Agent skill

Radiology Frontier

by huang-sir1 in huang-sir1/radiology-skills

Identify evidence-grounded imaging frontiers and gaps; not design lock or journal choice.

Custom licenceAuto-check passed

Install Radiology Frontier

skills CLI
$ npx skills add huang-sir1/radiology-skills --skill radiology-frontier -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install huang-sir1/radiology-skills radiology-frontier --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/huang-sir1/radiology-skills.git skills-src && mkdir -p .claude/skills && cp -r skills-src/radiology-skills/skills/radiology-frontier .claude/skills/radiology-frontier && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
radiology-frontier
GitHub stars
1.9k
Token cost
~1.7k tokens
SKILL.md length
857 words
Files
7 (incl. references)
Skills in repo
39
Repo updated
First seen
Licence
Custom licence

At a glance

Identify evidence-grounded imaging frontiers and gaps; not design lock or journal choice.

  • Works in 8 steps: Read the data — disease, modality, n,… → Scan themes (frontier-themes.md) and… → For AI/radiogenomics strategy, open… → …
  • SKILL.md covers Core stance, When to use, When to open extra files and Workflow, plus 3 more sections
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Radiology Frontier is an agent skill from huang-sir1/radiology-skills. Identify evidence-grounded imaging frontiers and gaps; not design lock or journal choice.

Its SKILL.md is about 1.7k tokens, which your agent loads only when the skill is triggered. The skill folder holds 8 other files, including reference files (for example `README.md`, `agents/openai.yaml` and `references/ai-radiogenomics-frontier-map.md`).

Example prompts

  • “/radiology-frontier”

Workflow steps

8 steps, taken from the first numbered list in SKILL.md.

  1. Read the data — disease, modality, n, centers, labels, follow-up, omics availability
  2. Scan themes (frontier-themes.md) and filter by fit — for each candidate direction,
  3. For AI/radiogenomics strategy, open ai-radiogenomics-frontier-map.md and judge the
  4. Ground in current evidence (evidence-layer.md) — retrieve relevant current primary literature
  5. Convert to questions (idea-to-question.md) — turn the best 2–4 directions into specific
  6. Add a falsification test — for each leading idea, state the counter-hypothesis, the
  7. Close the search handoff — use radiology-search when needed and carry its verified seed
  8. Return a ranked shortlist: direction → fit → evidence pattern → executable question →

What it can do on your machine

Read from SKILL.md and the folder at commit aaa0fe6. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    No scripts in the folder and no shell commands in SKILL.md.

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Radiology Frontier loads about 1.7k tokens when it runs, and up to ~6.3k if it reads all its reference files. Until then it costs about 27 tokens; SKILL.md has 857 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~27
When it runs · the whole SKILL.md, loaded when a task matches
~1.7k
With references · SKILL.md plus every file in references/, read only if the agent opens them
~6.3k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

Its licence (Custom licence) doesn't allow us to republish the file, so here is its outline and opening line. It has 857 words (~1,733 tokens).

“Use this skill to turn "what's hot in imaging AI" into a publishable question matched to the user's data — and to expose the publication-pattern evidence behind each recommendation. It is the strategic front of the chain: before designing (→…”

— opening of SKILL.md by huang-sir1, Custom licence
name
radiology-frontier

Read the full SKILL.md on GitHub

Files

SKILL.md and 6 other files (references) in radiology-skills/skills/radiology-frontier of huang-sir1/radiology-skills.

  • SKILL.md
  • README.md
  • agents/openai.yaml
  • references/ai-radiogenomics-frontier-map.md
  • references/evidence-layer.md
  • references/frontier-themes.md
  • references/idea-to-question.md

Open the folder on GitHubat commit aaa0fe6

Compare with similar skills

Radiology Frontier next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Radiology Frontier compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Radiology Frontier this skillhuang-sir1/radiology-skills1.9k—~1.7kAutomated safety check: PassCustom licence
Tao Generate Image GroundingNVIDIA/skills3.6k—~2kAutomated safety check: NotesApache-2.0
Image Manipulation Image Magickgithub/awesome-copilot40k1 repos~1.7kAutomated safety check: NotesMIT
AI Image Generation and Editingzhayujie/CowAgent47k—~1.3kAutomated safety check: PassMIT
9Router Image Generationdecolua/9router31k—~830Automated safety check: PassMIT
Image Compressionthedaviddias/Front-End-Checklist74k—~405Automated safety check: PassMIT

Similar skills

  • Official

    Two-step image grounding pipeline: extracts referring expressions from (image, caption) pairs and grounds them to pixel-space bounding boxes via a VLM.

    3.6k GitHub stars~2k tokensUpdated yesterday
    Media & CreativeAuto-check: notes
  • Image Manipulation Image Magick

    github/awesome-copilot

    Official

    Process and manipulate images using ImageMagick. An agent skill from github/awesome-copilot.

    40k GitHub starsUsed in 1 repo~1.7k tokens
    Data & AnalyticsAuto-check: notes
  • Generates or edits images from text prompts through a Python script that picks an image backend based on which API keys are configured.

    47k GitHub stars~1.3k tokensUpdated yesterday
    Media & CreativeAuto-check passed
  • Generates images through a 9Router gateway's image endpoint, with model discovery, the request fields and per-provider quirks for OpenAI, Gemini, MiniMax and others.

    31k GitHub stars~830 tokensUpdated 3 days ago
    Media & CreativeAuto-check passed
  • Image Compression

    thedaviddias/Front-End-Checklist

    A skill your agent uses when reviewing image assets, markup, and CDN or build transforms related to Compress images without quality loss.

    74k GitHub stars~405 tokensUpdated 5 days ago
    Media & CreativeAuto-check passed
  • Structured Image Generation

    bytedance/deer-flow

    Turns an image request into a structured JSON prompt and runs a bundled Python script to generate the picture, optionally guided by reference images.

    84k GitHub starsUsed in 4 repos~2.9k tokens
    Media & CreativeAuto-check passed

More from huang-sir1/radiology-skills

All 39 skills in this repo
  • Radiology Table

    huang-sir1/radiology-skills

    Create/audit editable publication tables with source reconciliation; not figures or statistical inference.

    1.9k GitHub stars~1.3k tokensUpdated 20 days ago
    Auto-check passed
  • Radiology Acquisition Qc

    huang-sir1/radiology-skills

    Audit imaging acquisition, reconstruction, series eligibility, quantitative transforms and protocol drift; not model training.

    1.9k GitHub stars~2.8k tokensUpdated 20 days ago
    Auto-check passed
  • Radiology Bibliometrics

    huang-sir1/radiology-skills

    Build reproducible radiology bibliometrics with corpus identity, disambiguation and sensitivity; not reviews.

    1.9k GitHub stars~2k tokensUpdated 20 days ago
    Auto-check passed
  • Radiology Clinical Domain

    huang-sir1/radiology-skills

    Set disease pathways, endpoints, reference standards and treatment timelines; not patient care.

    1.9k GitHub stars~2.9k tokensUpdated 20 days ago
    Auto-check passed
  • Radiology Consensus Guideline

    huang-sir1/radiology-skills

    Design/audit consensus and evidence-to-recommendation products; not review synthesis or endorsement.

    1.9k GitHub stars~2.5k tokensUpdated 20 days ago
    Auto-check passed
  • Radiology Dissemination

    huang-sir1/radiology-skills

    Create traceable posters, conference abstracts, summaries and media; not papers, decks or figures.

    1.9k GitHub stars~2.1k tokensUpdated 20 days ago
    Auto-check passed

Questions about Radiology Frontier

What does Radiology Frontier do?

Identify evidence-grounded imaging frontiers and gaps; not design lock or journal choice. Radiology Frontier is an agent skill from huang-sir1/radiology-skills. Identify evidence-grounded imaging frontiers and gaps; not design lock or journal choice.

How do I install Radiology Frontier in Claude Code?

Run `npx skills add huang-sir1/radiology-skills --skill radiology-frontier -a claude-code`. Or copy the skill folder (radiology-skills/skills/radiology-frontier in huang-sir1/radiology-skills) into .claude/skills/radiology-frontier in your project. Claude Code loads it when a task matches its description.

How do I install Radiology Frontier in Codex?

Run `npx skills add huang-sir1/radiology-skills --skill radiology-frontier -a codex`. Or copy the skill folder (radiology-skills/skills/radiology-frontier in huang-sir1/radiology-skills) into .agents/skills/radiology-frontier in your project. Codex loads it when a task matches its description.

Can I use Radiology Frontier in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add huang-sir1/radiology-skills --skill radiology-frontier -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/radiology-frontier, .gemini/skills/radiology-frontier, .github/skills/radiology-frontier and .opencode/skills/radiology-frontier in your project.

What does Radiology Frontier need to run?

SKILL.md names no scripts, command-line tools or credentials: Radiology Frontier is instructions for the agent only.

Does Radiology Frontier access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Radiology Frontier safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Radiology Frontier use?

Radiology Frontier has a licence file (the repository's licence) that doesn't match a standard licence. Read it on GitHub before reusing the skill.

How many tokens does Radiology Frontier use?

About 1.7k tokens (SKILL.md is roughly 6.9k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 4.5k tokens, read only when the agent opens those files.

What are the alternatives to Radiology Frontier?

Skills that share tags, products or a category with Radiology Frontier: Tao Generate Image Grounding (NVIDIA/skills, 3.6k stars), Image Manipulation Image Magick (github/awesome-copilot, 40k stars), AI Image Generation and Editing (zhayujie/CowAgent, 47k stars) and 9Router Image Generation (decolua/9router, 31k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Radiology Frontier?

huang-sir1 (a GitHub user) maintains it in huang-sir1/radiology-skills, which has 1,923 GitHub stars. The repository holds 39 skills in this directory. The repository was last updated on September 21, 2026.

Source: huang-sir1/radiology-skills on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.