skeptical-labmate SKILL.md skillA
skeptical-labmate from uchicago-dsi/ai-sci-skills is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.
mdr add uchicago-dsi/ai-sci-skills/skeptical-labmate@git:20260921.9b3de7cPins git:20260921.9b3de7c in mdr.lock. Pin the fingerprint instead.
- Audit grade
- A, 17 of 17 checks passed
- Kind
- SKILL.md skill
- Repository
- uchicago-dsi/ai-sci-skills
- Path
skills/skeptical-labmate/SKILL.md- Versions recorded
- 2
- Latest version
- git:20260921.9b3de7c, committed Sep 21, 2026
- First version recorded
- Mar 20, 2026
- Size
- 4,327 bytes
- Repository stars
- 20
- License
- MIT
Review a claim, result, or next-step recommendation like a sharp labmate who is trying to catch overclaiming, bad baselines, confounds, and missing checks. Use when the agent is about to trust a result, recommend a follow-up, or tell a scientific story.
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
# Skeptical Labmate ## Use It As A Review Pass - Use this skill before strong conclusions, expensive follow-ups, or paper-style summaries. - Compose it with `$sensemaking` or `$experiment-design`; this skill is the critical second pass, not the primary analysis. - The goal is not generic doubt. The goal is to name the most dangerous weak point and the cheapest way to resolve it. ## Use This Output Contract When using this skill, report: 1. Claim or plan under review. 2. Strongest alternative explanation or confound. 3. Weakest assumption, comparison, or baseline. 4. Cheapest check that would most improve confidence. 5. Recommendation: - proceed - proceed but weaken claim - run one more check - stop or pivot ## Apply These Rules - Attack the baseline first: is it current, fair, and actually comparable? - Ask what else changed besides the claimed cause. - Ask whether the result could be measurement, logging, data-split, scheduler, or implementation artifact. - Ask whether the claim is stronger than the evidence. - Ask whether the claimed confidence is higher than the evidence supports. - Ask what a hostile reviewer or careful labmate would object to first. …
Read the whole file at its exact version.
How to install
mdr add uchicago-dsi/ai-sci-skills/skeptical-labmate@sha256:95e39a40738172f2The line at the top of this page pins the label git:20260921.9b3de7c, 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_hgvezb7xwmlcurl2)
3 badge image fetches in 30 days. What the badge shows.
Versions
The registry has recorded 2 versions of this file, between Mar 20, 2026 and Sep 21, 2026, about one every 185 days.
| version | committed | commit | size | audit | |
|---|---|---|---|---|---|
| git:20260921.9b3de7c latest | 2026-09-21 | 9b3de7c | 4,327 B | A | view · diff |
| git:20260320.999ac68 | 2026-03-20 | 999ac68 | 2,574 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 (4327 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
uchicago-dsi/ai-sci-skills · 20 stars · license MIT · pushed 2026-11-07 · branch main
API
GET https://markdownregistry.com/api/v1/artifacts/art_hgvezb7xwmlcurl2 GET https://markdownregistry.com/api/v1/resolve?ref=uchicago-dsi/ai-sci-skills/skeptical-labmate GET https://markdownregistry.com/api/v1/blob/95e39a40738172f20d783331cc2d2b19dbbb1222b5a49077e23f03b6d639c81a
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.