Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →DeepChat app settings modification (DeepChat 设置/偏好) skill. Activate ONLY when the user explicitly asks to change DeepChat's own settings/preferences (e.g., theme, language, font size...). Do NOT activate for OS/system settings, editor settings, or other apps.
.claude/skills/thinkinaixyz-deepchat-settings/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-02 | ✗→✓ | ▲ Improved | 500% | 0% |
| case-15 | ✗→✓ | ▲ Improved | -31% | 0% |
| case-21 | ✗→✓ | ▲ Improved | 26% | 0% |
| case-03 | ✓→✓ | ＝ Same ✓ | 50% | 0% |
| case-04 | ✓→✓ | ＝ Same ✓ | 44% | 0% |
Use this skill to safely change DeepChat application settings during a conversation.
deepchat-settings SKILL.md activates this skill for the current conversation and exposes the deepchat_settings_* tools in the next tool loop iteration.Toggles:
soundEnabled: enable/disable sound effects.copyWithCotEnabled: enable/disable copying COT details.Enums:
language: DeepChat locale, including system, zh-CN, en-US, zh-TW, zh-HK, ko-KR, ru-RU, ja-JP, fr-FR, fa-IR, pt-BR, da-DK, he-IL.theme: dark | light | system.fontSizeLevel: integer level within supported range.Settings navigation (open-only):
deepchat_settings_open only when the request cannot be fulfilled by the settings tools, and avoid calling it if the change is already applied.section hints: common, display, provider, mcp, prompt, acp, skills, knowledge-base, database, shortcut, about.deepchat-settings skill document first so the skill becomes active for this conversation.deepchat_settings_toggledeepchat_settings_set_languagedeepchat_settings_set_themedeepchat_settings_set_font_sizedeepchat_settings_open (with section) and provide a short pointer to the correct Settings section. Do not call it if the requested change has already been applied.| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-01 | fail→fail | 4,599 | 10,280 | +124% | 1 | 1 | 0% | 601 | 1,230 | +105% | 0 | 0 | — |
case-02 | fail→pass | 3,793 | 16,423 | +333% | 1 | 1 | 0% | 619 | 3,713 | +500% | 0 | 0 | — |
case-03 | pass→pass | 6,777 | 5,187 | -23% | 1 | 1 | 0% | 1,116 | 1,672 | +50% | 0 | 0 | — |
case-04 | pass→pass | 5,168 | 3,975 | -23% | 1 | 1 | 0% | 1,031 | 1,484 | +44% | 0 | 0 | — |
case-14 | pass→pass | 6,974 | 10,436 | +50% | 1 | 1 | 0% | 991 | 1,977 | +99% | 0 | 0 | — |
case-05 | pass→pass | 4,105 | 2,448 | -40% | 1 | 1 | 0% | 787 | 1,166 | +48% | 0 | 0 | — |
case-06 | pass→pass | 7,801 | 2,822 | -64% | 1 | 1 | 0% | 1,300 | 1,220 | -6% | 0 | 0 | — |
case-07 | fail→fail | 6,782 | 4,960 | -27% | 1 | 1 | 0% | 1,038 | 1,022 | -2% | 0 | 0 | — |
case-08 | fail→fail | 7,127 | 19,457 | +173% | 1 | 1 | 0% | 1,080 | 942 | -13% | 0 | 0 | — |
case-09 | fail→fail | 4,523 | 5,243 | +16% | 1 | 1 | 0% | 630 | 1,040 | +65% | 0 | 0 | — |
case-10 | fail→fail | 4,018 | 14,695 | +266% | 1 | 1 | 0% | 593 | 2,978 | +402% | 0 | 0 | — |
case-11 | pass→pass | 12,486 | 8,538 | -32% | 1 | 1 | 0% | 2,467 | 1,383 | -44% | 0 | 0 | — |
case-12 | fail→fail | 5,777 | 6,970 | +21% | 1 | 1 | 0% | 1,004 | 1,158 | +15% | 0 | 0 | — |
case-13 | pass→pass | 3,494 | 5,305 | +52% | 1 | 1 | 0% | 531 | 1,650 | +211% | 0 | 0 | — |
case-15 | fail→pass | 14,457 | 6,789 | -53% | 1 | 1 | 0% | 2,031 | 1,404 | -31% | 0 | 0 | — |
case-16 | fail→fail | 4,769 | 4,611 | -3% | 1 | 1 | 0% | 795 | 1,045 | +31% | 0 | 0 | — |
case-17 | fail→fail | 3,322 | 13,558 | +308% | 1 | 1 | 0% | 454 | 3,289 | +624% | 0 | 0 | — |
case-18 | fail→fail | 4,869 | 4,974 | +2% | 1 | 1 | 0% | 756 | 1,006 | +33% | 0 | 0 | — |
case-19 | fail→fail | 4,432 | 7,844 | +77% | 1 | 1 | 0% | 591 | 1,976 | +234% | 0 | 0 | — |
case-20 | pass→pass | 4,499 | 7,727 | +72% | 1 | 1 | 0% | 640 | 1,296 | +102% | 0 | 0 | — |
case-21 | fail→pass | 6,606 | 8,238 | +25% | 1 | 1 | 0% | 1,101 | 1,392 | +26% | 0 | 0 | — |
case-22 | fail→fail | 5,624 | 20,917 | +272% | 1 | 1 | 0% | 966 | 1,037 | +7% | 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, and 14 counted toward the lift figure. The other 8 produced results that are not comparable between the two arms, so they are excluded from the headline rather than averaged into it. The headline lift of +14 percentage points is the difference between those two pass rates over the 14 comparable cases. 2 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.