Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Expert in building Telegram bots that solve real problems - from simple automation to complex AI-powered bots. Covers bot architecture, the Telegram Bot API, user experience, monetization strategies, and scaling bots to thousands of users. Use when: telegram bot, bot api, telegram automation, chat bot telegram, tg bot.
.claude/skills/dokhacgiakhoa-telegram-bot-builder/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-01 | ✗→✓ | ▲ Improved | -25% | 0% |
| case-03 | ✗→✓ | ▲ Improved | 0% | 0% |
| case-09 | ✗→✓ | ▲ Improved | 2% | 0% |
| case-16 | ✗→✓ | ▲ Improved | 23% | 0% |
| case-17 | ✗→✓ | ▲ Improved | 12% | 0% |
Role: Telegram Bot Architect
You build bots that people actually use daily. You understand that bots should feel like helpful assistants, not clunky interfaces. You know the Telegram ecosystem deeply - what's possible, what's popular, and what makes money. You design conversations that feel natural.
| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-01 | fail→pass | 34,541 | 29,643 | -14% | 1 | 1 | 0% | 7,040 | 5,289 | -25% | 0 | 0 | — |
case-02 | fail→fail | 22,617 | 19,975 | -12% | 1 | 1 | 0% | 3,147 | 3,292 | +5% | 0 | 0 | — |
case-03 | fail→pass | 21,808 | 19,251 | -12% | 1 | 1 | 0% | 3,132 | 3,146 | +0% | 0 | 0 | — |
case-04 | pass→pass | 20,032 | 21,195 | +6% | 1 | 1 | 0% | 2,708 | 3,399 | +26% | 0 | 0 | — |
case-05 | pass→pass | 23,276 | 16,016 | -31% | 1 | 1 | 0% | 3,392 | 3,574 | +5% | 0 | 0 | — |
case-06 | pass→pass | 20,824 | 21,365 | +3% | 1 | 1 | 0% | 3,102 | 3,790 | +22% | 0 | 0 | — |
case-07 | pass→pass | 17,932 | 23,948 | +34% | 1 | 1 | 0% | 3,032 | 3,830 | +26% | 0 | 0 | — |
case-08 | pass→pass | 19,644 | 18,861 | -4% | 1 | 1 | 0% | 2,554 | 3,039 | +19% | 0 | 0 | — |
case-09 | fail→pass | 14,681 | 18,035 | +23% | 1 | 1 | 0% | 2,593 | 2,632 | +2% | 0 | 0 | — |
case-10 | pass→pass | 21,650 | 16,725 | -23% | 1 | 1 | 0% | 2,888 | 3,704 | +28% | 0 | 0 | — |
case-11 | pass→pass | 22,502 | 20,231 | -10% | 1 | 1 | 0% | 3,005 | 3,064 | +2% | 0 | 0 | — |
case-12 | pass→pass | 19,122 | 18,209 | -5% | 1 | 1 | 0% | 2,251 | 2,547 | +13% | 0 | 0 | — |
case-13 | pass→pass | 22,250 | 17,691 | -20% | 1 | 1 | 0% | 3,164 | 3,901 | +23% | 0 | 0 | — |
case-14 | pass→pass | 21,279 | 20,150 | -5% | 1 | 1 | 0% | 2,670 | 2,944 | +10% | 0 | 0 | — |
case-15 | pass→pass | 10,141 | 15,815 | +56% | 1 | 1 | 0% | 1,873 | 2,609 | +39% | 0 | 0 | — |
case-16 | fail→pass | 20,239 | 22,241 | +10% | 1 | 1 | 0% | 2,740 | 3,358 | +23% | 0 | 0 | — |
case-17 | fail→pass | 21,493 | 19,679 | -8% | 1 | 1 | 0% | 2,970 | 3,330 | +12% | 0 | 0 | — |
case-18 | pass→pass | 18,473 | 19,340 | +5% | 1 | 1 | 0% | 2,512 | 3,120 | +24% | 0 | 0 | — |
case-19 | fail→pass | 18,041 | 16,799 | -7% | 1 | 1 | 0% | 2,432 | 2,813 | +16% | 0 | 0 | — |
case-20 | pass→pass | 16,465 | 17,711 | +8% | 1 | 1 | 0% | 2,261 | 2,994 | +32% | 0 | 0 | — |
case-21 | pass→pass | 20,021 | 11,694 | -42% | 1 | 1 | 0% | 3,080 | 2,869 | -7% | 0 | 0 | — |
case-22 | pass→pass | 24,562 | 19,651 | -20% | 1 | 1 | 0% | 4,623 | 5,084 | +10% | 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 +27 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.