Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Write copy following Sentry brand guidelines. Use when writing UI text, error messages, empty states, onboarding flows, 404 pages, documentation, marketing copy, or any user-facing content. Covers both Plain Speech (default) and Sentry Voice tones.
.claude/skills/sickn33-brand-guidelines/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-02 | ✗→✓ | ▲ Improved | 81% | 0% |
| case-03 | ✗→✓ | ▲ Improved | 76% | 0% |
| case-04 | ✗→✓ | ▲ Improved | 73% | 0% |
| case-06 | ✗→✓ | ▲ Improved | 128% | 0% |
| case-08 | ✗→✓ | ▲ Improved | 121% | 0% |
Write user-facing copy following Sentry's brand guidelines.
Choose the appropriate tone based on context:
| Use Plain Speech | Use Sentry Voice | |------------------|------------------| | Product UI (buttons, labels, forms) | 404 pages | | Documentation | Empty states | | Error messages | Onboarding flows | | Settings pages | Loading states | | Transactional emails | "What's New" announcements | | Help text | Marketing copy |
Default to Plain Speech unless the context specifically calls for personality.
Plain Speech is clear, direct, and functional. Use it for most UI elements.
| Instead of | Write | |------------|-------| | "Click here to save your changes" | "Save" | | "You can filter results by date" | "Filter by date" | | "An error has occurred" | "Something went wrong" | | "Please enter a valid email address" | "Enter a valid email" | | "Are you sure you want to delete?" | "Delete this item?" |
Sentry Voice adds personality in appropriate moments. It's empathetic, self-aware, and occasionally snarky.
404 Pages: > "This page doesn't exist. Maybe it never did. Maybe it was a dream. Either way, let's get you back on track."
Empty States: > "No errors yet. Enjoy this moment of peace while it lasts."
Onboarding: > "Let's get your first error. Don't worry, it's not as scary as it sounds."
Loading States: > "Crunching the numbers..." > "Fetching your data..."
| Avoid | Prefer | |-------|--------| | Please | (omit) | | Sorry | (be specific about the problem) | | Error occurred | Something went wrong | | Invalid | (explain what's wrong) | | Success! | (describe what happened) | | Oops | (be specific) |
| Type | Use | Example | |------|-----|---------| | Hyphen (-) | Compound words, ranges | "real-time", "1-10" | | En-dash (--) | Ranges, relationships | "2023--2024", "parent--child" | | Em-dash (---) | Interruption, emphasis | "Errors---even small ones---matter" |
In most UI contexts, use hyphens. Reserve en-dashes for date ranges and em-dashes for longer prose.
Good: "Could not save changes. Check your connection and try again." Bad: "Error: Save failed."
Good: "No projects yet. Create your first project to start tracking errors."
Avoid these common mistakes:
| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-01 | pass→pass | 6,034 | 4,543 | -25% | 1 | 1 | 0% | 1,221 | 2,385 | +95% | 0 | 0 | — |
case-02 | fail→pass | 7,986 | 6,390 | -20% | 1 | 1 | 0% | 1,459 | 2,636 | +81% | 0 | 0 | — |
case-03 | fail→pass | 7,913 | 5,903 | -25% | 1 | 1 | 0% | 1,441 | 2,543 | +76% | 0 | 0 | — |
case-04 | fail→pass | 8,920 | 7,251 | -19% | 1 | 1 | 0% | 1,613 | 2,789 | +73% | 0 | 0 | — |
case-05 | pass→pass | 4,474 | 4,178 | -7% | 1 | 1 | 0% | 779 | 2,148 | +176% | 0 | 0 | — |
case-06 | fail→pass | 4,554 | 3,338 | -27% | 1 | 1 | 0% | 876 | 1,993 | +128% | 0 | 0 | — |
case-07 | fail→fail | 5,628 | 3,059 | -46% | 1 | 1 | 0% | 1,099 | 1,976 | +80% | 0 | 0 | — |
case-08 | fail→pass | 6,735 | 5,755 | -15% | 1 | 1 | 0% | 1,164 | 2,575 | +121% | 0 | 0 | — |
case-09 | pass→pass | 4,279 | 6,049 | +41% | 1 | 1 | 0% | 750 | 2,422 | +223% | 0 | 0 | — |
case-10 | pass→pass | 3,379 | 3,590 | +6% | 1 | 1 | 0% | 656 | 2,055 | +213% | 0 | 0 | — |
case-11 | fail→pass | 5,822 | 3,007 | -48% | 1 | 1 | 0% | 1,039 | 1,982 | +91% | 0 | 0 | — |
case-12 | pass→pass | 5,270 | 3,633 | -31% | 1 | 1 | 0% | 941 | 2,035 | +116% | 0 | 0 | — |
case-13 | pass→pass | 7,179 | 3,664 | -49% | 1 | 1 | 0% | 1,296 | 2,032 | +57% | 0 | 0 | — |
case-14 | pass→pass | 7,963 | 5,311 | -33% | 1 | 1 | 0% | 1,436 | 2,377 | +66% | 0 | 0 | — |
case-15 | pass→fail | 5,847 | 2,978 | -49% | 1 | 1 | 0% | 1,159 | 1,915 | +65% | 0 | 0 | — |
case-16 | fail→pass | 8,228 | 4,884 | -41% | 1 | 1 | 0% | 1,269 | 2,364 | +86% | 0 | 0 | — |
case-17 | fail→pass | 6,353 | 3,126 | -51% | 1 | 1 | 0% | 1,136 | 1,913 | +68% | 0 | 0 | — |
case-18 | pass→fail | 4,772 | 4,174 | -13% | 1 | 1 | 0% | 811 | 2,059 | +154% | 0 | 0 | — |
case-19 | pass→pass | 2,612 | 2,722 | +4% | 1 | 1 | 0% | 437 | 1,878 | +330% | 0 | 0 | — |
case-20 | fail→fail | 6,926 | 3,103 | -55% | 1 | 1 | 0% | 1,368 | 1,918 | +40% | 0 | 0 | — |
case-21 | pass→pass | 6,650 | 4,657 | -30% | 1 | 1 | 0% | 1,349 | 2,270 | +68% | 0 | 0 | — |
case-22 | pass→pass | 6,037 | 4,193 | -31% | 1 | 1 | 0% | 1,228 | 2,141 | +74% | 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. 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.