de-ai SKILL.md skillA
de-ai from skymanbp/sci-paper is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.
mdr add skymanbp/sci-paper/de-ai@git:20261002.7e38af6Pins git:20261002.7e38af6 in mdr.lock. Pin the fingerprint instead.
- Audit grade
- A, 17 of 17 checks passed
- Kind
- SKILL.md skill
- Repository
- skymanbp/sci-paper
- Path
skills/de-ai/SKILL.md- Versions recorded
- 12
- Latest version
- git:20261002.7e38af6, committed Oct 2, 2026
- First version recorded
- Aug 16, 2026
- Size
- 34,322 bytes
- Repository stars
- 6
- License
- a license file GitHub does not identify
The single de-AI skill. Chains three passes over one target file: (1) in-house de-AI subsystem measurement (L0 lexicon plus L1-L4 structural and learned signals), (2) a vendored humanizer structural-tell audit (AIScientists-Dev/academic-humanizer Layers 1-5 plus blader/humanizer patterns 2.12-2.16 and the Pass-2 self-interrogation), and (3) claim-first faithful rewriting under hard fidelity eligibility and the §5.3 length budget. Every number, formula and citation is preserved; it strips…
Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file the same grade.
What the file says
> **Normative authority:** `docs/SCIPAPER_STANDARD.md`. Where this file and the > standard disagree, the standard wins. `docs/architecture/DEAI_SUBSYSTEM.md` explains the > design; `docs/architecture/EVALUATION.md` records the empirical evidence. Style profiles > and learned models supply evidence and positive anchors, never competing > policy. > > **Provenance (MIT, attribution retained):** this skill chains three de-AI > sources into one pipeline — the in-house de-AI subsystem (the L0-L4 tools and > the standard's feedback contract) and two vendored humanizers: > [AIScientists-Dev/academic-humanizer](https://github.com/AIScientists-Dev/academic-humanizer) > v0.3.3 (MIT; the Layer 1-5 catalog) and > [blader/humanizer](https://github.com/blader/humanizer) (MIT; the structural > families 2.12-2.16, the Pass-2 self-interrogation, and the false-positive > guards). The upstream word lists are **not** normative here — corpus evidence > is (§7 Corpus overrides). # de-ai — one skill, three passes ## 0. What this skill does Three sequential passes over one target, all inside the standard's `measure -> type -> rank -> edit -> re-measure -> disposition` loop: …
Read the whole file at its exact version.
How to install
mdr add skymanbp/sci-paper/de-ai@sha256:7b42b5af36f77ac5The line at the top of this page pins the label git:20261002.7e38af6, which is what most people want. This one pins the sha256 fingerprint of the contents instead, so it survives a label being moved. Either way the exact version is written to mdr.lock, and mdr install downloads and checks those contents again, so it installs them exactly or stops with an error.
[](https://markdownregistry.com/a/art_zgw5ztsu2lgzmsr4)
5 badge image fetches in 30 days. What the badge shows.
Versions
The registry has recorded 12 versions of this file, between Aug 16, 2026 and Oct 2, 2026, about one every 4 days.
| version | committed | commit | size | audit | |
|---|---|---|---|---|---|
| git:20261002.7e38af6 latest | 2026-10-02 | 7e38af6 | 34,322 B | A | view · diff |
| git:20260927.2c70054 | 2026-09-27 | 2c70054 | 33,985 B | A | view · diff |
| git:20260927.bbd355a | 2026-09-27 | bbd355a | 33,815 B | A | view · diff |
| git:20260927.b25f4cd | 2026-09-27 | b25f4cd | 33,814 B | A | view · diff |
| git:20260927.de925a9 | 2026-09-27 | de925a9 | 33,594 B | A | view · diff |
| git:20260927.1ad6ed7 | 2026-09-27 | 1ad6ed7 | 33,441 B | A | view · diff |
| git:20260916.6107991 | 2026-09-16 | 6107991 | 31,906 B | A | view · diff |
| git:20260905.8b73f8f | 2026-09-05 | 8b73f8f | 31,537 B | A | view · diff |
| git:20260905.e3a98f0 | 2026-09-05 | e3a98f0 | 31,366 B | A | view · diff |
| git:20260904.6b79020 | 2026-09-04 | 6b79020 | 31,184 B | A | view · diff |
| git:20260817.43132c7 | 2026-08-17 | 43132c7 | 29,206 B | A | view · diff |
| git:20260816.d75ea4a | 2026-08-16 | d75ea4a | 28,860 B | A | view |
Audit of the latest version
- pass: Frontmatter block present
- pass: Frontmatter declares a name
- pass: Frontmatter declares a description
- pass: Size between 200 bytes and 200 KB (34322 bytes)
- pass: No zero-width or bidi control characters
- pass: No instruction hidden inside an HTML comment
- pass: No link to an exfiltration or paste host
- pass: No credential-shaped string
- pass: No instruction to send local credentials anywhere
- pass: No text hidden with inline styles
- pass: No prompt-injection phrasing
- pass: No curl or wget piped into a shell
- pass: No recursive delete of root, home or parent
- pass: No instruction to read or print local credentials
- pass: No base64 blob over 200 characters
- pass: No link to a raw IP address
- pass: No script tag
Source
skymanbp/sci-paper · 6 stars · license a license file GitHub does not identify · pushed 2026-10-17 · branch main
API
GET https://markdownregistry.com/api/v1/artifacts/art_zgw5ztsu2lgzmsr4 GET https://markdownregistry.com/api/v1/resolve?ref=skymanbp/sci-paper/de-ai GET https://markdownregistry.com/api/v1/blob/7b42b5af36f77ac546252d3b7d7eee02d2a50e3e997462c27a8bd703b6262647
Your AI assistant does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.
Guides: the SKILL.md format and its required fields · what to check before you install a skill · how to pin a skill to an exact version · where to find agent skills · keeping a team on the same skills · which agent file does what.