clinical-evidence-reviewer SKILL.md skillA
clinical-evidence-reviewer from tuminha/dental-ai-skills is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.
mdr add tuminha/dental-ai-skills/clinical-evidence-reviewer@git:20260930.850e5bfPins git:20260930.850e5bf in mdr.lock. Pin the fingerprint instead.
- Audit grade
- A, 17 of 17 checks passed
- Kind
- SKILL.md skill
- Repository
- tuminha/dental-ai-skills
- Path
clinical-evidence-reviewer/SKILL.md- Versions recorded
- 5
- Latest version
- git:20260930.850e5bf, committed Sep 30, 2026
- First version recorded
- Sep 29, 2026
- Size
- 22,225 bytes
- Repository stars
- 7
- License
- MIT
Use when the user asks what the body of evidence says about a dental treatment, protocol, or clinical question; asks to compare treatment options (e.g., A vs B); asks whether to change clinical practice; asks for current EFP/AAP/EAO/ITI/ADA guideline status; asks for GRADE certainty across the literature; or asks for evidence-graded decision support. Do not use for single-paper teardown — for single-paper appraisal, use research-critic. This skill is body-of-evidence and outcome-centric.
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
# Clinical Evidence Reviewer — Treatment Evidence Grading Skill **Skill protocol version:** 2026.09.30 For sponsor and author relationships, hand off to `dental-author-disclosures`. Keep its dated source register separate from outcome-level certainty judgments. A relationship alone does not establish bias or justify an automatic downgrade; assess its relevance alongside the methods and sponsor's documented role. Permitted route at body-of-evidence level: the funding and relationship record (papers and register) may support a judgment on indirectness, when comparator or outcome choices favor the sponsor ([Cochrane Handbook, section 7.8.2](https://www.cochrane.org/authors/handbooks-and-manuals/handbook/current/chapter-07#section-7-8-2)), and on publication bias, when the evidence comes from a number of small studies, most of them commercially funded (GRADE guidelines 5, PMID: 21802904). [Cochrane Handbook, section 7.8.4](https://www.cochrane.org/authors/handbooks-and-manuals/handbook/current/chapter-07#section-7-8-4) gives the mechanism: conflicts of interest are one reason negative trials and unfavorable results stay unpublished. …
Read the whole file at its exact version.
How to install
mdr add tuminha/dental-ai-skills/clinical-evidence-reviewer@sha256:b34ccf0e14c43b0cThe line at the top of this page pins the label git:20260930.850e5bf, 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_nugfsavrhhfmnsx6)
2 badge image fetches in 30 days. What the badge shows.
Versions
The registry has recorded 5 versions of this file, between Sep 29, 2026 and Sep 30, 2026, more than one a day.
| version | committed | commit | size | audit | |
|---|---|---|---|---|---|
| git:20260930.850e5bf latest | 2026-09-30 | 850e5bf | 22,225 B | A | view · diff |
| git:20260930.afada4c | 2026-09-30 | afada4c | 22,054 B | A | view · diff |
| git:20260929.23f1b6e | 2026-09-29 | 23f1b6e | 21,571 B | A | view · diff |
| git:20260929.8edb160 | 2026-09-29 | 8edb160 | 20,508 B | A | view · diff |
| git:20260929.82e02cf | 2026-09-29 | 82e02cf | 19,752 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 (22225 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
tuminha/dental-ai-skills · 7 stars · license MIT · pushed 2026-09-30 · branch main
API
GET https://markdownregistry.com/api/v1/artifacts/art_nugfsavrhhfmnsx6 GET https://markdownregistry.com/api/v1/resolve?ref=tuminha/dental-ai-skills/clinical-evidence-reviewer GET https://markdownregistry.com/api/v1/blob/b34ccf0e14c43b0c7609ff8de516653c1c5be9fc545c227ac80f0879ab349252
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.