bedriyan

bedriyan/medkit-app

Command Claude Code

Propose one sharpening tweak to docs/evolution.md based on recent work. Draft-only — waits for approval before writing.

bedriyan/medkit-app

Command Claude Code

Run deterministic simulator invariants and append PASS/FAIL to verify.log. Safe for /loop 20m /medkit-verify-simulation.

bedriyan/medkit-app

Skill Claude CodeCodex

Reference for the DEBRIEF MODE that lives inside the medkit-attending Managed Agent. Use this skill when debugging why the agent emitted a particular rendercaseevaluation payload, when modifying the rubric scoring logic, or when a citation appears unresolved in the UI. NOT used to author new rubrics — see…

bedriyan/medkit-app

Skill Claude CodeCodex

Curate or refresh entries in src/data/guidelines.ts from authoritative society sources via WebFetch. Use whenever the registry needs a new condition (because a hero case rubric needs a citation that doesn't exist yet) or whenever existing entries should be checked for newer guideline versions. Designed to run on a…

bedriyan/medkit-app

Skill Claude CodeCodex

Author a CaseRubric for an existing PatientCase with PLAB2/RCGP/NURSE/SEGUE framework tags and citation discipline. Use whenever a case needs to graduate from the auto-derived fallback rubric to a hand-authored one for hero-level grading. Outputs an in-place edit of src/data/polyclinicPatients.ts (or…

bedriyan/medkit-app

Instructions file

Claude Code instructions for bedriyan/medkit-app, covering medkit — claude code project notes, tech stack, key files (what to read first), commands and running node-binary wrappers on this machine.

bedriyan/medkit-app

Skill Claude CodeCodex

Scores a completed OSCE encounter against the case rubric and produces a structured debrief. Cites guideline IDs from registry. Never invents recommendation classes or LoE.

bedriyan/medkit-app

Skill Claude CodeCodex

Generates OSCE-style GP case JSON variants from an authoritative guideline + a variant brief. Outputs strict JSON conforming to cases/case.schema.json. Every clinical fact and rubric item is traceable back to a registry guideline ID.

bedriyan/medkit-app

Skill Claude CodeCodex

Drafts entries for guidelines/registry.json by fetching authoritative society/agency guidelines via WebFetch, restricted to the source whitelist. Output is always verificationStatus="auto-fetched" — only the MD signs off "verified". Designed to run on a weekly /loop to keep the registry current.

bedriyan/medkit-app

Skill Claude CodeCodex

Voices the patient in real time during a MedKit OSCE encounter. Reads hidden.historyfacts + personality + plantedcues + lies. Outputs naturalistic spoken utterances; never breaks character; never reveals more than a real standardised patient would.

bedriyan/medkit-app

Skill Claude CodeCodex

World physics for MedKit. For every student action (order test, prescribe, refer, examine, advise) returns strict JSON describing validity, what the student sees, time cost, and any change to patient state. Never speaks to the student.