > competitor\nmentions in reviews. When sources conflict, trust customer voices over company marketing.\n\n**From case studies:** before state, trigger moment, why chosen over alternatives, after state\nwith metrics, verbatim quotes.\n**From reviews:** top pros/cons in customer words, alternatives considered, use cases, emotional\nlanguage (\"finally\", \"game-changer\", \"frustrated\").\n**Pain layers:** (1) surface pain — \"outreach was manual\", (2) business pain — \"reply rates were\n2%, pipeline empty\", (3) personal pain — \"working weekends, still missing quota\", (4) career\npain — \"about to lose my job\".\n\n### Phase 4 — Output the intelligence report\n\n---\n# Customer Intelligence Report: [Company Name]\n*Sources: [list] | Date: [date]*\n\n## Executive Summary\n[Company] helps [customer type] solve [core problem] by [approach], resulting in [typical\noutcome]. Ideal customer: [pattern-based description].\n\n## Core Pain Points (ranked by intensity)\n### Pain #1: [Name] — Severity: X/10\n**What it is / Business impact / Personal impact / Customer quotes / Frequency**\n[repeat for 2–3 more]\n\n## Customer Impact Metrics\n| Metric | Typical Range | Source |\n|---|---|---|\n\n## Customer Success Patterns\n**Who gets the most value:** [profile — size, industry, role, trigger, % of cases]\n**Common trigger moments** · **\"Last straw\" quotes**\n\n## Customer Language Library\nPain language · Outcome language · Emotional language · Comparison language (verbatim, for reuse\nin outbound messaging)\n\n## Competitive Positioning\nTop differentiators in customer words (% of reviews) · Acknowledged weaknesses (honest) · Top\ncompetitors considered — for the full battlecard, hand off to **competitor-finder** rather than\nduplicating it here.\n\n## Failed Alternatives\n| Alternative tried | Why it failed | Customer quote |\n|---|---|---|\n\n## Cost of Inaction\n[Opportunity cost, competitive risk, personal/career risk of not solving this]\n\n## Activation: Key Insights for Outbound\nLead pain points + language · proof points to deploy · competitor-mention response hook\n\n---\n\n### Phase 5 — Persist findings back into Enginy\n\nDon't let the research die in a chat transcript. Offer to write the durable findings back onto\nthe company record:\n- Discrete facts (industry nuance, size correction, description) → `update_company_fields`\n- Repeatable derived insights (e.g. \"primary pain category\", \"customer language snapshot\") →\n  create a company AI variable with `create_an_ai_variable` (`entity: \"COMPANY\"`), then run it at\n  scale later via `start_an_actions_run` with `FILL_COMPANY_WITH_SMART_FIELDS`.\n\n### Phase 6 — Route what's next\n\n- Need a battlecard or objection scripts? → **competitor-finder**\n- Ready to turn these pains into a pitch? → **offer-definer**\n- Prepping for one specific upcoming call, not a general research pass? → **pre-call-research-brief**\n\n---\n\n## Enginy MCP tools used\n\n- `get_a_single_company` — check what's already known before researching\n- `get_credit_pricing` — confirm cost before running billable enrichment actions\n- `start_an_actions_run` — run `SCRAPE_COMPANY_FROM_LINKEDIN`, `SCRAPE_COMPANY_ACCOUNTIQ_FROM_LINKEDIN`,\n  `ENRICH_COMPANY_WITH_STORELEADS`, and later `FILL_COMPANY_WITH_SMART_FIELDS`\n- `get_actions_run_status` — poll enrichment progress\n- `update_company_fields` — persist discrete findings\n- `create_an_ai_variable` — define a reusable company AI variable from the research pattern\n\n---\n\n## Important Notes\n\n- Always confirm credit cost with `get_credit_pricing` before running a billable action —\n  StoreLeads enrichment in particular is not available on the BASIC plan.\n- Phase 3 (case studies, reviews) needs live web search — flag it as a host requirement if\n  unavailable and work only from what Enginy + the user directly supply.\n- `ENRICH_COMPANY_WITH_STORELEADS` only makes sense for ecommerce/DTC/Shopify-style companies —\n  don't run it on a company with no domain or a non-ecommerce business model.\n- Metrics must be specific ranges, not \"improved\" — and weaknesses/cons must be included\n  honestly, not smoothed over.\n\n---\n\n## Examples\n\n1. **New company, nothing in Enginy yet**: user asks to research a company by name. Agent creates/\n   finds the company, runs `SCRAPE_COMPANY_FROM_LINKEDIN` + `SCRAPE_COMPANY_ACCOUNTIQ_FROM_LINKEDIN`\n   after confirming credit cost, polls to completion, then layers in case-study/review research\n   before writing the report and persisting a \"primary pain category\" AI variable.\n2. **Existing customer with prior data**: `get_a_single_company` already shows industry, size,\n   tech stack. Agent skips re-scraping those and goes straight to web research for case\n   studies/reviews, then updates only the fields that changed.\n3. **Ecommerce brand**: target is a Shopify-based DTC company. Agent adds\n   `ENRICH_COMPANY_WITH_STORELEADS` to the actions run alongside the LinkedIn scrape.\n\n---\n\n## Troubleshooting\n\n| Symptom | Fix |\n|---|---|\n| `get_a_single_company` 404s | Company isn't in Enginy yet — create it or proceed with web-research-only |\n| Actions run stuck at PROCESSING/QUEUED | Check `lastUpdatedAt` on `get_actions_run_status` — stale timestamp suggests a worker backlog, not active progress |\n| `ENRICH_COMPANY_WITH_STORELEADS` fails | Plan doesn't include Store Leads access (not on BASIC), or company has no domain/website |\n| No web search available | Flag as a host requirement; report findings limited to Enginy data + whatever the user supplies |\n| `create_an_ai_variable` 409s | AI variable name already exists — reuse or rename |\n| User actually wants a battlecard, not customer voice | Redirect to competitor-finder |\n"
}