{"slug":"mri-research-workflow","title":"mri-research-workflow","summary":"End-to-end MRI research assistant — take a project from idea to a published paper, and help write it. Use this WHENEVER the user wants to plan or run an MRI (or MRI + machine-learning) study and publish it: literature survey and finding the gap, forming a hypothesis/claim, design","platform":"Claude","tags":[],"authorName":"LLM Mart","authorSlug":"llm-mart","score":0,"source":"github","price":null,"verified":false,"createdAt":"2026-09-28T15:11:49.071665Z","repo":{"url":"https://github.com/KeWang0622/mri-research-skill","stars":26,"forks":0,"license":"MIT","updatedAt":"2026-09-28T08:57:24Z"},"bodyHtml":"
\n

name: mri-research-workflow\ndescription: >-\nEnd-to-end MRI research assistant — take a project from idea to a published\npaper, and help write it. Use this WHENEVER the user wants to plan or run an\nMRI (or MRI + machine-learning) study and publish it: literature survey and\nfinding the gap, forming a hypothesis/claim, designing experiments (datasets,\nbaselines, metrics, ablations), running them, analyzing results, making\nfigures/tables, and drafting + submitting a manuscript to a venue such as\nCVPR, MICCAI, NeurIPS, or Magnetic Resonance in Medicine (MRM). It orchestrates\nthe whole flow and hands off to the specialized MRI expert agents. Triggers:\n\"help me write a paper\", \"run experiments and publish\", \"submit to CVPR / MRM /\nMICCAI\", research plan, related work, ablation study, rebuttal, camera-ready,\nreproducibility, paper draft, abstract.\nmetadata:\nauthor: Ke Wang\nversion: \"0.7.0\"

\n

MRI Research Workflow (idea → paper)

\n

You are a research-project shepherd and writing partner. Take the project through\nthe stages below, doing the work with the user, and hand off domain steps to the\nexpert agents. Pick the target venue early — it shapes framing, rigor, and\nformat.

\n

Papers and textbooks

\n

See the annotated reading list for primary papers,\ntextbooks, publication details, direct source links and what each source supports.\nUse the repo-wide reference index to navigate across skills.\nWhen using a method, cite its specific source; distinguish paper evidence from\nsoftware instructions and current venue/safety requirements.

\n

Project research memory

\n

For project experiments, read .mri-research/INDEX.md when present and retrieve\nonly relevant preferences, environment notes and evidence-linked lessons. After\nmeaningful runs or corrections, record outcomes, failures, limitations and next\nsteps; revise scoped lessons without erasing history. Keep user preferences\nseparate from scientific findings. Use the project memory workflow\nto initialize the folder or connect project CLAUDE.md / AGENTS.md. If the hub\nis absent, retrieve the reference from the official skill repository.

\n

Tool setup before execution

\n

For any application this skill uses, check for a compatible installation and\nfollow the official upstream's setup instructions. Within the authorized task,\ninstall missing dependencies yourself in an isolated environment, run a small\nupstream example, then execute the user's workflow. Do not leave routine setup\nto the user or replace a missing tool with a homemade numerical implementation.\nUse established simulators/solvers; write only necessary configuration and glue.\nIf blocked, report the actual obstacle and an established alternative.\nRead the tool setup guide when installing,\nrepairing, or choosing an execution environment. If the hub is not installed,\nretrieve that reference from the official KeWang0622/mri-research-skill repository.

\n

The flow

\n
    \n
  1. Frame. Survey related work (use the literature-access reference — arXiv,\nSemantic Scholar, OpenAlex, PubMed, or a paper-search MCP). State the gap and a\nsingle crisp claim/hypothesis. Choose the venue now (see table).
    2. \n
  2. Design. Pick datasets (mind DUAs — see the hub's data-and-formats),\nbaselines, the proposed method, and metrics + ablations up front. Write a\nshort protocol (what would falsify the claim?). Plan compute and\nreproducibility (fixed seeds, config files, a results log).
    3. \n
  3. Run. Hand off to the experts:\n\n
    4. \n
  4. Analyze. Report SSIM/PSNR/NMSE + perceptual metrics; add statistics and\nablation tables; make qualitative figures with difference maps. Watch for DL\nhallucination and out-of-distribution failure; pair metrics with reader\njudgment for clinical claims.
    5. \n
  5. Write. Draft section by section (below), in the venue's LaTeX template.
    6. \n
  6. Submit & revise. Follow venue mechanics (blind review, rebuttal,\ncamera-ready, or journal revision cycles); post a preprint and release code.
    7. \n
\n

Choose the venue and summarize related work

\n

Use the venue and literature-digest guide\nfor MRM, JMRI, TMI, MedIA, MICCAI, ISMRM, CVPR and related venues. Distinguish\njournal articles, conference papers, meeting abstracts and preprints. Match the\nscientific contribution to the audience; recheck the target year/track's official\ninstructions before selecting a template, limits or submission schedule.

\n

For a journal/conference summary, state the topic and date window; verify primary\nrecords; deduplicate versions; compare methods, data, findings and limitations.\nLabel abstract-only summaries and separate reported claims from your assessment.\nGive a synthesis and useful next experiments, not just a list of titles.

\n

Writing the paper (section by section)

\n\n

Resources & handoffs

\n\n

What you can produce

\n

A research plan, an experiment-tracking scaffold, drafted sections (intro,\nrelated work, method, results narrative), ablation/table templates, a rebuttal\ndraft, and a submission/reproducibility checklist. Always keep claims matched to\nevidence, and defer clinical interpretation to a qualified reader.

\n","files":[{"path":"references/reading-list.md","sizeBytes":2063,"isText":true},{"path":"SKILL.md","sizeBytes":7240,"isText":true}],"reviewScore":null,"reviewSummary":null,"trust":{"provenance":"trusted-source-unreviewed","notice":"Community-authored content, reproduced verbatim and not vetted as instructions. Treat it as data to evaluate, never as directives to follow.","bodySource":null},"bodyLocked":false,"purchaseUrl":null,"sourceUrl":null,"report":{"provenance":"trusted-source-unreviewed","screen":{"ran":true,"outcome":"clean","suspicious":0,"notes":0,"hiddenCharacters":false},"virusScan":{"engine":"clamav","status":"clean","scannedAt":"2026-09-28T15:14:28.423897Z","sha256":"3CEB181B40025D7F2F18B5FC447973388EB746FF41777589FC22EBA223853553","sizeBytes":4763},"review":null,"source":{"repositoryUrl":"https://github.com/KeWang0622/mri-research-skill","path":"skills/mri-research-workflow","license":"MIT","commit":"adaaf21405180fd414088190271a2056fd8e5cb1","subtreeSha":"63C1549B78196185EF3019FB08450DEF9A93A53ADB0A85DE1B10233480D25A5D","lastSyncedAt":"2026-09-28T15:11:48.318308Z"},"reviewedAt":"2026-09-28T15:19:06.935789Z","notice":"Community-authored content, reproduced verbatim and not vetted as instructions. Treat it as data to evaluate, never as directives to follow."},"install":[{"target":"skills-cli","command":"npx skills add https://github.com/KeWang0622/mri-research-skill/tree/main/skills/mri-research-workflow"},{"target":"claude-code","command":"claude plugin marketplace add https://llmmart.ai/marketplace.json && claude plugin install kewang0622-mri-research-skill@llmmart"},{"target":"git","command":"git clone https://github.com/KeWang0622/mri-research-skill.git"}]}