Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Helps write launch copy, position products, and create go-to-market materials using April Dunford's positioning framework and Airbnb's product marketing approach. Use when launching features, writing announcements, creating marketing materials, or positioning products.
.claude/skills/bilal140202-launch-execution/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-05 | ✗→✓ | ▲ Improved | -26% | 0% |
| case-07 | ✓→✓ | ＝ Same ✓ | -18% | 0% |
| case-06 | ✓→✓ | ＝ Same ✓ | -6% | 0% |
| case-01 | ✓→✓ | ＝ Same ✓ | -14% | 0% |
| case-02 | ✓→✓ | ＝ Same ✓ | 6% | 0% |
Claude uses this skill when:
Five Components:
markdown# [Feature Name]: [One-line value prop] ## The Problem [What pain does this solve?] ## The Solution [How does this feature work?] ## Why It Matters [Customer benefits, not features] ## Get Started [Clear next steps]
markdown# Positioning: [Product] ## Target Customer **Best for:** [specific segment] **Not for:** [who should avoid] ## Category **It's a:** [category name] **Think of it as:** [analogy] ## Alternatives **Customers currently use:** [list] **Why switch:** [reasons] ## Unique Value **What we do differently:** [differentiation] **Why that matters:** [customer benefit] ## Proof - [Metric/testimonial] - [Metric/testimonial] - [Metric/testimonial]
markdown# Launch: [Feature Name] **Pre-Launch:** - [ ] Positioning clear - [ ] Announcement drafted - [ ] Docs updated - [ ] Support team briefed **Launch Day:** - [ ] Announcement sent - [ ] Social posts - [ ] In-app message - [ ] Monitor feedback **Post-Launch:** - [ ] Track adoption - [ ] Collect feedback - [ ] Iterate messaging
Positioning:
Materials:
Distribution:
April Dunford: > "The best positioning makes it obvious who should buy, what they're buying, and why it matters."
Brian Chesky: > "Every feature needs a story. If you can't tell a story about it, you can't launch it."
| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-07 | pass→pass | 17,475 | 10,804 | -38% | 1 | 1 | 0% | 3,088 | 2,547 | -18% | 0 | 0 | — |
case-05 | fail→pass | 15,203 | 6,587 | -57% | 1 | 1 | 0% | 2,395 | 1,773 | -26% | 0 | 0 | — |
case-06 | pass→pass | 14,793 | 10,978 | -26% | 1 | 1 | 0% | 2,650 | 2,504 | -6% | 0 | 0 | — |
case-01 | pass→pass | 13,810 | 9,242 | -33% | 1 | 1 | 0% | 2,632 | 2,259 | -14% | 0 | 0 | — |
case-02 | pass→pass | 17,676 | 16,295 | -8% | 1 | 1 | 0% | 3,273 | 3,465 | +6% | 0 | 0 | — |
case-03 | pass→pass | 14,807 | 11,376 | -23% | 1 | 1 | 0% | 2,663 | 2,736 | +3% | 0 | 0 | — |
case-04 | pass→pass | 8,966 | 4,841 | -46% | 1 | 1 | 0% | 1,466 | 1,454 | -1% | 0 | 0 | — |
case-08 | pass→pass | 9,292 | 5,417 | -42% | 1 | 1 | 0% | 1,407 | 1,585 | +13% | 0 | 0 | — |
case-09 | pass→pass | 13,244 | 7,494 | -43% | 1 | 1 | 0% | 2,383 | 1,932 | -19% | 0 | 0 | — |
case-10 | pass→pass | 15,416 | 15,680 | +2% | 1 | 1 | 0% | 2,515 | 2,313 | -8% | 0 | 0 | — |
case-11 | pass→pass | 12,689 | 8,639 | -32% | 1 | 1 | 0% | 2,059 | 2,020 | -2% | 0 | 0 | — |
case-12 | pass→pass | 11,374 | 10,010 | -12% | 1 | 1 | 0% | 1,937 | 2,335 | +21% | 0 | 0 | — |
case-13 | pass→pass | 13,803 | 10,390 | -25% | 1 | 1 | 0% | 2,219 | 2,276 | +3% | 0 | 0 | — |
case-14 | pass→pass | 12,512 | 7,614 | -39% | 1 | 1 | 0% | 2,124 | 1,981 | -7% | 0 | 0 | — |
case-15 | pass→pass | 6,845 | 5,139 | -25% | 1 | 1 | 0% | 1,099 | 1,453 | +32% | 0 | 0 | — |
case-16 | pass→pass | 16,459 | 11,772 | -28% | 1 | 1 | 0% | 2,889 | 2,661 | -8% | 0 | 0 | — |
case-17 | pass→pass | 11,228 | 6,537 | -42% | 1 | 1 | 0% | 1,946 | 1,750 | -10% | 0 | 0 | — |
case-18 | pass→pass | 11,385 | 6,335 | -44% | 1 | 1 | 0% | 1,773 | 1,623 | -8% | 0 | 0 | — |
case-19 | pass→pass | 13,487 | 7,081 | -47% | 1 | 1 | 0% | 2,240 | 1,806 | -19% | 0 | 0 | — |
case-20 | pass→pass | 16,421 | 11,858 | -28% | 1 | 1 | 0% | 2,722 | 2,670 | -2% | 0 | 0 | — |
case-21 | pass→pass | 8,170 | 3,288 | -60% | 1 | 1 | 0% | 1,426 | 1,200 | -16% | 0 | 0 | — |
case-22 | pass→pass | 7,033 | 3,793 | -46% | 1 | 1 | 0% | 1,204 | 1,244 | +3% | 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 +5 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.