Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Write or rewrite text in ASD-STE100 Simplified Technical English. ONLY use this skill when the user explicitly invokes it by name — i.e. they type "/ste" or literally write "use the ste skill" / "apply ASD-STE100". Do NOT trigger it on paraphrased intent such as "simplify this", "make it clearer", "write technical documentation", or "shorter sentences please" — the user has deliberately scoped this skill to explicit invocation only. For those requests, respond normally without loading this skill
.claude/skills/penpot-ste/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-01 | ✗→✓ | ▲ Improved | 43% | 0% |
| case-02 | ✗→✓ | ▲ Improved | 480% | 0% |
| case-03 | ✗→✓ | ▲ Improved | 171% | 0% |
| case-11 | ✗→✓ | ▲ Improved | 121% | 0% |
| case-12 | ✗→✓ | ▲ Improved | 79% | 0% |
Apply the ASD-STE100 standard to all prose you produce in this task. Do not announce that you use STE, do not name the standard, and do not explain the style unless the user asks. If the user later asks you to "write more naturally," ask one short question to confirm they want to leave STE before you drop it.
Compliance note (for you, not for output): the official specification and its dictionary are copyright ASD. This skill encodes paraphrased rules and a publicly sourced word list. For certified aerospace/defense deliverables, tell the user that full compliance requires the free official specification (asd-ste100.org) and a human sign-off. Never claim certified compliance.
Only when the user explicitly invokes it: they type /ste, or say "use the ste skill" / "apply ASD-STE100". Requests like "simplify this", "make it clearer", or "shorter sentences" do NOT invoke it — respond normally unless it is named.
Before writing a single sentence, decide: is this procedural text (instructions someone follows) or descriptive text (explanation, background, description)? Every limit below depends on this. Mixed documents get classified section by section.
references/word-substitutions.md and apply it; it is the working dictionary for this skill."WARNING: Do not touch the terminal. The terminal has a dangerous voltage."
After drafting, scan your text once for each of these and fix every hit before you respond:
references/word-substitutions.mdreferences/word-substitutions.md — unapproved → approved word mappings and one-meaning rulings. Read it before drafting; it is short.references/examples.md — worked before/after rewrites (procedural, descriptive, warnings, common mistakes). Read it when rewriting existing text or when unsure how a rule applies.Code blocks, command strings, file paths, error messages, quoted UI text, and proper nouns stay exactly as written. STE applies to the prose around them.
| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-01 | fail→pass | 18,690 | 17,300 | -7% | 1 | 1 | 0% | 3,162 | 4,517 | +43% | 0 | 0 | — |
case-02 | fail→pass | 8,733 | 47,872 | +448% | 1 | 1 | 0% | 1,049 | 6,087 | +480% | 0 | 0 | — |
case-03 | fail→pass | 18,496 | 34,393 | +86% | 1 | 1 | 0% | 3,010 | 8,147 | +171% | 0 | 0 | — |
case-04 | pass→pass | 11,019 | 24,776 | +125% | 1 | 1 | 0% | 801 | 5,809 | +625% | 0 | 0 | — |
case-05 | pass→pass | 6,551 | 6,195 | -5% | 1 | 1 | 0% | 783 | 2,313 | +195% | 0 | 0 | — |
case-06 | fail→fail | 4,617 | 5,219 | +13% | 1 | 1 | 0% | 628 | 1,953 | +211% | 0 | 0 | — |
case-07 | pass→pass | 21,217 | 14,900 | -30% | 1 | 1 | 0% | 3,326 | 3,926 | +18% | 0 | 0 | — |
case-08 | pass→pass | 8,578 | 10,572 | +23% | 1 | 1 | 0% | 1,426 | 3,378 | +137% | 0 | 0 | — |
case-09 | pass→pass | 16,461 | 9,299 | -44% | 1 | 1 | 0% | 2,481 | 2,853 | +15% | 0 | 0 | — |
case-10 | pass→pass | 15,383 | 9,516 | -38% | 1 | 1 | 0% | 2,272 | 2,931 | +29% | 0 | 0 | — |
case-11 | fail→pass | 9,173 | 8,284 | -10% | 1 | 1 | 0% | 1,240 | 2,745 | +121% | 0 | 0 | — |
case-12 | fail→pass | 20,288 | 10,604 | -48% | 1 | 1 | 0% | 1,689 | 3,020 | +79% | 0 | 0 | — |
case-13 | fail→pass | 12,041 | 9,556 | -21% | 1 | 1 | 0% | 1,743 | 2,774 | +59% | 0 | 0 | — |
case-14 | pass→pass | 13,784 | 25,188 | +83% | 1 | 1 | 0% | 1,943 | 3,431 | +77% | 0 | 0 | — |
case-15 | fail→pass | 12,737 | 9,236 | -27% | 1 | 1 | 0% | 2,086 | 2,756 | +32% | 0 | 0 | — |
case-16 | pass→pass | 16,703 | 6,352 | -62% | 1 | 1 | 0% | 2,573 | 2,248 | -13% | 0 | 0 | — |
case-17 | fail→pass | 10,159 | 8,670 | -15% | 1 | 1 | 0% | 1,455 | 2,793 | +92% | 0 | 0 | — |
case-18 | fail→pass | 13,584 | 11,680 | -14% | 1 | 1 | 0% | 2,031 | 3,254 | +60% | 0 | 0 | — |
case-19 | fail→pass | 10,236 | 20,535 | +101% | 1 | 1 | 0% | 1,643 | 3,668 | +123% | 0 | 0 | — |
case-20 | pass→pass | 12,329 | 10,849 | -12% | 1 | 1 | 0% | 1,813 | 3,178 | +75% | 0 | 0 | — |
case-21 | fail→pass | 4,605 | 2,291 | -50% | 1 | 1 | 0% | 582 | 1,576 | +171% | 0 | 0 | — |
case-22 | fail→pass | 13,574 | 8,129 | -40% | 1 | 1 | 0% | 2,302 | 2,622 | +14% | 0 | 0 | — |
case-23 | fail→fail | 21,583 | 12,503 | -42% | 1 | 1 | 0% | 1,430 | 3,252 | +127% | 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. 23 cases were attempted. The headline lift of +52 percentage points is the difference between those two pass rates over the 23 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.