Skills from the UT REAL Project MAPLES research group for creating, importing, reviewing, transforming, dry-running, validating, and formatting OSCE rubrics.
Validate specific OSCE rubric concerns for clinical validity, assessment quality, severity, and actionable fixes through expert-style critique and synthesis. Use when an agent needs to judge whether a disputed rubric issue or proposed change is valid, including concerns surfaced by dry-run grading, compare competing interpretations, incorporate educator guidance, or produce a consensus recommendation with exact rubric changes.
Analyze an OSCE case, draft rubric, example student artifact, and validated trial grade sheet to identify dry-run friction and produce prioritized rubric-improvement suggestions. Use when dry-run evidence shows grading ambiguity, evidence mismatch, weak scoring discrimination, missing case-critical expectations, or safety and fairness concerns.
Generate synthetic OSCE student artifacts such as post-encounter notes, encounter transcripts, or transcript-derived observation logs from case materials, optional templates, learner profiles, target performance bands, and rubric focus areas. Use when an agent needs realistic sample learner output for dry-run grading. Do not use for grading, rubric critique, rubric revision, raw audio or video generation, native media analysis, or inventing hidden case facts.
Produce provisional OSCE grade sheets from a Rubric Maker rubric and text analogues of OSCE evidence. Use when an agent needs to dry-run scoring against a draft rubric using post-encounter-note text, transcript text for audio evidence, observation-log text for video evidence, or a transcript-plus-observations bundle, with evidence, rationale, confidence, subtotals, totals, and deterministic grade-sheet validation. Do not use for generating student artifacts, revising rubrics, adjudicating clinical validity, or inspecting raw audio/video.
Review OSCE rubrics for clinical alignment, safety, observability, objectivity, feasibility, reliability, scoring clarity, missing Technique/Purpose fields, and Rubric Maker suggestion output. Use when an agent needs to audit an existing rubric, produce clarifying questions, or generate structured improvement suggestions. Use evaluate-dry-run instead when the critique is based on a trial grade sheet, and use content-validation when a specific concern or proposed fix needs clinical-validity adjudication, severity, consensus, or educator-guided tie-breaking.
Own this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimOwn this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimBased on adoption, maintenance, documentation, and repository signals. Not a security audit or endorsement.
This repository is a marketplace for Codex CLI and Claude Code plugins published by the UT REAL Project MAPLES research group.
The marketplace currently contains one installable plugin, Rubric Maker, plus placeholder directories for future Case Generation and Validation Analysis plugins.
.
├── .agents/plugins/marketplace.json
├── .claude-plugin/marketplace.json
├── plugins/
│ ├── rubric-maker-skill/
│ ├── case-generation/
│ └── validation-analysis/
├── scripts/
└── README.md
Each plugin is self-contained.
Plugin manifests, skills, scripts, references, and Python requirements live inside
plugins/<plugin-name>/.
This layout follows the Codex repo marketplace pattern of
.agents/plugins/marketplace.json with one plugins[] entry per tracked plugin and
./plugins/<plugin-name> source paths.
It also follows the Claude Code plugin convention where each plugin has its own
.claude-plugin/plugin.json and component directories at the plugin root.
The Codex marketplace keeps placeholder plugins visible with
policy.installation: "NOT_AVAILABLE". The Claude Code marketplace exposes only
installable plugins because Claude marketplace entries do not have an equivalent
unavailable policy.
| Plugin | Status | Purpose |
|---|---|---|
rubric-maker-skill | Available | Skills and scripts for creating, importing, reviewing, transforming, dry-running, validating, and formatting OSCE rubrics. |
case-generation | Codex placeholder only | Future case generation workflows and skills. |
validation-analysis | Codex placeholder only | Future validation analysis workflows and skills. |
Use the public marketplace repository URL when adding this marketplace.
codex plugin marketplace add https://github.com/JamiesonLabUTSW/maples-toolkit
codex plugin install rubric-maker-skill --source ut-real-project-maples
For local development, run Codex from this repository root.
Codex can read the repo marketplace at .agents/plugins/marketplace.json, where each
plugin entry points to ./plugins/<plugin-name>.
/plugin marketplace add https://github.com/JamiesonLabUTSW/maples-toolkit
/plugin install rubric-maker-skill@ut-real-project-maples
For local development, load a plugin directly:
cc --plugin-dir plugins/rubric-maker-skill
Install only the requirements for the plugin you are using:
python3 -m pip install -r plugins/rubric-maker-skill/requirements.txt
The root requirements.txt is a compatibility shim for the currently available plugin:
python3 -m pip install -r requirements.txt
Future plugins should maintain their own plugins/<plugin-name>/requirements.txt when
they ship Python scripts or other Python runtime dependencies.
Contributor setup, pre-commit hooks, CI checks, and validation commands are documented in CONTRIBUTING.md.
npx claudepluginhub jamiesonlabutsw/maples-toolkit --plugin rubric-maker-skillEditorial "Web Designer" bundle for Claude Code from Antigravity Awesome Skills.
Memory compression system for Claude Code - persist context across sessions
Ultra-compressed communication mode. Cuts ~75% of tokens while keeping full technical accuracy by speaking like a caveman.
Frontend design skill for UI/UX implementation
Comprehensive UI/UX design plugin for mobile (iOS, Android, React Native) and web applications with design systems, accessibility, and modern patterns
Marketing skills for AI agents — conversion optimization, copywriting, SEO, paid ads, ad creative, and growth