Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Optimise a LinkedIn profile to be found and to convert. Use when asked to write or improve a LinkedIn headline, About section, or profile, or to make a profile recruiter-friendly. Produces an optimised headline, a first-person About section with a hook and keywords, achievement-led experience bullets, and a skills/keyword list tuned for LinkedIn search.
.claude/skills/mohitagw15856-linkedin-profile/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-05 | ✗→✓ | ▲ Improved | 63% | 0% |
| case-06 | ✗→✓ | ▲ Improved | 24% | 0% |
| case-09 | ✓→✗ | ▼ Worse | 61% | 0% |
| case-20 | ✓→✗ | ▼ Worse | -26% | 0% |
| case-01 | ✓→✓ | ＝ Same ✓ | 145% | 0% |
LinkedIn is two audiences at once: a search algorithm (recruiters filter by keywords) and a human who decides in the first two lines whether to keep reading. This skill optimises for both — a keyword-rich headline, an About section that hooks then proves, and achievement-led experience — so the profile gets surfaced and converts the click.
Ask for these only if they aren't already provided:
Headline (≤220 chars) — not just your job title: role + value + keywords. e.g. "Senior PM · B2B SaaS & PLG · I turn messy roadmaps into shipped outcomes." Keyword-rich for search.
About (first person, 3–5 short paragraphs):
Experience bullets — for the top roles, achievement-led bullets (same standard as a resume: action → impact → metric), lightly more narrative than a CV.
Skills list — the 10–15 keyword skills to add (LinkedIn ranks search partly on these), ordered by relevance to the target role.
LinkedIn profile-optimisation practice — keyword-aware headline/About, hook-before-fold, recruiter search ranking.
| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-01 | pass→pass | 3,695 | 5,233 | +42% | 1 | 1 | 0% | 625 | 1,532 | +145% | 0 | 0 | — |
case-02 | fail→fail | 8,093 | 9,332 | +15% | 1 | 1 | 0% | 1,395 | 2,224 | +59% | 0 | 0 | — |
case-03 | pass→pass | 10,286 | 8,003 | -22% | 1 | 1 | 0% | 1,752 | 1,898 | +8% | 0 | 0 | — |
case-04 | pass→pass | 13,273 | 6,629 | -50% | 1 | 1 | 0% | 2,026 | 1,543 | -24% | 0 | 0 | — |
case-05 | fail→pass | 6,356 | 7,136 | +12% | 1 | 1 | 0% | 1,116 | 1,823 | +63% | 0 | 0 | — |
case-06 | fail→pass | 6,326 | 4,547 | -28% | 1 | 1 | 0% | 1,158 | 1,433 | +24% | 0 | 0 | — |
case-07 | pass→pass | 7,620 | 6,455 | -15% | 1 | 1 | 0% | 1,404 | 1,762 | +25% | 0 | 0 | — |
case-08 | pass→pass | 7,906 | 3,260 | -59% | 1 | 1 | 0% | 1,228 | 1,100 | -10% | 0 | 0 | — |
case-09 | pass→fail | 9,867 | 11,259 | +14% | 1 | 1 | 0% | 1,524 | 2,454 | +61% | 0 | 0 | — |
case-10 | pass→pass | 9,516 | 10,939 | +15% | 1 | 1 | 0% | 1,461 | 2,428 | +66% | 0 | 0 | — |
case-11 | pass→pass | 7,901 | 6,661 | -16% | 1 | 1 | 0% | 1,215 | 1,715 | +41% | 0 | 0 | — |
case-12 | fail→fail | 9,371 | 9,261 | -1% | 1 | 1 | 0% | 1,579 | 2,146 | +36% | 0 | 0 | — |
case-13 | pass→pass | 8,934 | 6,198 | -31% | 1 | 1 | 0% | 1,422 | 1,659 | +17% | 0 | 0 | — |
case-14 | pass→pass | 11,735 | 12,564 | +7% | 1 | 1 | 0% | 1,721 | 2,678 | +56% | 0 | 0 | — |
case-15 | pass→pass | 10,696 | 8,728 | -18% | 1 | 1 | 0% | 1,878 | 2,147 | +14% | 0 | 0 | — |
case-16 | pass→pass | 10,662 | 9,687 | -9% | 1 | 1 | 0% | 1,873 | 2,348 | +25% | 0 | 0 | — |
case-17 | fail→fail | 7,582 | 8,280 | +9% | 1 | 1 | 0% | 1,332 | 1,912 | +44% | 0 | 0 | — |
case-18 | pass→pass | 6,494 | 6,118 | -6% | 1 | 1 | 0% | 1,103 | 1,639 | +49% | 0 | 0 | — |
case-19 | pass→pass | 9,549 | 5,629 | -41% | 1 | 1 | 0% | 1,705 | 1,606 | -6% | 0 | 0 | — |
case-20 | pass→fail | 13,122 | 6,693 | -49% | 1 | 1 | 0% | 2,283 | 1,694 | -26% | 0 | 0 | — |
case-21 | pass→pass | 8,090 | 8,750 | +8% | 1 | 1 | 0% | 1,352 | 2,075 | +53% | 0 | 0 | — |
case-22 | pass→pass | 14,217 | 6,267 | -56% | 1 | 1 | 0% | 2,473 | 1,776 | -28% | 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. 22 cases were attempted. The headline lift of 0 percentage points is the difference between those two pass rates over the 22 comparable cases. 2 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.