Radiology Stats

What it does

Example prompts

• “/radiology-stats”

Requirements

• PowerShell

Workflow steps

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

1. 1Declare route, evidence and execution state. Inventory the supplied protocol, effect rows,
2. 2Restate the design and hierarchy — independent experimental unit, patient/lesion/slice/
3. 3Pick the estimand and model/test using the route reference. Name the population quantity,
4. 4Choose the uncertainty method (e.g. Wilson/Clopper-Pearson for single-study proportions; DeLong or
5. 5Handle dependence, missingness, exclusions, attrition and deviations before looking at significance;
6. 6Handle multiplicity — declare the primary analysis; correct the rest (method + family).
7. 7Run the stop gate. If an estimand, independent/allocation unit, dependence structure, effect
8. 8Specify, then run only when ready. Complete the route template. Provide code/configuration and
9. 9Write the result — a _Radiology_-style sentence (estimate, CI, p, n) plus a Methods
10. 10Sanity-check — does the interval width align with information size? is the model paired,
11. 11In mentor mode, do not prescribe a larger model or sample by fashion. Separate

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

  Ships 1 file in scripts/ (PowerShell, from the files we listed), which the agent can run.

  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 Stats loads about 4.5k tokens when it runs, and up to ~29k if it reads all its reference files. Until then it costs about 36 tokens; SKILL.md has 1,796 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it

~36

When it runs · the whole SKILL.md, loaded when a task matches

~4.5k

With references · SKILL.md plus every file in references/, read only if the agent opens them

~29k

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

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); the scripts in this folder 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 1,796 words (~4,478 tokens).

name

radiology-stats

Read the full SKILL.md on GitHub

Files

SKILL.md and 23 other files (scripts, references) in radiology-skills/skills/radiology-stats of huang-sir1/radiology-skills.

• SKILL.md
• README.md
• agents/openai.yaml
• references/agreement-mrmc.md
• references/analysis-hierarchy-and-missingness.md
• references/causal-and-clinical-impact-inference.md
• references/diagnostic-accuracy.md
• references/experimental-inference-and-power.md
• references/high-dimensional-omics.md
• references/incremental-value.md
• references/longitudinal-and-multistate-imaging.md
• references/meta-analysis-inference.md
• references/method-comparison-and-sensitivity.md
• references/model-evaluation.md
• references/quantitative-imaging-measurement-science.md
• references/sample-size.md
• references/survival-prognostic.md
• scripts/validate_stats_skill.ps1
• … and 6 more

Open the folder on GitHubat commit aaa0fe6