What it does
This repo is a collection of 40 skills
- Connects Instruction files the AI reads
- Account or key No key found in README or SKILL.md
- Category Other
For makers: add a badge to your README
If you made this, paste this code into your README. The badge links back to this page.
[](https://mcp.popnx.com/en/skills/huang-sir1-radiology-skills)Similar Skills
Same kind of work, ordered like the Skills list
| This one radiology-skills | llmfit | claude-video | VideoCaptioner | claude-cookbooks | |
|---|---|---|---|---|---|
| Maker | huang-sir1 | AlexsJones | bradautomates | WEIFENG2333 | anthropics |
| Skills | 40 | 1 | 1 | 1 | 4 |
| GitHub stars | 1,982 | 39,119 | 21,321 | 16,585 | 54,886 |
| Last code change | Sep 21, 2026 | Nov 18, 2026 | Sep 25, 2026 | Sep 12, 2026 | Nov 20, 2026 |
| License | – | MIT | MIT | GPL-3.0 | MIT |
40 skills (instruction sets) by huang-sir1 that an AI reads and follows · not an MCP server
Pick the skill to install
Install only the ones you use. Open a skill to see how to install it
This set has 40 skills, too many to install at once: every installed skill’s description loads into every chat, so the AI picks the wrong one more easily. Pick only the ones you use from the list below
- radiology-acquisition-qc
Audit imaging acquisition, reconstruction, series eligibility, quantitative transforms and protocol drift; not model training.
- radiology-annotation
Design/audit imaging truth, readers, ROI geometry, reproducibility and label noise; not model training.
- radiology-bibliometrics
Build reproducible radiology bibliometrics with corpus identity, disambiguation and sensitivity; not reviews.
- radiology-citation
Verify claim-level sources and DOI/PMID; export checked citations. Not discovery or evidence synthesis.
- radiology-clinical-domain
Set disease pathways, endpoints, reference standards and treatment timelines; not patient care.
- radiology-consensus-guideline
Design/audit consensus and evidence-to-recommendation products; not review synthesis or endorsement.
- radiology-data
Plan/audit imaging provenance, DICOM de-identification, sharing, repositories and retention; not ethics approval.
- radiology-deep-learning
Design/train/audit imaging DL pipelines, splits, tuning and validation; not deployment studies.
- radiology-design
Lock study feasibility, population, estimand, imaging task and validation; not novelty scanning or execution. CN: 可行性、课题设计、样本量、外部验证
- radiology-dissemination
Create traceable posters, conference abstracts, summaries and media; not papers, decks or figures.
- radiology-ethics
Audit IRB, consent, privacy, IACUC/IBC, biosafety and dual use; not logistics or lab execution.
- radiology-experiment-design
Design/audit tissue, cell, organoid, animal, perturbation and rescue validation; not physical SOP execution.
- radiology-figure
Create/audit publication plots, visual abstracts and imaging panels with render QA; not tables or decks. CN: 统计图、ROC、森林图、影像图版
- radiology-frontier
Identify evidence-grounded imaging frontiers and gaps; not design lock or journal choice.
- radiology-grant
Develop/review radiology grants against a live call, including current NSFC rules, code/call routing, funder criteria and imaging feasibility; not papers or decks. CN: 标书、国自然、基金评审
- radiology-health-economics
Plan/audit imaging economic evaluation, decision models, budget impact, uncertainty and HTA reporting.
- radiology-innovation-transfer
Assess disclosure, prior-art handoff, rights and transfer readiness; not patentability, FTO or legal advice.
- radiology-journal
Match a near-finished imaging paper to live journal scope and tier; not scientific review or file audit.
- radiology-method-evaluation
Audit parameter provenance, metric fit, fair comparisons and robustness; not execution or paper review.
- radiology-paper2ppt
Plan/create/audit evidence-led research decks for defenses, meetings and talks, with render QA. CN: PPT、答辩、组会汇报
- radiology-pipeline
Mentor and route ambiguous, multistage or resumed radiology research; tutoring defaults to read-only. CN: 总控、课题导航、下一步
- radiology-polishing
Polish existing research prose while preserving facts and claims; not drafting or scientific repair.
- radiology-prereview
Run author, peer or editorial scientific review with traceable findings; not checklists or upload audits. CN: 模拟审稿、预审、大修风险
- radiology-qualitative-mixed-methods
Design/audit qualitative and mixed-methods sampling, reflexivity, integration and claim limits.
- radiology-radiogenomics
Interpret mechanisms and imaging-mechanism bridges with competing explanations and causal ceilings.
- radiology-radiomics
Design/audit radiomics preprocessing, IBSI extraction, stability, leakage-safe selection and validation.
- radiology-reader
Create bilingual figure-aware readers from supplied papers; not reader-study or MRMC design.
- radiology-reporting
Select/audit reporting guidelines across imaging AI, diagnosis, reviews, guidelines and economics.
- radiology-reproducibility
Audit/package computational replay with manifests, environments, provenance and evidence levels.
- radiology-research-integrity
Audit authorship, COI, AI use, selective reporting and artifact integrity; not misconduct adjudication.
- radiology-research-ops
Plan/audit sites, RACI, milestones, dependencies, resources, risks and closeout; not scientific design.
- radiology-response
Adjudicate reviews, draft point-by-point responses and verify closure; not initial prereview.
- radiology-search
Search/deduplicate imaging papers or datasets into reproducible corpora; not claim checks or review synthesis. CN: 文献检索、公共数据集
- radiology-stats
Plan/compute/audit inference on defined data/effect rows: CI, AUC, MRMC, survival, meta-analysis and power. CN: 统计、样本量、AUC比较、校准
- radiology-submission
Audit journal or conference packages against current exact-venue fields/files; not scientific review. CN: 投稿材料、投稿包、文件检查
- radiology-systematic-review
Design/audit systematic or scoping reviews from protocol through synthesis, certainty and living updates.
- radiology-table
Create/audit editable publication tables with source reconciliation; not figures or statistical inference.
- radiology-transcriptomics-analysis
Build/run/audit bulk RNA, sc/snRNA and spatial workflows with traceable QC; not mechanism claims.
- radiology-translation
Design clinical use, reader/impact studies, human factors, deployment and lifecycle evidence.
- radiology-writing
Draft/restructure manuscripts or theses from fixed evidence; not polishing, review or rebuttal. CN: 论文写作、英文稿、结构化摘要
How a Skill differs from MCP
MCP = the hands
Connects the AI to an outside service or data, such as reading Notion or creating an invoice. A program or server has to be running.
Skill = the manual
A text file that teaches the AI how to do a task. It connects to nothing.
Some overlap: a few Skills run scripts that call tools, and a few MCP servers only send knowledge. Start from the task you want done.
Works with
Not stated by the maker · SKILL.md skills work in apps that support Agent Skills, such as Claude Code, Codex and Cursor
Install
Pick a skill first
This repo has 40 skills. Pick one from the list above; its page shows every way to install it, including letting the AI install it and a ZIP
Discussion
Ask, share a tip or report that it does not work. Sorted by what people marked helpful.
No posts yet. Be the first to ask or share.
Posts here are written by users, not the PopNx team.
From GitHub
- GitHub stars
- 1,982
Stars are for the whole repo, not each skill - Maker
- huang-sir1
- License
- License per folder (1) No repo-wide license, but Skill folders carry their own license files (1 folders). They may differ: check the LICENSE in the folder of the Skill you use.
- Last code change
- Sep 21, 2026
- SKILL.md files in the repo (including translated copies and templates)
- 40