presubmit SKILL.md skillA
presubmit from scdenney/open-science-skills is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.
mdr add scdenney/open-science-skills/presubmit@git:20261028.910eafePins git:20261028.910eafe in mdr.lock. Pin the fingerprint instead.
- Audit grade
- A, 17 of 17 checks passed
- Kind
- SKILL.md skill
- Repository
- scdenney/open-science-skills
- Path
plugin/skills/presubmit/SKILL.md- Versions recorded
- 8
- Latest version
- git:20261028.910eafe, committed Oct 28, 2026
- First version recorded
- Jul 2, 2026
- Size
- 14,016 bytes
- Repository stars
- 69
- License
- a license file GitHub does not identify
Launches and configures the standalone presubmit CLI, an API-driven adversarial peer-review pipeline with 40-plus stages, including Red Team finders, Blue Team defence, proportionality, verification cascade, reference check, legal pass, and copyedit, producing one consolidated report on disk. Verifies installation and API key, chooses the output location and smoke, standard, or custom mode, launches the run, and reports the result path. Use when the user asks to run presubmit, wants a deep…
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
# Presubmit Activator A launcher and setup wizard for the [`presubmit`](https://github.com/scdenney/presubmit) Python CLI — the standalone, API-driven adversarial peer-review pipeline that writes a consolidated review report to disk. The review itself happens in the CLI against the Anthropic API (~30 stages, ~$5–10 per full run on a typical manuscript); this skill verifies the install and the key, settles where output lands, launches the run, and reports where the report ended up. This is for self-audit of your own drafts pre-submission. Refereeing someone else's manuscript goes to `journal-review`. Since presubmit 0.2.0 the CLI ports reviewer2 v2.0.0, upstream's final release: finder personas raise issues, a Blue Team defends the paper, proportionality stages demote objections the paper's own text answers, an assessment audits each defence, and a reference check looks up every bibliography entry. It adds four prompt rules from the same author's successor suite, [`research_skills`](https://github.com/isitcredible/research_skills) (robustness sentences, a defence counts only if its test could have failed, and the burden kept on the paper). It has no claim ledger… …
Read the whole file at its exact version.
How to install
mdr add scdenney/open-science-skills/presubmit@sha256:5afae5122dac37eeThe line at the top of this page pins the label git:20261028.910eafe, 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_uhe3wej7wkd7fzze)
4 badge image fetches in 30 days. What the badge shows.
Versions
The registry has recorded 8 versions of this file, between Jul 2, 2026 and Oct 28, 2026, about one every 17 days.
| version | committed | commit | size | audit | |
|---|---|---|---|---|---|
| git:20261028.910eafe latest | 2026-10-28 | 910eafe | 14,016 B | A | view · diff |
| git:20261008.697c89f | 2026-10-08 | 697c89f | 12,755 B | A | view · diff |
| git:20260909.08bf795 | 2026-09-09 | 08bf795 | 12,772 B | A | view · diff |
| git:20260905.c12f077 | 2026-09-05 | c12f077 | 12,828 B | A | view · diff |
| git:20260902.da5a263 | 2026-09-02 | da5a263 | 12,797 B | A | view · diff |
| git:20260727.b2ef5f3 | 2026-07-27 | b2ef5f3 | 12,193 B | A | view · diff |
| git:20260726.ec471db | 2026-07-26 | ec471db | 11,793 B | A | view · diff |
| git:20260702.539af7b | 2026-07-02 | 539af7b | 15,316 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 (14016 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
scdenney/open-science-skills · 69 stars · license a license file GitHub does not identify · pushed 2026-11-05 · branch main
API
GET https://markdownregistry.com/api/v1/artifacts/art_uhe3wej7wkd7fzze GET https://markdownregistry.com/api/v1/resolve?ref=scdenney/open-science-skills/presubmit GET https://markdownregistry.com/api/v1/blob/5afae5122dac37eee154e626efd30e7277e62d42d6e172fb1c640b7a8d2c23b5
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.