Skip to content

gooseworks-ai/goose-skills / skills/marketing/write-outreach

write-outreach

Verified

Cold outreach a person sends to business buyers: email and LinkedIn sequences, a first line per prospect, reply and objection answers, and a read of replies. Use when the marketer says "write a cold email sequence", "what do I send to this list", "write LinkedIn messages for these leads", "how do I reply to this prospect" or "handle this objection", "reply to this demo request", "win back or reconnect with accounts that churned or went quiet", or "why is nobody replying to my outreach". Drafts only; the marketer sends from their own tool. Not for finding the people — use research-audience; not for emails to subscribers or users, or consumer win-back — use email-lifecycle.

skill.meta.json

View on GitHub
{
  "slug": "write-outreach",
  "category": "playbooks",
  "tier": "playbook",
  "version": "0.2.2",
  "tags": [
    "outreach",
    "sales"
  ],
  "collections": [
    "brand-growth"
  ],
  "collection_stage": "create",
  "requires_skills": [
    "claims-gate",
    "marketing-data-access",
    "marketing-guide",
    "outcomes-ledger",
    "run-memory",
    "save-learning",
    "save-to-brain",
    "spend-gate",
    "voice-card",
    "write-outreach-draft-sequence",
    "write-outreach-outreach-qa",
    "write-outreach-reply-reader",
    "write-report"
  ],
  "pillar": "8 — Outbound (writing; sending stays with the marketer)",
  "intents": [
    "Write a cold email sequence for this list",
    "What do I send to these prospects?",
    "Write LinkedIn connection notes and messages for these leads",
    "First lines for my prospects, from their buying signals",
    "How do I reply to this prospect? / Handle this objection",
    "Win back business accounts that churned",
    "Why is nobody replying to my outreach?"
  ],
  "reads": [
    "Brand Brain when brand_knowledge_* tools are listed: brand_knowledge_browse first (core rules, never-list, waiting items, chapters 14, 22, 23, products), brand_knowledge_search for lessons and signed-off claims; fallback brand_read + knowledge_search",
    "workspace research/audience/ — newest <date>-<list>/list.csv (rows, segments, signals, hooks, region flags), fit-definition.md, buyer-groups.md, voc-bank.md, ledger.csv, lessons/ (research-audience)",
    "workspace outreach/ — earlier packs, results and lessons (this playbook)",
    "claims via claims-gate (its scoped sign-off, or earlier records by learn-my-brand, unreleased) — every proof line",
    "brand brain: summary, kit, products with prices, learnings incl. [outreach …] rules (server research and the app, save-learning; learn-my-brand, unreleased)",
    "the sender's voice card brand/voices/<handle>.md if one exists (voice-card, read only)",
    "human-supplied: replies, campaign stats, churned-account list (win-back), the sending tool's import format",
    "run records runs/write-outreach/outreach/<pack-slug>/… (run-memory) and the ledger for per-segment and per-opener outcomes"
  ],
  "writes": [
    "local gooseworks-reports/<brand-slug>/<date>-outreach.md and workspace outreach/<date>-<slug>/pack.md → 'Outreach pack — <Brand> — <date>' (keep-history) via write-report and save-to-brain — read by the marketer and the next run",
    "local gooseworks-reports/<brand-slug>/<date>-outreach-send.csv and workspace outreach/<date>-<slug>/send.csv (never imported to the brain — people's data) — read by the marketer's sending tool",
    "workspace outreach/<date>-<slug>/results.md → 'Outreach results — <Brand> — <date>' (keep-history) — read by the next pack and research-audience",
    "research/audience/ledger.csv statuses and research/audience/lessons/<date>.md via outcomes-ledger (entity: person) — read by research-audience and the next pack",
    "run records runs/write-outreach/outreach/<pack-slug>/<date>.md (keep-history) via run-memory — counts, rates and links only; ledger opener_id and sequence_id columns at delivery"
  ],
  "needs": {
    "mcp": [
      "gooseworks:get_started",
      "gooseworks:tools_load",
      "gooseworks:brand_read",
      "gooseworks:knowledge_search",
      "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:brand_knowledge_browse",
      "gooseworks:brand_knowledge_read",
      "gooseworks:brand_knowledge_search"
    ]
  }
}
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: 115kUpdated Claude CodeCodexVerifiedInstall
add-runner-evalpaperclipai/paperclipAdd or extend a Paperclip Runner protocol evaluation definition, roster, assertion, or report fixture with provenance and narrow validation.Stars: 115kUpdated Claude CodeCodexVerifiedInstall
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: 115kUpdated Claude CodeCodexVerifiedInstall
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: 115kUpdated Claude CodeCodexVerifiedInstall