borghei/Claude-Skills / personal-productivity/lead-researcher
lead-researcher
VerifiedQualify and prioritize sales leads against an ICP, score lead lists, and draft personalized outreach hooks. Use when building a target account list, qualifying inbound leads, prepping for outreach, or scoring prospects.
| File | Kind | Size |
|---|---|---|
| SKILL.md | skill md | 7.4 KB |
| assets/icp_schema.json | config | 2.7 KB |
| assets/outreach_template.md | markdown | 2.3 KB |
| references/icp_framework.md | markdown | 4.6 KB |
| scripts/lead_qualifier.py | script | 5.3 KB |
assets/outreach_template.md
View on GitHub# Cold Outreach Template — Signal-Led First Touch
Use one signal. Keep it under 90 words. End on a single, specific question.
---
## Email Skeleton
**Subject:** `{specific noun, not a pitch}` — short, lowercase, no clickbait
> Examples:
> - "checkout abandonment ideas"
> - "your Snowflake setup"
> - "thoughts on your hiring spike"
**Body:**
```
Hi {first name},
{One sentence referencing the actual signal — e.g., funding round, hiring,
public quote, integration adoption, product launch. Be specific enough that
it could not have been sent to anyone else.}
{One sentence connecting that signal to the pain you solve. Use language they
would use, not your product's language.}
{One question — concrete, low-cost to answer, not "do you want to chat?"}
— {Your name}
{One line of credentials, e.g., "previously @ Stripe / led billing infra"}
```
---
## Worked Example
> Subject: your Snowflake migration
>
> Hi Priya,
>
> Saw your post about migrating the analytics stack to Snowflake last month — congrats on shipping that. We've helped four data teams in similar moves cut warehouse spend 30-40% by tuning warehouse sizing and query routing in the first 90 days post-migration.
>
> Curious — what's been the biggest unexpected cost line item since you cut over?
>
> — Mo
> previously @ Mode Analytics, now building cost-tuning tooling for Snowflake teams
---
## Anti-Patterns
| Don't | Why |
|-------|-----|
| "Hope you're doing well!" | Filler. Skip pleasantries. |
| "I came across your profile" | Too generic. Replace with the actual signal. |
| Multi-paragraph value-prop dump | Reads as a deck. The first email should ask one thing. |
| "Do you have 15 min to chat?" | Too high-cost an ask. Replace with a question they can answer in one line. |
| Three CTAs | Pick one. Three is none. |
| Image attachments / logos | Increases spam rate, doesn't help reply rate. |
---
## Sequence Cadence (lightweight)
| Day | Touch | Channel |
|-----|-------|---------|
| 0 | Signal-led first email (this template) | Email |
| 3 | Brief follow-up — one new angle, no "just checking in" | Email |
| 7 | LinkedIn connection request — reference the email subject | LinkedIn |
| 14 | Final email — short, gives them an out ("happy to deprioritize for now") | Email |
If no reply by day 21, drop and recycle in 90 days only if signals refresh.
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 |