# Linkedin Outreach Batch

> Thin compatibility entrypoint for preparing approved LinkedIn outreach batches through the generalized linkedin-outreach lane workflow.

- Skill: `speciliam/linkedin-outreach-batch` (Agent Skill, multi-file: 4 files)
- Install (CLI): `npx skillmds@latest add speciliam/linkedin-outreach-batch`
- Raw SKILL.md: https://api.skillmd.com/api/skills/speciliam/linkedin-outreach-batch/raw
- Safety review: pending
- Works with: Claude Code, Claude.ai, OpenAI Codex
- Category: Productivity
- Author: SpeciLiam (https://skillmd.com/u/speciliam)
- Updated: 2026-09-21
- Page: https://skillmd.com/skills/speciliam/linkedin-outreach-batch

---


# LinkedIn Outreach Batch

This skill is deprecated as a standalone workflow. Use `linkedin-outreach` for the lane-agnostic process; this wrapper remains because existing visualizer commands, automations, and batch markdown files still reference the batch entrypoint.

For any lane, build the outreach queue with:

```bash
python3 skills/linkedin-outreach/scripts/build_outreach_targets.py --contact-type <lane> --limit <N>
```

For the legacy batch markdown manifests, the compatibility script still works:

```bash
python3 skills/linkedin-outreach-batch/scripts/build_recruiter_batch.py --contact-type recruiter
python3 skills/linkedin-outreach-batch/scripts/build_recruiter_batch.py --contact-type engineer
```

Before sending, re-read `skills/linkedin-outreach/OPERATING_CARD.md`. It is the source of truth for approval gates, send behavior, and outcome recording.

For large engineer or recruiter batches, use the monitored runner from the
generalized skill instead of keeping one long Codex context alive:

```bash
python3 skills/linkedin-outreach/scripts/run_monitored_batches.py --contact-type engineer --mode label
python3 skills/linkedin-outreach/scripts/run_monitored_batches.py --contact-type engineer --mode send
```

`label` finds and verifies missing contacts, then leaves them at `Needs
approval`. `send` only processes rows already marked `Approved`.