Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Write a developer-audience launch post — Show HN, a Product Hunt blurb, a 'we shipped X' dev blog intro, or a launch tweet thread. Use when launching a tool, library, API, or open-source project to a technical audience. Produces a credible, hype-free post that leads with what it does and why it's different, plus title options and a comment-ready first reply.
.claude/skills/mohitagw15856-launch-post/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-01 | ✗→✓ | ▲ Improved | 30% | 0% |
| case-03 | ✗→✓ | ▲ Improved | 79% | 0% |
| case-05 | ✗→✓ | ▲ Improved | 77% | 0% |
| case-06 | ✗→✓ | ▲ Improved | -9% | 0% |
| case-08 | ✗→✓ | ▲ Improved | -3% | 0% |
Developers smell marketing from a mile away. A launch post that lands with them is concrete, honest about trade-offs, and leads with what it does and why you built it — not adjectives. This skill writes that post (Show HN, Product Hunt, dev blog, or a tweet thread), tuned to the channel, with title options and a strong first comment to seed the discussion.
Ask for these only if they aren't already provided:
Title options (3) — concrete and specific; for Show HN follow the Show HN: [Name] – [what it does] form. No hype words.
The post
First comment (seed) — a ready-to-post reply adding technical context or answering the obvious first question, to kick off discussion.
Channel notes — tweaks for the chosen channel (HN: no marketing tone, be in the thread to reply; PH: tagline + first comment; X: thread hook + cadence).
Developer-launch craft (Show HN / Product Hunt norms): substance over hype, honest trade-offs, seed the discussion.
| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-01 | fail→pass | 12,698 | 13,367 | +5% | 1 | 1 | 0% | 2,232 | 2,910 | +30% | 0 | 0 | — |
case-02 | fail→fail | 8,409 | 13,007 | +55% | 1 | 1 | 0% | 1,442 | 2,882 | +100% | 0 | 0 | — |
case-03 | fail→pass | 8,917 | 11,473 | +29% | 1 | 1 | 0% | 1,366 | 2,441 | +79% | 0 | 0 | — |
case-04 | fail→fail | 9,166 | 11,097 | +21% | 1 | 1 | 0% | 1,425 | 2,546 | +79% | 0 | 0 | — |
case-05 | fail→pass | 8,277 | 11,073 | +34% | 1 | 1 | 0% | 1,464 | 2,585 | +77% | 0 | 0 | — |
case-06 | fail→pass | 17,763 | 13,362 | -25% | 1 | 1 | 0% | 3,064 | 2,798 | -9% | 0 | 0 | — |
case-07 | fail→fail | 25,186 | 13,371 | -47% | 1 | 1 | 0% | 6,179 | 3,230 | -48% | 0 | 0 | — |
case-08 | fail→pass | 14,003 | 11,315 | -19% | 1 | 1 | 0% | 2,654 | 2,580 | -3% | 0 | 0 | — |
case-09 | fail→fail | 9,139 | 14,470 | +58% | 1 | 1 | 0% | 1,621 | 3,004 | +85% | 0 | 0 | — |
case-10 | pass→pass | 8,851 | 6,141 | -31% | 1 | 1 | 0% | 1,571 | 1,744 | +11% | 0 | 0 | — |
case-11 | fail→fail | 7,552 | 9,389 | +24% | 1 | 1 | 0% | 1,303 | 2,202 | +69% | 0 | 0 | — |
case-12 | fail→fail | 13,989 | 10,761 | -23% | 1 | 1 | 0% | 2,296 | 2,464 | +7% | 0 | 0 | — |
case-13 | pass→fail | 12,231 | 7,254 | -41% | 1 | 1 | 0% | 1,934 | 1,866 | -4% | 0 | 0 | — |
case-14 | pass→fail | 11,809 | 13,473 | +14% | 1 | 1 | 0% | 1,933 | 3,022 | +56% | 0 | 0 | — |
case-15 | pass→fail | 12,879 | 14,016 | +9% | 1 | 1 | 0% | 2,218 | 3,106 | +40% | 0 | 0 | — |
case-16 | fail→pass | 7,134 | 13,375 | +87% | 1 | 1 | 0% | 1,075 | 2,879 | +168% | 0 | 0 | — |
case-17 | fail→fail | 6,115 | 10,218 | +67% | 1 | 1 | 0% | 1,073 | 2,616 | +144% | 0 | 0 | — |
case-18 | fail→fail | 14,305 | 15,244 | +7% | 1 | 1 | 0% | 2,434 | 3,213 | +32% | 0 | 0 | — |
case-19 | fail→fail | 8,090 | 11,824 | +46% | 1 | 1 | 0% | 1,389 | 2,765 | +99% | 0 | 0 | — |
case-20 | fail→fail | 5,110 | 11,198 | +119% | 1 | 1 | 0% | 1,046 | 2,552 | +144% | 0 | 0 | — |
case-21 | pass→pass | 9,961 | 13,110 | +32% | 1 | 1 | 0% | 1,847 | 2,971 | +61% | 0 | 0 | — |
case-22 | fail→fail | 17,328 | 11,294 | -35% | 1 | 1 | 0% | 2,709 | 2,714 | +0% | 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 +11 percentage points is the difference between those two pass rates over the 22 comparable cases. 4 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.