deep-learning-recon SKILL.md skillA
deep-learning-recon from kewang0622/mri-research-skill is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.
mdr add kewang0622/mri-research-skill/deep-learning-recon@v0.14.0Pins v0.14.0 in mdr.lock. Pin the fingerprint instead.
- Audit grade
- A, 17 of 17 checks passed
- Kind
- SKILL.md skill
- Repository
- kewang0622/mri-research-skill
- Path
skills/deep-learning-recon/SKILL.md- Versions recorded
- 14
- Latest version
- v0.14.0, committed Oct 31, 2026
- First version recorded
- Sep 20, 2026
- Size
- 4,909 bytes
- Repository stars
- 31
- License
- MIT
Read before training, fine-tuning, applying or evaluating a neural network for MRI reconstruction: unrolled and variational networks, self-supervised training (SSDU), diffusion or score-based priors, fastMRI, DIRECT, torchkbnufft. Prevents silent errors from train/test leakage, inconsistent normalization and masks, unfair classical baselines and metrics on the wrong region or scale. Classical reconstruction belongs to mri-reconstruction; reviewing or writing a manuscript belongs to…
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
# MRFoundry: Deep-Learning MRI Reconstruction You are a DL-recon researcher. **Unrolled networks** combine iterative solver steps with learned regularizers/updates and measurement consistency. Evaluate the forward model and data consistency, but do not treat consistency as proof of feature fidelity: undersampling leaves information unconstrained, and priors can influence that information even when measurement residuals are small. Method families (VN, MoDL, E2E-VarNet, SSDU, score-based), frameworks (DIRECT, fastMRI, ATOMMIC, torchkbnufft) and datasets with citations and licences: [methods, frameworks and data](references/methods-and-frameworks.md). ## Training & evaluation - Select endpoints for the intended use before training/tuning. Report benchmark metrics with their conventions when useful, alongside task-relevant evidence. Distinguish perceived image quality from measured diagnostic performance; adding SSIM, VIF/LPIPS or appearance ratings does not establish the latter. - **Split before anything is fitted.** Split by subject (or by volume when only one subject exists), tune on validation only, and touch the test set once at the end. …
Read the whole file at its exact version.
How to install
mdr add kewang0622/mri-research-skill/deep-learning-recon@sha256:c2eea13379a9191eThe line at the top of this page pins the label v0.14.0, 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_l3p6e5ph7xvl53ec)
1 badge image fetches in 30 days. What the badge shows.
Versions
The registry has recorded 14 versions of this file, between Sep 20, 2026 and Oct 31, 2026, about one every 3 days.
| version | committed | commit | size | audit | |
|---|---|---|---|---|---|
| v0.14.0 latest | 2026-10-31 | e7494be | 4,909 B | A | view · diff |
| v0.13.0 | 2026-10-31 | 4618a27 | 4,909 B | A | view · diff |
| v0.12.0 | 2026-10-31 | 747f65f | 4,909 B | A | view · diff |
| v0.12.0 | 2026-10-31 | 5143fae | 4,774 B | A | view · diff |
| v0.12.0 | 2026-10-31 | 5e72e16 | 6,204 B | A | view · diff |
| v0.8.0 | 2026-10-10 | 6e4408e | 7,841 B | A | view · diff |
| v0.8.0 | 2026-10-09 | 305d420 | 7,689 B | A | view · diff |
| v0.8.0 | 2026-10-07 | 4cc7dff | 7,741 B | A | view · diff |
| v0.7.0 | 2026-09-29 | c70057d | 7,499 B | A | view · diff |
| v0.7.0 | 2026-09-28 | adaaf21 | 6,510 B | A | view · diff |
| v0.7.0 | 2026-09-24 | 90d0c56 | 6,095 B | A | view · diff |
| v0.7.0 | 2026-09-24 | f90c25f | 5,482 B | A | view · diff |
| v0.7.0 | 2026-09-22 | c1cd332 | 4,652 B | A | view · diff |
| v0.1.0 | 2026-09-20 | a8f0a76 | 3,389 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 (4909 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
kewang0622/mri-research-skill · 31 stars · license MIT · pushed 2026-11-05 · branch main
API
GET https://markdownregistry.com/api/v1/artifacts/art_l3p6e5ph7xvl53ec GET https://markdownregistry.com/api/v1/resolve?ref=kewang0622/mri-research-skill/deep-learning-recon GET https://markdownregistry.com/api/v1/blob/c2eea13379a9191e8794c96dcbf8a160d5d52edd513f6c2f96d20472b7ca5276
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.