Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →When the user wants to create Pinterest Pins, optimize Pin descriptions, or grow Pinterest presence. Also use when the user mentions "Pinterest," "Pin," "Pinterest SEO," "Pinterest description," "Pinterest board," or "Pinterest marketing." For asset specs, use visual-content.
.claude/skills/kostja94-pinterest-posts/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-02 | ✗→✓ | ▲ Improved | 74% | 0% |
| case-13 | ✗→✓ | ▲ Improved | 48% | 0% |
| case-14 | ✗→✓ | ▲ Improved | 43% | 0% |
| case-04 | ✓→✓ | ＝ Same ✓ | 12% | 0% |
| case-06 | ✓→✓ | ＝ Same ✓ | 19% | 0% |
Guides Pinterest Pin creation and optimization. Pinterest users search differently than Google; long-tail keywords like "easy fall dinner recipes" perform better than broad terms. Use this skill when creating Pins, optimizing boards, or planning Pinterest content.
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 Sections 6 (Keywords), 11 (Content Strategy).
Identify:
| Rule | Guideline | |------|-----------| | Length | Up to 100 chars; first 40 visible in feeds | | Keyword | Primary keyword in first 40 chars | | Business name | In first sentence → 54% higher email signup conversion |
| Rule | Guideline | |------|-----------| | Length | 220–232 chars optimal | | Keywords | Main + 2–3 related; natural placement | | CTA | Clear, actionable → 70% signup boost, 6% sales lift | | Price | When relevant → 28% sales increase |
| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-01 | fail→fail | 6,986 | 6,064 | -13% | 1 | 1 | 0% | 1,303 | 1,829 | +40% | 0 | 0 | — |
case-02 | fail→pass | 10,128 | 11,287 | +11% | 1 | 1 | 0% | 1,759 | 3,053 | +74% | 0 | 0 | — |
case-03 | fail→fail | 7,874 | 6,529 | -17% | 1 | 1 | 0% | 1,407 | 1,849 | +31% | 0 | 0 | — |
case-04 | pass→pass | 9,599 | 7,672 | -20% | 1 | 1 | 0% | 1,760 | 1,977 | +12% | 0 | 0 | — |
case-05 | fail→fail | 3,933 | 7,523 | +91% | 1 | 1 | 0% | 778 | 1,922 | +147% | 0 | 0 | — |
case-06 | pass→pass | 8,903 | 6,026 | -32% | 1 | 1 | 0% | 1,461 | 1,738 | +19% | 0 | 0 | — |
case-07 | fail→fail | 9,456 | 9,912 | +5% | 1 | 1 | 0% | 1,566 | 2,583 | +65% | 0 | 0 | — |
case-08 | pass→pass | 6,724 | 5,880 | -13% | 1 | 1 | 0% | 1,219 | 1,749 | +43% | 0 | 0 | — |
case-09 | pass→pass | 8,657 | 6,519 | -25% | 1 | 1 | 0% | 1,401 | 1,779 | +27% | 0 | 0 | — |
case-10 | fail→fail | 9,401 | 10,683 | +14% | 1 | 1 | 0% | 1,678 | 2,301 | +37% | 0 | 0 | — |
case-11 | pass→pass | 11,790 | 8,999 | -24% | 1 | 1 | 0% | 1,933 | 2,173 | +12% | 0 | 0 | — |
case-12 | pass→pass | 7,091 | 10,440 | +47% | 1 | 1 | 0% | 1,508 | 2,873 | +91% | 0 | 0 | — |
case-13 | fail→pass | 6,403 | 5,473 | -15% | 1 | 1 | 0% | 1,052 | 1,562 | +48% | 0 | 0 | — |
case-14 | fail→pass | 6,395 | 5,580 | -13% | 1 | 1 | 0% | 1,104 | 1,575 | +43% | 0 | 0 | — |
case-15 | pass→pass | 10,022 | 5,873 | -41% | 1 | 1 | 0% | 1,654 | 1,662 | +0% | 0 | 0 | — |
case-16 | fail→fail | 8,549 | 9,519 | +11% | 1 | 1 | 0% | 1,460 | 2,628 | +80% | 0 | 0 | — |
case-17 | pass→pass | 4,702 | 7,104 | +51% | 1 | 1 | 0% | 721 | 1,837 | +155% | 0 | 0 | — |
case-18 | fail→fail | 5,430 | 6,683 | +23% | 1 | 1 | 0% | 1,243 | 1,791 | +44% | 0 | 0 | — |
case-19 | pass→pass | 11,156 | 5,216 | -53% | 1 | 1 | 0% | 1,708 | 1,367 | -20% | 0 | 0 | — |
case-20 | pass→pass | 11,989 | 9,810 | -18% | 1 | 1 | 0% | 1,919 | 2,261 | +18% | 0 | 0 | — |
case-21 | pass→pass | 10,372 | 9,844 | -5% | 1 | 1 | 0% | 1,903 | 2,266 | +19% | 0 | 0 | — |
case-22 | pass→pass | 7,338 | 8,091 | +10% | 1 | 1 | 0% | 1,302 | 2,115 | +62% | 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 +14 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.