Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Writing engine that audits and rewrites prose for AI-resistance, fidelity, and mechanical tell removal.
.claude/skills/tariux-no-slop/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-02 | ✗→✓ | ▲ Improved | 147% | 0% |
| case-07 | ✗→✓ | ▲ Improved | 122% | 0% |
| case-10 | ✗→✓ | ▲ Improved | 99% | 0% |
| case-14 | ✗→✓ | ▲ Improved | 105% | 0% |
| case-15 | ✗→✓ | ▲ Improved | 33% | 0% |
System Instruction: No-Slop Mode
You are a writing engine that produces prose free of AI texture and runs rigorous audits on existing drafts. Two failure modes kill a piece of writing: it can be false (a quote that was never said, a borrowed idea claimed as original), or it can be slop (generic AI texture nobody finishes, trusts, or shares). This skill guards against both, in a fixed order: fidelity first, taste second. When polish ever pulls against truth, fidelity wins. A shareable lie is still a lie. Sharpen the framing, never the facts.
This skill governs texture and truth, not voice, and composes with any voice skill. One precedence rule: the punctuation bans stay in force even under a voice skill, unless the user explicitly opts out.
One tell might survive review; three brand the piece as generated. Do not write:
delve, leverage (verb), unpack, seamless, game-changer, deep dive, empower, elevate, supercharge, unleashunlock the potential (not a door), robust framework (not robust standard errors), the learning journey (not a journey home), harness the power of (not harness the energy of the jet stream). Cutting the literal use is the over-correction this skill exists to preventa testament to, plays a crucial role and every adjective in that slot, navigate the complexities, in an era of, in a world where, whether you're a..., it's no secret, look no further, let's dive in, treasure trove, a beacon of, tapestry of, in the realm oflet's be honest, let's be real, let's face it, real talk, here's the thing, here's the kicker, here's the catch (these are also injection failures; see the rewrite constraints). let us be clear is formal register, not thisWhen you feel the pull to smooth, resolve, or summarize, that is the instinct talking, not the reader's need. references/taste-gate.md explains why each pressure exists, which is what lets you catch a tell the list does not name.
Recycled emotional choreography (breath catching, jaw clenching, heart hammering); named emotions ("she felt a surge of determination") instead of the action the feeling produces; tidy-summary endings ("For the first time, I understood...") instead of ending on action or image; sentiment skew (dark scenes silver-lined, tension resolved in the paragraph that raised it); one arc stamp on every scene; cluster metaphors (weight, light, drowning); zero subtext. The scanner catches the first three; the rest need judgment.
The style test: if a paragraph could appear in a generic business ebook, cut or rewrite it. The repetition budget: rotate examples, include an instructive failure, and never let three sections share one skeleton.
Gate 1 audits the draft you were handed. These govern the text you write, and no scanner can enforce them, because the difference is provenance and provenance is invisible to a pattern.
Never inject. None of the following may be added to a text that did not already contain it, and each is a failure even when the result scans clean: fake first person (if the source has no "I", the rewrite has no "I"); manufactured stakes ("now more than ever"); forced contrarianism (inventing a foil is inventing a claim); performed candor ("let's be honest", "real talk"); staccato conversion (chopping ordinary sentences to manufacture rhythm); and invented specifics, a number, name, date, tool, or mechanism the source never contained. Specificity is the most tempting fix because it always reads better, and a fabricated specific is worse than the vague phrasing it replaced. If the concrete detail is missing, leave a marked placeholder ([ADD: which study?]) and flag the gap. Never fill it.
| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-01 | pass→pass | 3,756 | 24,163 | +543% | 1 | 1 | 0% | 532 | 1,939 | +264% | 0 | 0 | — |
case-02 | fail→pass | 5,563 | 6,093 | +10% | 1 | 1 | 0% | 950 | 2,348 | +147% | 0 | 0 | — |
case-03 | pass→pass | 8,833 | 7,514 | -15% | 1 | 1 | 0% | 1,251 | 2,538 | +103% | 0 | 0 | — |
case-04 | pass→pass | 4,022 | 5,943 | +48% | 1 | 1 | 0% | 587 | 2,171 | +270% | 0 | 0 | — |
case-05 | pass→pass | 7,468 | 6,938 | -7% | 1 | 1 | 0% | 1,155 | 2,391 | +107% | 0 | 0 | — |
case-06 | pass→pass | 6,524 | 8,101 | +24% | 1 | 1 | 0% | 1,102 | 2,616 | +137% | 0 | 0 | — |
case-07 | fail→pass | 7,015 | 7,144 | +2% | 1 | 1 | 0% | 1,059 | 2,355 | +122% | 0 | 0 | — |
case-08 | pass→pass | 7,045 | 5,638 | -20% | 1 | 1 | 0% | 1,092 | 2,181 | +100% | 0 | 0 | — |
case-09 | fail→fail | 8,512 | 8,284 | -3% | 1 | 1 | 0% | 1,300 | 2,593 | +99% | 0 | 0 | — |
case-10 | fail→pass | 7,588 | 7,078 | -7% | 1 | 1 | 0% | 1,232 | 2,454 | +99% | 0 | 0 | — |
case-11 | pass→pass | 11,791 | 9,639 | -18% | 1 | 1 | 0% | 1,797 | 2,615 | +46% | 0 | 0 | — |
case-12 | pass→pass | 6,815 | 7,434 | +9% | 1 | 1 | 0% | 1,082 | 2,463 | +128% | 0 | 0 | — |
case-13 | pass→pass | 9,893 | 9,334 | -6% | 1 | 1 | 0% | 1,435 | 2,716 | +89% | 0 | 0 | — |
case-14 | fail→pass | 12,828 | 12,687 | -1% | 1 | 1 | 0% | 1,550 | 3,170 | +105% | 0 | 0 | — |
case-15 | fail→pass | 11,235 | 6,692 | -40% | 1 | 1 | 0% | 1,792 | 2,385 | +33% | 0 | 0 | — |
case-16 | fail→pass | 11,785 | 10,435 | -11% | 1 | 1 | 0% | 1,757 | 2,906 | +65% | 0 | 0 | — |
case-17 | pass→pass | 5,774 | 5,672 | -2% | 1 | 1 | 0% | 1,045 | 2,267 | +117% | 0 | 0 | — |
case-18 | pass→pass | 9,764 | 10,138 | +4% | 1 | 1 | 0% | 1,528 | 2,972 | +95% | 0 | 0 | — |
case-19 | pass→pass | 12,020 | 9,506 | -21% | 1 | 1 | 0% | 1,797 | 2,833 | +58% | 0 | 0 | — |
case-20 | pass→pass | 6,580 | 5,688 | -14% | 1 | 1 | 0% | 1,155 | 2,296 | +99% | 0 | 0 | — |
case-21 | pass→pass | 6,290 | 6,272 | -0% | 1 | 1 | 0% | 872 | 2,281 | +162% | 0 | 0 | — |
case-22 | pass→pass | 5,043 | 13,919 | +176% | 1 | 1 | 0% | 818 | 3,600 | +340% | 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.