Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Plan and execute off-page SEO including link building, digital PR, brand mentions, citation building, and external authority signals. Use this skill whenever the user wants to build backlinks, plan a digital PR campaign, list local citations, run guest post outreach, develop linkable assets, recover lost links, or audit a backlink profile for risk. Triggers on link building, backlinks, digital PR, brand mentions, citation building, guest post, outreach, linkable asset, broken link building, HARO
.claude/skills/rampstackco-seo-offpage/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-01 | ✗→✓ | ▲ Improved | 41% | 0% |
| case-02 | ✗→✓ | ▲ Improved | 7% | 0% |
| case-03 | ✗→✓ | ▲ Improved | -2% | 0% |
| case-05 | ✗→✓ | ▲ Improved | 49% | 0% |
| case-07 | ✗→✓ | ▲ Improved | 59% | 0% |
Build the external signals that earn rankings: backlinks, brand mentions, citations, and trusted sources pointing back to the site. Stack-agnostic.
seo-onpage or seo-technical)seo-keyword)seo-competitor, then return here for outreach planning)Off-page work splits into four strategy types. Most programs blend them. Pick the mix that fits your phase.
Links and mentions you earn through coverage, journalism, or contribution.
Strength: Highest authority, hardest to replicate. Cost: Time-intensive, often requires PR or content budget. Volume: Low to medium per quarter.
Linkable assets on your own site that attract links passively over time.
Strength: Compounds over time. Each link points at an evergreen asset. Cost: Upfront content investment. Volume: Slow to start, accelerates as the asset earns mentions.
Links earned through real business relationships.
Strength: Trustworthy, contextually relevant. Cost: Time to develop relationships. Volume: Medium and consistent.
Local and category-specific listings that establish entity legitimacy.
Strength: Foundational for local and entity SEO. Cost: Low to medium, mostly setup time. Volume: One-time foundation, occasional refresh.
Default output is a markdown plan at offpage-strategy.md plus tracking spreadsheets for prospects and outreach.
Structure:
This skill's output depends on data, measurements, or tool results it cannot generate on its own. When a required input, tool, or data source is unavailable or unverifiable, the sanctioned output is the deliverable with the gap stated: what was needed, what was actually obtained or verified, and which parts of the output are affected. Fabricating, estimating, or interpolating a required number to complete the deliverable is never sanctioned. A stated gap is a complete answer.
references/outreach-templates.md - Templates for guest posting, expert quotes, broken-link outreach, podcast pitches.references/linkable-assets-guide.md - Categories of linkable assets with examples and effort estimates.| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-01 | fail→pass | 28,928 | 31,447 | +9% | 1 | 1 | 0% | 4,793 | 6,779 | +41% | 0 | 0 | — |
case-02 | fail→pass | 35,443 | 27,367 | -23% | 1 | 1 | 0% | 5,789 | 6,208 | +7% | 0 | 0 | — |
case-03 | fail→pass | 35,129 | 24,090 | -31% | 1 | 1 | 0% | 5,655 | 5,518 | -2% | 0 | 0 | — |
case-04 | fail→fail | 16,799 | 18,775 | +12% | 1 | 1 | 0% | 3,009 | 4,883 | +62% | 0 | 0 | — |
case-05 | fail→pass | 19,415 | 21,999 | +13% | 1 | 1 | 0% | 3,594 | 5,371 | +49% | 0 | 0 | — |
case-06 | fail→fail | 20,757 | 10,901 | -47% | 1 | 1 | 0% | 4,021 | 3,576 | -11% | 0 | 0 | — |
case-07 | fail→pass | 17,163 | 17,062 | -1% | 1 | 1 | 0% | 2,743 | 4,362 | +59% | 0 | 0 | — |
case-08 | pass→pass | 12,875 | 8,783 | -32% | 1 | 1 | 0% | 2,190 | 3,067 | +40% | 0 | 0 | — |
case-09 | pass→pass | 10,526 | 6,286 | -40% | 1 | 1 | 0% | 1,727 | 2,563 | +48% | 0 | 0 | — |
case-10 | pass→pass | 25,068 | 11,456 | -54% | 1 | 1 | 0% | 1,418 | 3,345 | +136% | 0 | 0 | — |
case-11 | fail→pass | 5,545 | 9,008 | +62% | 1 | 1 | 0% | 847 | 3,074 | +263% | 0 | 0 | — |
case-12 | pass→pass | 14,187 | 10,670 | -25% | 1 | 1 | 0% | 2,245 | 3,303 | +47% | 0 | 0 | — |
case-13 | fail→fail | 13,099 | 10,927 | -17% | 1 | 1 | 0% | 2,109 | 3,443 | +63% | 0 | 0 | — |
case-14 | pass→pass | 15,194 | 18,647 | +23% | 1 | 1 | 0% | 2,363 | 4,557 | +93% | 0 | 0 | — |
case-15 | pass→pass | 15,480 | 12,734 | -18% | 1 | 1 | 0% | 2,527 | 3,598 | +42% | 0 | 0 | — |
case-16 | pass→pass | 12,176 | 8,442 | -31% | 1 | 1 | 0% | 1,843 | 2,854 | +55% | 0 | 0 | — |
case-17 | pass→pass | 17,923 | 17,759 | -1% | 1 | 1 | 0% | 2,451 | 4,294 | +75% | 0 | 0 | — |
case-18 | fail→pass | 24,637 | 22,870 | -7% | 1 | 1 | 0% | 3,763 | 5,152 | +37% | 0 | 0 | — |
case-19 | pass→pass | 17,722 | 11,381 | -36% | 1 | 1 | 0% | 2,465 | 3,127 | +27% | 0 | 0 | — |
case-20 | pass→pass | 10,646 | 7,987 | -25% | 1 | 1 | 0% | 1,683 | 2,737 | +63% | 0 | 0 | — |
case-21 | fail→pass | 18,728 | 15,648 | -16% | 1 | 1 | 0% | 2,693 | 3,928 | +46% | 0 | 0 | — |
case-22 | pass→pass | 15,167 | 18,168 | +20% | 1 | 1 | 0% | 2,340 | 4,265 | +82% | 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 +36 percentage points is the difference between those two pass rates over the 22 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.