bereach-ai/linkedin-prospecting-skills / skills/linkedin-outreach-method
linkedin-outreach-method
VerifiedRuns the whole LinkedIn outreach loop: find, sort by persona, voice, one template per persona, send, measure acceptance and replies at 7 days. Start here for any LinkedIn outreach.
| File | Kind | Size |
|---|---|---|
| SKILL.md | skill md | 10.0 KB |
| references/advanced.md | markdown | 1.9 KB |
| references/artifacts.md | markdown | 19.9 KB |
| references/conversation-review.md | markdown | 4.7 KB |
| references/frameworks.md | markdown | 21.0 KB |
| references/icp.md | markdown | 20.0 KB |
| references/measuring.md | markdown | 10.2 KB |
| references/search-doors.md | markdown | 3.7 KB |
references/advanced.md
View on GitHub# Advanced options (optional)
Only after a text template per persona is validated and measured. Each one is a test: half of one persona,
the other half on the text baseline, sent the same days, read at 7 days (SKILL.md step 7). The user decides
whether to try any of them; none is needed to do well.
| Option | What it is | Evidence | Who does what |
|---|---|---|---|
| Voice note | A 20 to 40 second recording in place of follow-up 1 | One randomized vendor test, one segment: replies 30.7% to 33.7%, meetings 4.1% to 5.0%; did worse in a German-speaking audience. The bigger claims online (25 to 40% against 5 to 15%) trace to nothing solid | Claude writes the script; the user records and sends it from their phone |
| Cloned voice | A voice note made by software from a sample of the user's voice | None found. Vendor claims only | Only with the user's own voice and their choice; same test as a voice note |
| Image or short video | A picture or video made for the person (their site, their name) | None found on LinkedIn. In email data, images had no meaningful effect | The user makes and sends it |
## A voice note script (Claude writes it, the user says it)
1. Their name and the personal line (one fact and why it made you write).
2. One line of value: their problem in their words, or one proof.
3. One easy ask, the same kind as the first message.
About 60 to 90 words. Written to be said: short sentences, no list, no number they must remember. Best for a
warm, informal persona at a small company; never as the first touch.
## Counting a test the tools do not send
These go out from the user's own phone or app, so BeReach does not see them as messages. Before sending, tag
the two halves (`bereach_contact_update`, `tags: { add: ["arm:<persona>:voice"] }` and `arm:<persona>:text`).
At 7 days, count answers per tag as in SKILL.md step 6, read with the verdicts of `measuring.md`.
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| slack-gif-creatoranthropics/skillsKnowledge and utilities for creating animated GIFs optimized for Slack. Provides constraints, validation tools, and animation concepts. Use when users request animated GIFs for Slack like "make me a GIF of X doing Y for Slack." | Stars: 198k | Updated | Claude CodeCodex | Verified | Install |
| ponytailDietrichGebert/ponytailLazy senior dev mode for any coding task: the smallest change that fully solves it, and a reply a busy human understands in one read. | Stars: 196k | Updated | Claude CodeCodex | Verified | Install |
| ponytail-debtDietrichGebert/ponytailHarvest every shortcut: comment into one debt ledger, so deferrals get tracked instead of forgotten. One-shot report. | Stars: 196k | Updated | Claude CodeCodex | Verified | Install |
| ponytail-debtDietrichGebert/ponytailList every `shortcut:` comment (and older `ponytail:` ones) as a debt ledger. One-shot report, changes nothing. Use for "ponytail debt", "what did ponytail defer", "list the shortcuts", /ponytail-debt. | Stars: 196k | Updated | Claude CodeCodex | Verified | Install |