gooseworks-ai/goose-skills / skills/marketing/research-audience
research-audience
VerifiedAudience research: who the buyers are, in their own words, where they gather and how to reach them — plus named prospect lists when asked. Use when the marketer says "research our audience", "who should we target", "mine our reviews", "why do people buy us or leave", "where does our audience hang out"; or for lists: "find 50 right-fit leads with emails", "find retailers or accounts to pitch", "score these leads / who do we call first", "who's looking for an alternative to X", "tell me when a past champion changes jobs". Reads the brand's own customer data first and delivers a readable report saved to the brand. Never contacts anyone. Not for market size or trends — use research-market; not for writing the messages — use write-outreach.
| File | Kind | Size |
|---|---|---|
| SKILL.md | skill md | 18.7 KB |
| references/audience-research.md | markdown | 15.9 KB |
| references/contacts-and-compliance.md | markdown | 9.7 KB |
| references/data-sources.md | markdown | 12.3 KB |
| references/fit-and-scoring.md | markdown | 7.6 KB |
| references/list-by-company-type.md | markdown | 4.5 KB |
| references/list-mode.md | markdown | 7.5 KB |
| references/list-sources.md | markdown | 9.9 KB |
| references/output-format.md | markdown | 5.3 KB |
| references/quote-bank.md | markdown | 6.3 KB |
| references/run-memory.md | markdown | 5.2 KB |
| references/score-a-list.md | markdown | 7.6 KB |
| references/signals-and-hooks.md | markdown | 6.1 KB |
| references/watches.md | markdown | 4.7 KB |
| skill.meta.json | config | 6.3 KB |
| tests/test-by-hand.md | markdown | 8.9 KB |
skill.meta.json
View on GitHub{
"slug": "research-audience",
"category": "playbooks",
"tier": "playbook",
"version": "0.8.3",
"tags": [
"research",
"lead-generation"
],
"collections": [
"brand-growth"
],
"collection_stage": "research",
"requires_skills": [
"claims-gate",
"marketing-data-access",
"marketing-guide",
"outcomes-ledger",
"research-audience-account-sourcing",
"research-audience-fit-definition",
"research-audience-people-and-contacts",
"research-audience-score-segment-qa",
"research-audience-segment-pass",
"research-audience-signals-and-hooks",
"run-memory",
"save-learning",
"save-to-brain",
"spend-gate",
"write-report"
],
"pillar": "3 — Customers and audience (owns buyer groups and the quote bank) · 8 — Outbound (list mode: build, score, watch)",
"intents": [
"Research our audience",
"Who is my customer / who are our buyers?",
"Build buyer personas",
"Voice of customer — mine our reviews; what words do customers use?",
"Why do people buy us or leave?",
"Where does our audience hang out?",
"How do we reach them?",
"Find me 50 right-fit people with emails (list mode)",
"Build a prospect or ABM list; find retail buyers or distributors (list mode)",
"Score these leads / which inbound leads do we answer first? (list mode)",
"Who's looking for an alternative to <rival>? (list mode, switch intent)",
"Tell me when a past champion changes jobs / when target accounts start hiring (list mode, watch)"
],
"reads": [
"Brand Brain when brand_knowledge_* tools are listed: brand_knowledge_browse first (core rules, never-list, items waiting for a yes, audience and customer chapters, 14, 22, 23), brand_knowledge_read / brand_knowledge_search for the task; fallback brand_read + knowledge_search",
"the brand's own customer data, asked for once up front when it has customers: customer or order export, cancel reasons, win/loss notes, support themes (counts and patterns only reach the brain)",
"brand brain: summary, kit audience text, products, competitors, organic, learnings (server research and the app; learn-my-brand, unreleased); customer evidence via knowledge_search",
"workspace research/market/ — latest market report (research-market): its market figures are context, group sizes are counted here; read for consistency",
"workspace research/competitors/ — rival records and report (research-competitors): read for consistency",
"workspace research/audience/ — buyer groups, quote bank, last report, group notes, ledger (this playbook, earlier runs); research/credits-log/<YYYY-MM>.md (spend-gate)",
"claims via claims-gate (its scoped sign-off, or earlier records by learn-my-brand, unreleased) — for messages and proof lines",
"human-supplied (list mode): exclusions export, email-checker results, outreach outcomes",
"human-supplied (list mode): a list to score (sign-ups, demo requests, webinar or event attendees they collected), a champions list, a target-account list for watches",
"public sources (list mode): Hacker News search API, public GitHub API, event speaker and sponsor pages, rivals' customer pages",
"run records runs/research-audience/<job-slug>/… (run-memory) — the last run of the same job; outreach/*/results.md and the ledger for what earlier lists led to"
],
"writes": [
"local gooseworks-reports/<brand-slug>/<date>-audience.md and workspace research/audience/<date>-report.md → 'Audience report — <Brand> — <date>' (keep-history) via write-report and save-to-brain — read by the marketer, the next run, research-market and research-competitors",
"workspace research/audience/buyer-groups.md → 'Buyer groups — <Brand> — <date>' (supersede) — the one list of buyer groups; read by research-market, plan-campaign, make-content, run-organic-social, the static-ad maker (make-static-ads), work-with-creators, list mode",
"workspace research/audience/voc-bank.md → 'Voice-of-customer bank — <Brand> — <date>' (supersede) and voc-bank.jsonl (not imported) — the quote bank; read by the static-ad maker (make-static-ads), make-content, run-organic-social, research-competitors, plan-campaign",
"brand audience: one brand_knowledge_save audience item per group when brand_knowledge_* tools are listed (waits for the marketer's yes), else brand_update knowledge.audience agent_proposal — skipped when the lead is provisional",
"workspace research/audience/segments/<slug>.md — read by the next run",
"research/credits-log/<YYYY-MM>.md rows — read by every playbook's spend estimates",
"list mode: local gooseworks-reports/<brand-slug>/<date>-list.md + <date>-list.csv; workspace research/audience/<date>-<list>/report.md → 'Prospect list report — <Brand> — <date>' (keep-history, no people's data), list.csv, segments.csv, catch-all.csv, dropped.csv (not imported); research/audience/ledger.csv via outcomes-ledger — read by write-outreach, the marketer's outreach tool and later runs",
"research/audience/fit-definition.md — read by list mode, score-a-list and write-outreach",
"watches: research/audience/watch/champions.csv, accounts.csv (not imported), watch/<date>.md — read by the scheduled watch and the marketer",
"run records runs/research-audience/<job-slug>/[<subject>/]<date>.md → 'Run record — <job>[ — <subject>] — <Brand> — <date>' (keep-history) via run-memory — counts and links only, read by the next run of the job"
],
"needs": {
"mcp": [
"gooseworks:get_started",
"gooseworks:tools_load",
"gooseworks:account_whoami",
"gooseworks:brand_read",
"gooseworks:knowledge_search",
"gooseworks:competitor_read",
"gooseworks:data_call_provider",
"gooseworks:file_list",
"gooseworks:file_read",
"gooseworks:file_write",
"gooseworks:file_url",
"gooseworks:media_upload",
"gooseworks:knowledge_import",
"gooseworks:job_get",
"gooseworks:brand_update",
"gooseworks:automation_upsert",
"gooseworks:media_list",
"gooseworks:media_update",
"gooseworks:automation_list",
"gooseworks:brand_knowledge_browse",
"gooseworks:brand_knowledge_read",
"gooseworks:brand_knowledge_search",
"gooseworks:brand_knowledge_save",
"gooseworks:marketing_data_describe",
"gooseworks:marketing_data_lookup"
]
}
}
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| add-product-e2e-evalpaperclipai/paperclipAdd or extend a Paperclip full-stack runner E2E workflow, fixture, matcher, or report evidence path for local or Daytona execution. | Stars: 115k | Updated | Claude CodeCodex | Verified | Install |
| add-runner-evalpaperclipai/paperclipAdd or extend a Paperclip Runner protocol evaluation definition, roster, assertion, or report fixture with provenance and narrow validation. | Stars: 115k | Updated | Claude CodeCodex | Verified | Install |
| diagnose-why-work-stoppedpaperclipai/paperclipCompatibility entry point for failed, stalled, looping, or over-recovered Paperclip work. Use fix-failed-paperclip-run for the full diagnosis, regression, repair, real verification, and green-PR workflow; honor an explicitly requested diagnosis-only scope. | Stars: 115k | Updated | Claude CodeCodex | Verified | Install |
| fix-failed-paperclip-runpaperclipai/paperclipDiagnose and fix failed, stuck, slow, or incorrectly blocked Paperclip tasks and runs. Use with a task/run URL or failure report to trace the root cause, prove a regression red then green, check second-order effects, verify the real workflow, and deliver a PR with passing checks. | Stars: 115k | Updated | Claude CodeCodex | Verified | Install |