Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →When the user wants to create a press coverage page, "As Seen In" section, or media mentions aggregation. Also use when the user mentions "press coverage," "media mentions," "as seen in," "as featured in," "in the news," "press mentions," "media coverage page," or "trusted by publications." For pitching journalists and press releases, use public-relations.
.claude/skills/kostja94-press-coverage-page-generator/SKILL.md| Model | Eval pass | Runs |
|---|---|---|
| gemini-3.6-flash | 100% | 12 |
| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-15 | ✗→✓ | ▲ Improved | 51% | 0% |
| case-08 | ✗→✓ | ▲ Improved | 17% | 0% |
| case-11 | ✗→✓ | ▲ Improved | 14% | 0% |
| case-12 | ✗→✓ | ▲ Improved | 9% | 0% |
| case-22 | ✗→✓ | ▲ Improved | 6% | 0% |
Guides press coverage and media mentions aggregation—showcasing third-party coverage from authoritative sites to build trust. Optional page; when coverage is sparse, implement as a small "As Seen In" or "As Featured In" section on homepage or elsewhere. Distinct from media-kit-page-generator (assets for journalists). For conceptual overview and comparison table, see reference.md.
When invoking: On first use, if helpful, open with 1–2 sentences on what this skill covers and why it matters, then provide the main output. On subsequent use or when the user asks to skip, go directly to the main output.
Check for project context first: If .claude/project-context.md or .cursor/project-context.md exists, read for company story and key messages.
Identify:
| Format | When to Use | Placement | |--------|-------------|-----------| | Full page | Substantial coverage (10+ mentions); journalists visit for expert contacts; "inbound PR" | /press, /news, /in-the-news | | Section | Sparse coverage (1–10); quick credibility; logo strip or quote carousel | Homepage below hero; About page; footer |
Rule: Homepage section = logos only, minimal, below main CTA. Full page = headlines, links, dates, contact.
| Element | Guideline | |---------|-----------| | Coverage list | Chronological or by publication; headline, outlet, date, link | | Separation | Press coverage (third-party) vs press releases (company-authored); coverage carries more credibility | | Types | News, podcasts, video features, awards, "Best X" lists | | Contact | Media inquiries; link to media kit | | Dates | Optional on evergreen content; omit to keep timeless |
| Element | Guideline | |---------|-----------| | Logos | Publication logos; high-contrast, consistent size | | Placement | Below hero/CTA; above fold or just below | | Quote | Optional: one compelling snippet; extract from best coverage | | Link | Optional: "See all coverage" → full page if exists |
Avoid: Clutter; too many logos; low-authority outlets that dilute trust.
| Type | Example | |------|---------| | News articles | Forbes, Bloomberg, TechCrunch, industry trade | | Podcasts | Interview features, guest appearances | | Video | TV segments, YouTube features | | Awards | "Best X 2024," "Top 10 Startups" | | Reviews | Product reviews, roundups |
| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-15 | fail→pass | 10,116 | 11,214 | +11% | 1 | 1 | 0% | 1,716 | 2,593 | +51% | 0 | 0 | — |
case-13 | pass→pass | 11,683 | 11,060 | -5% | 1 | 1 | 0% | 1,898 | 2,646 | +39% | 0 | 0 | — |
case-01 | fail→fail | 16,314 | 10,166 | -38% | 1 | 1 | 0% | 2,861 | 2,708 | -5% | 0 | 0 | — |
case-02 | fail→fail | 16,608 | 7,825 | -53% | 1 | 1 | 0% | 2,657 | 2,216 | -17% | 0 | 0 | — |
case-03 | pass→pass | 12,425 | 11,032 | -11% | 1 | 1 | 0% | 2,012 | 2,808 | +40% | 0 | 0 | — |
case-04 | pass→pass | 14,457 | 11,404 | -21% | 1 | 1 | 0% | 2,882 | 2,966 | +3% | 0 | 0 | — |
case-05 | pass→pass | 16,305 | 13,140 | -19% | 1 | 1 | 0% | 2,947 | 3,089 | +5% | 0 | 0 | — |
case-06 | pass→pass | 15,899 | 11,315 | -29% | 1 | 1 | 0% | 2,751 | 2,611 | -5% | 0 | 0 | — |
case-07 | pass→pass | 13,742 | 10,948 | -20% | 1 | 1 | 0% | 2,233 | 2,724 | +22% | 0 | 0 | — |
case-08 | fail→pass | 13,307 | 9,543 | -28% | 1 | 1 | 0% | 2,113 | 2,472 | +17% | 0 | 0 | — |
case-14 | pass→pass | 10,332 | 8,859 | -14% | 1 | 1 | 0% | 1,748 | 2,431 | +39% | 0 | 0 | — |
case-09 | pass→pass | 14,384 | 11,319 | -21% | 1 | 1 | 0% | 2,418 | 2,985 | +23% | 0 | 0 | — |
case-10 | pass→pass | 14,071 | 10,498 | -25% | 1 | 1 | 0% | 2,378 | 2,725 | +15% | 0 | 0 | — |
case-11 | fail→pass | 11,643 | 8,698 | -25% | 1 | 1 | 0% | 1,968 | 2,239 | +14% | 0 | 0 | — |
case-12 | fail→pass | 14,005 | 11,520 | -18% | 1 | 1 | 0% | 2,668 | 2,896 | +9% | 0 | 0 | — |
case-16 | pass→pass | 11,195 | 7,274 | -35% | 1 | 1 | 0% | 1,573 | 1,954 | +24% | 0 | 0 | — |
case-17 | pass→pass | 10,580 | 7,661 | -28% | 1 | 1 | 0% | 1,545 | 2,069 | +34% | 0 | 0 | — |
case-18 | pass→pass | 16,610 | 8,146 | -51% | 1 | 1 | 0% | 2,336 | 2,155 | -8% | 0 | 0 | — |
case-19 | pass→pass | 10,487 | 9,794 | -7% | 1 | 1 | 0% | 1,778 | 2,379 | +34% | 0 | 0 | — |
case-20 | pass→pass | 7,875 | 12,409 | +58% | 1 | 1 | 0% | 1,408 | 2,867 | +104% | 0 | 0 | — |
case-21 | pass→pass | 13,328 | 10,096 | -24% | 1 | 1 | 0% | 1,941 | 2,334 | +20% | 0 | 0 | — |
case-22 | fail→pass | 14,867 | 10,637 | -28% | 1 | 1 | 0% | 2,535 | 2,687 | +6% | 0 | 0 | — |
case-23 | pass→pass | 12,001 | 8,866 | -26% | 1 | 1 | 0% | 2,019 | 2,163 | +7% | 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. 23 cases were attempted. The headline lift of +22 percentage points is the difference between those two pass rates over the 23 comparable cases.
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.