gooseworks-ai/goose-skills / skills/marketing/write-outreach
write-outreach
VerifiedCold 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.
| File | Kind | Size |
|---|---|---|
| SKILL.md | skill md | 16.7 KB |
| references/angles-by-signal.md | markdown | 7.3 KB |
| references/email-craft.md | markdown | 5.7 KB |
| references/handoff-and-compliance.md | markdown | 9.1 KB |
| references/linkedin-craft.md | markdown | 3.4 KB |
| references/outreach-by-company-type.md | markdown | 3.3 KB |
| references/reading-results.md | markdown | 5.9 KB |
| references/replies-and-objections.md | markdown | 4.8 KB |
| references/run-memory.md | markdown | 6.0 KB |
| references/sequences.md | markdown | 4.7 KB |
| skill.meta.json | config | 3.7 KB |
| tests/test-by-hand.md | markdown | 3.6 KB |
references/sequences.md
View on GitHub# Sequences
Load at step 2. A sequence is a small set of touches across email and LinkedIn, each with a new reason to reply, ending politely. Touch 1 brings most replies; follow-ups still add a real share, so they're not optional — but a follow-up that adds nothing hurts.
## Default shapes
**Signal-led cold (the default)** — **at most 6 touches in all** (4 emails, the connection request, one LinkedIn message) over about three weeks:
| Day | Channel | Touch | Words / chars | What it adds |
|---|---|---|---|---|
| 1 | Email | Signal → proof → ask | 50–90 words | Their signal and our relevance |
| 2–3 | LinkedIn | Connection note | ≤200 chars | A face and a reason to connect, no pitch |
| 4–5 | Email (same thread) | New angle | 30–50 | A second pain, or a short resource ("one-page breakdown, no pitch — want it?") |
| 6–8 | LinkedIn message (if connected) | Value first | ≤300 chars | One insight tied to their signal, one question |
| 8–10 | Email | Proof or practice | 20–40 | Signed-off proof only; without it, a general practice framed as such ("teams hiring for this often…") or a short resource — never an invented peer story |
| 14–21 | Email | Last touch | 20–30 | "If <pain> comes back, I'm easy to find" — no guilt, door open |
**No signal (segment-led)** — 3 email touches (days 1, 5, 12) plus the connection note; the first line is the segment's sharpest pain, not a fake personal hook.
**Warm (past champion, past user, someone who engaged)** — 3 touches, wider gaps (days 1, 7, 14), the last a gentle check-in, not a breakup. LinkedIn first when that's where the relationship lives. Very close contacts get one personal note, not a sequence.
**Retail buyers and shops (a consumer brand pitching stockists)** — 3 touches over about three weeks: email (why it sells on their shelf, one line on price tier, offer samples), a follow-up with a line sheet or lookbook link, a last short note; **no LinkedIn for independent shops**; chains go through the vendor portal or buying office first. Wholesale terms (margin, minimums) only from the brand's own sheet — if the brain doesn't have them, "wholesale terms needed" is a decision, never an invented margin. `UK-soletrader` shops get a letter (or a visit), not email.
**Win-back (churned business accounts)** — angles-by-signal.md § Win-back.
**Event-led** — touch 1 within a week of the event (before: "will you be at…"; after: the talk or topic), then the default shape.
## Lead source → sequence
| Where the row came from (research-audience) | Sequence | First-line source |
|---|---|---|
| New leader in the buying role | Signal-led, timed to their weeks in role | angles-by-signal § New leader |
| Hiring for the role we replace or support | Signal-led, worded by the post's age | § Hiring |
| A past champion who moved | Warm | § Champion moved |
| Switch intent ("alternative to X", "moving off X") | Signal-led, fast (within days of the post) | § Switch intent |
| Rival's public customer or testimonial | Segment-led, honest comparison | § Rival's customer |
| Speaker, sponsor or exhibitor at an event | Event-led | § Event |
| News (launch, expansion, acquisition, regulation) | Signal-led | § News |
| Funding (paired with another signal) | Signal-led | § Funding |
| Running ads now / developer activity | Signal-led | § Ads, § Developer activity |
| Fit, no signal | No signal | the segment's pain |
| Churned account | Win-back | § Win-back |
## Rules
- Every touch has a new reason to reply; never repeat an ask word for word.
- Later touches are shorter.
- One thread per channel; follow-up emails reply in the thread.
- A reply on any channel stops the whole sequence for that person; an out-of-office pauses it.
- Send Monday–Friday in the recipient's working hours, their time zone.
- **Cool-down:** after a sequence ends with no reply, wait **12 weeks** before contacting that person again on any channel (the ledger's timed exclusion). Anyone in an active sequence is never added to another.
- **Account spread:** at most 3 people per account, in different roles, started a few days apart — never the same day.
- **Volume:** count **emails, not people**: about 30–50 emails a day per warmed-up mailbox in total, follow-ups included — roughly 10–15 new people a day once a 4-email sequence is running. A new domain or mailbox needs 2–4 weeks of warm-up first (handoff-and-compliance.md).
## Calibration
Write the first touch for 3–5 rows across different signals and show them at the top of the pack as "the shape for every row", then write the rest. Corrections the marketer makes to those samples apply to every row (and, if they state a rule, become an `[outreach-copy …]` learning).
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 |