DetectAI
/DetectAI
Wykrywa tekst pisany przez AI: audyt heurystyczny, sygnały statystyczne, wynik Pangram i skan sygnatur znaków wodnych.
- Autor
- danielmiessler ↗
- Repozytorium
- personal_ai_infrastructure ↗
- Licencja
- MIT
- Ostatnia zmiana repozytorium
- 05.11.2026
Ocena i bezpieczeństwo
- Pliki w paczce
- 5
- Skrypty
- 0
- Komentarze HTML
- 0
- Adresy URL w SKILL.md
- 0
Brak sygnałów. Repozytorium zmienione 05.11.2026, bez odwołań do wycofanych modeli i API.
MIT, otwarta: można używać i zmieniać, z zachowaniem informacji o autorze.
Co robi i kiedy
Wykrywa tekst pisany przez AI: audyt heurystyczny, sygnały statystyczne, wynik Pangram i skan sygnatur znaków wodnych.
Oryginalny opis (EN)
Detects AI-generated writing: heuristic audit against known AI patterns, statistical signals (entropy, burstiness), an empirical Pangram score, and a keyless scan for watermark or steganography signatures (invisible characters, homoglyphs, bidi). USE WHEN detect AI writing, is this AI, AI detection, AI detector, did an AI write this, does this sound like AI, pangram, scan for AI tells, AI-isms, burstiness, is this watermarked. NOT FOR rewriting prose (a writing skill), plagiarism, judging quality.
Jak działa
- Ideal State
- Intent Routing
- Data & Config
- Gotchas
- Examples
Podgląd SKILL.md
---
name: DetectAI
evals:
deterministic:
- command: "printf 'ab\\342\\200\\213cd' | bun LIFEOS/TOOLS/WatermarkScan.ts --json | bun -e 'const j = JSON.parse(await Bun.stdin.text()); const hit = j.classes.flatMap(c => c.sample).some(x => x.codepoint === \"U+200B\" && x.index === 2); process.exit(hit ? 0 : 1)'"
falsifier: "WatermarkScan.ts --json, given a fixture with U+200B at offset 2, reports no hit with that codepoint and offset"
manual:
reason: "an AI-writing assessment requires a reviewer to judge whether reported signals support the conclusion for the supplied prose"
falsifier: "the reviewer finds the verdict overstates the evidence or fails to distinguish heuristic signals from proof"
metadata:
short-description: "Detect AI writing patterns, statistical signals, Pangram scores, and hidden watermark characters. Excludes rewriting, plagiarism, and image detection."
version: 1.2.1
description: Detects AI-generated writing: heuristic audit against known AI patterns, statistical signals (entropy, burstiness), an empirical Pangram score, and a keyless scan for watermark or steganography signatures (invisible characters, homoglyphs, bidi). USE WHEN detect AI writing, is this AI, AI detection, AI detector, did an AI write this, does this sound like AI, pangram, scan for AI tells, AI-isms, burstiness, is this watermarked. NOT FOR rewriting prose (a writing skill), plagiarism, judging quality.
---
# DetectAI
Answers two questions, *how much does this read as machine-generated?* and *does it carry an embedded mark?*, with four independent measures: a heuristic audit against a severity-tiered pattern catalog, which explains why each flag fired; deterministic statistical signals (`LIFEOS/TOOLS/StatSignals.ts`), each labeled with its reliability; an empirical Pangram score, which costs money and needs a key; and a keyless watermark scan for covert channels in the bytes. Detect, the statistics and Watermark are free and need no key. The measures disagree often, and the disagreement is the useful part: text can clear every pattern on the list and still score 100% AI, which means the tells are structural rather than lexical, and a watermark hit is bytes-level proof whatever the other measures say.
## Ideal State
- Every answer rests on measures that actually ran (the pattern catalog, `StatSignals.ts`, a recorded Pangram run, `WatermarkScan.ts`), and the report names which ran and which did not.
- A plain "is this AI?" with a key configured gets the heuristic audit and the Pangram score side by side, and where they disagree the report says what the gap means.
- No report treats one signal as proof of authorship: scores carry their length and baseline caveats, and a clean watermark scan is never read as "human-written".
- The text under review is reported on, never rewritten.
## Intent Routing
| Intent | Trigger | File |
|--------|---------|------|
| **Detect** | "scan for AI tells", "flag AI patterns", "does this sound like AI", "audit this for AI-isms", "statistical signals", "burstiness", "entropy" — heuristic + deterministic statistical pass, no key needed | `Intents/Detect.md` |
| **Score** | "score this for AI", "is this AI generated", "AI detection score", "pangram", "compare these drafts" — empirical, needs key | `Intents/Score.md` |
| **Watermark** | "is this watermarked", "detect a watermark", "scan for hidden/invisible characters", "steganography", "zero-width chars" — keyless byte-level signature scan, no key needed | `Intents/Watermark.md` |
"Is this watermarked?" routes to Watermark, which answers a different question: whether a covert channel is embedded in the bytes, not whether the prose reads as AI. For "is this AI and is it marked?", run Score plus Watermark.
| File | Read when |
|------|-----------|
| `Setup.md` | getting or storing the Pangram key, credits and rates, troubleshooting 401/402/429 or a stalled task |
## Data & Config
Detect and Watermark need no setup. Score needs `PANGRAM_API_KEY` in `~/.claude/.env` (prepaid credits, about $0.05 per 1,000 words); key, credits, verification and troubleshooting are in `Setup.md`.
## Gotchas
- **Never degrade writing to beat a detector.** Injected typos, broken sentences, and "humanizer" laundering damage the prose and don't fix the underlying problem. If text must read human, the fix is a human in the loop.
## Examples
- "Scan this post for AI tells, don't change it" → **Detect**: tiered P0/P1/P2 flag report, each marked clear-problem vs judgment-call, no edits.
- "Is this AI generated?" → **Score**: single Pangram run, headline verdict plus AI/AI-assisted/human percentages, with the length caveat stated if the sample is short.
- "Which of these three drafts reads most human?" → **Score** in batch-compare mode: one call per draft, ranked table, relative comparison foregrounded over absolute numbers.
- "Did my rewrite actually help?" → **Score** before and after, with two known-human passages scored in the same batch as calibration.
Pliki w paczce (5)
- SKILL.md 5 KB
- Setup.md 5 KB
- Intents/Detect.md 3 KB
- Intents/Score.md 4 KB
- Intents/Watermark.md 2 KB
Wersje
| Repozytorium | Wynik | Licencja |
|---|---|---|
| Ta strona · danielmiessler/personal_ai_infrastructure | 95 | MIT |
| danielmiessler/LifeOS | 95 | MIT |
Migawka bazy z 13.11.2026 · wersja paczki 75042551da47 (skrót SHA-256 całej paczki)
Pobrania w ostatnich 30 dniach: 0 · ranking
Zgłoś problem z tym skillem: szkodliwa treść, błędny opis albo prośba autora o usunięcie.
Podobne skille
- 95Writing
Składa tekst z materiałów autora, usuwa ślady pisania AI i ocenia wynik narzędziem Pangram. - 95humanizer
Wykrywa i usuwa wzorce typowe dla tekstów LLM, korzystając z 24 detektorów, ponad 500 haseł słownika AI i analizy statystycznej (burstiness, type-token ratio, czytelność), i ocenia tekst. - 100humanizer
Humanizuje tekst z AI przez 28 detektorów wzorców, ponad 560 haseł słownictwa AI w 3 poziomach oraz analizę statystyczną (burstiness, type-token ratio, czytelność), w tym ocenę pod detekcję AI. - 100ai-writing-detector
Wykrywa, skanuje i ocenia wzorce pisania AI bez przepisywania tekstu, z deterministycznym lokalnym wynikiem detektora, gdy host uruchamia Node. - 100ai-writing-detector
Wykrywa, skanuje i ocenia wzorce pisania AI bez przepisywania tekstu, z deterministycznym lokalnym wynikiem detektora, gdy host potrafi uruchomić Node. - 98human-writing
Przepisuje tekst tak, by brzmiał naturalnie i w głosie autora, i sprawdza, czy nie wygląda na tekst wygenerowany przez AI.