Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Build targeted prospect lists by analyzing LinkedIn profiles, extracting job titles, companies, locations, and recent activity. Identifies decision-makers, tracks job changes for warm outreach, and enriches contact data. Use when users need to find prospects, build lead lists, or track decision-maker movements.
.claude/skills/onewave-ai-linkedin-sales-navigator-alt/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-01 | ✗→✓ | ▲ Improved | 22% | 0% |
| case-03 | ✗→✓ | ▲ Improved | 26% | 0% |
| case-14 | ✗→✓ | ▲ Improved | 15% | 0% |
| case-08 | ✓→✗ | ▼ Worse | 28% | 0% |
| case-18 | ✓→✗ | ▼ Worse | 40% | 0% |
Find and qualify prospects on LinkedIn without expensive subscriptions, using only publicly available information.
references/output-template.md — full prospect-list Markdown structure and section layoutreferences/campaigns.md — segmented campaign playbooks (new-in-role, account-based, event follow-up)references/tools-and-export.md — contact-finding methods, tool stack, CSV/CRM export formatsreferences/examples.md — trigger phrases, example request, best practicesWork only with publicly available information and respect LinkedIn's Terms of Service. Encourage official LinkedIn tools where appropriate. Aggregate public data for legitimate business development only.
references/tools-and-export.md for discovery and verification methods.references/output-template.md, attach relevant campaign playbooks from references/campaigns.md, and provide export-ready data per references/tools-and-export.md.Deliver a targeted, researched set of qualified prospects with personalization context — not just a list of names. See references/examples.md for trigger phrases and best practices.
| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-11 | pass→pass | 12,769 | 10,665 | -16% | 1 | 1 | 0% | 1,970 | 2,306 | +17% | 0 | 0 | — |
case-01 | fail→pass | 29,481 | 26,247 | -11% | 1 | 1 | 0% | 3,774 | 4,588 | +22% | 0 | 0 | — |
case-02 | fail→fail | 13,312 | 15,637 | +17% | 1 | 1 | 0% | 2,002 | 2,701 | +35% | 0 | 0 | — |
case-03 | fail→pass | 17,114 | 18,260 | +7% | 1 | 1 | 0% | 2,487 | 3,135 | +26% | 0 | 0 | — |
case-10 | pass→pass | 9,030 | 9,800 | +9% | 1 | 1 | 0% | 1,536 | 2,147 | +40% | 0 | 0 | — |
case-04 | fail→fail | 2,582 | 3,072 | +19% | 1 | 1 | 0% | 343 | 924 | +169% | 0 | 0 | — |
case-05 | fail→fail | 10,448 | 10,301 | -1% | 1 | 1 | 0% | 1,506 | 2,051 | +36% | 0 | 0 | — |
case-06 | pass→pass | 4,026 | 12,409 | +208% | 1 | 1 | 0% | 578 | 1,442 | +149% | 0 | 0 | — |
case-07 | fail→fail | 18,930 | 16,965 | -10% | 1 | 1 | 0% | 2,899 | 3,218 | +11% | 0 | 0 | — |
case-08 | pass→fail | 12,563 | 12,848 | +2% | 1 | 1 | 0% | 2,078 | 2,662 | +28% | 0 | 0 | — |
case-09 | pass→pass | 10,110 | 10,576 | +5% | 1 | 1 | 0% | 1,890 | 2,387 | +26% | 0 | 0 | — |
case-12 | pass→pass | 20,268 | 15,832 | -22% | 1 | 1 | 0% | 3,154 | 3,032 | -4% | 0 | 0 | — |
case-13 | pass→pass | 14,696 | 15,757 | +7% | 1 | 1 | 0% | 2,271 | 2,724 | +20% | 0 | 0 | — |
case-14 | fail→pass | 10,721 | 9,369 | -13% | 1 | 1 | 0% | 1,771 | 2,043 | +15% | 0 | 0 | — |
case-15 | pass→pass | 12,006 | 12,087 | +1% | 1 | 1 | 0% | 1,870 | 2,490 | +33% | 0 | 0 | — |
case-16 | pass→pass | 11,018 | 11,400 | +3% | 1 | 1 | 0% | 1,790 | 2,226 | +24% | 0 | 0 | — |
case-17 | fail→fail | 6,577 | 8,702 | +32% | 1 | 1 | 0% | 1,047 | 1,800 | +72% | 0 | 0 | — |
case-18 | pass→fail | 9,617 | 10,722 | +11% | 1 | 1 | 0% | 1,647 | 2,303 | +40% | 0 | 0 | — |
case-19 | pass→pass | 8,695 | 9,859 | +13% | 1 | 1 | 0% | 1,573 | 2,319 | +47% | 0 | 0 | — |
case-20 | pass→fail | 11,391 | 8,909 | -22% | 1 | 1 | 0% | 2,047 | 1,860 | -9% | 0 | 0 | — |
case-21 | pass→pass | 12,606 | 13,642 | +8% | 1 | 1 | 0% | 1,782 | 2,772 | +56% | 0 | 0 | — |
case-22 | pass→pass | 13,418 | 18,156 | +35% | 1 | 1 | 0% | 2,129 | 2,826 | +33% | 0 | 0 | — |
case-23 | pass→pass | 10,480 | 9,457 | -10% | 1 | 1 | 0% | 1,709 | 1,984 | +16% | 0 | 0 | — |
case-24 | fail→fail | 15,377 | 17,132 | +11% | 1 | 1 | 0% | 2,383 | 3,181 | +33% | 0 | 0 | — |
case-25 | fail→fail | 19,204 | 19,867 | +3% | 1 | 1 | 0% | 3,112 | 3,634 | +17% | 0 | 0 | — |
case-26 | pass→pass | 9,294 | 14,574 | +57% | 1 | 1 | 0% | 1,419 | 1,995 | +41% | 0 | 0 | — |
DecimalAI ran this skill against gemini-3.6-flash twice over the same eval suite — once with the skill loaded and once without — and compared the two runs case by case. 26 cases were attempted. The headline lift of 0 percentage points is the difference between those two pass rates over the 26 comparable cases. 3 cases got worse with the skill loaded, and they are included in that figure.
Without the skill loaded, the model failed this case. With it loaded, the same prompt on the same model passed. This is one improved case from the latest verified run; every case, including any that regressed, is in the table above.
Other measured skills in the registry, with their headline benchmark lift.