Add pyem-model-generator skill with templates and offline references

[shawnrhoads]

Motivation

• Provide a reusable skill to scaffold new computational cognitive model modules and example notebooks for pyEM, including from free-text task/model descriptions with equations.
• Support consistent pyEM-style sim/fit function signatures, parameter transforms, variant handling, and parameter-recovery notebooks.
• Include offline contract and templates so generation works even when the full pyem package is not available.

Description

• Add skills/pyem-model-generator with README.md and SKILL.md that explain usage, required clarifications, free-text parsing, and generation workflow.
• Add an example-notebook template references/example-notebook-template.json to drive code and notebook generation.
• Add reference specs for common model classes (references/rl.json, references/bayes.json, references/glm.json) and generation helpers (references/model-file-template.py, references/modelclass-utils-template.py).
• Add offline resources references/pyem-runtime-contract.md and references/parameter-recovery-notebook.md to specify runtime contracts and notebook plotting requirements.

Testing

• No automated tests were added or executed as part of this change.
• The skill documentation includes recommended smoke checks (import generated module, run *_sim, run *_fit) that can be wired into CI for future automated validation.

---

Codex Task

[Copilot]

Pull request overview

Adds a new pyem-model-generator skill intended to scaffold standalone pyEM-style model modules and parameter-recovery notebooks using bundled offline reference specs/templates.

Changes:

• Introduces bundled reference specs for RL/Bayes/GLM anchors (references/*.json) to drive generation.
• Adds Python and notebook templates (model-file-template.py, modelclass-utils-template.py, example-notebook-template.json) plus offline documentation for runtime/notebook contracts.
• Adds skill-facing docs (SKILL.md, README.md) describing the generation workflow and required clarifications.

Reviewed changes

Copilot reviewed 10 out of 10 changed files in this pull request and generated 12 comments.

Show a summary per file

File	Description
skills/pyem-model-generator/references/rl.json	RL anchor spec describing required fields/imports/outputs for generated RL models.
skills/pyem-model-generator/references/bayes.json	Bayes anchor spec describing required fields/imports/outputs for generated Bayes models.
skills/pyem-model-generator/references/glm.json	GLM anchor spec describing required fields/imports/outputs for generated GLM models.
skills/pyem-model-generator/references/modelclass-utils-template.py	Shared utils template intended to be emitted alongside generated model modules.
skills/pyem-model-generator/references/model-file-template.py	Per-model Python module template (mod_desc/spec/id + sim/fit contracts).
skills/pyem-model-generator/references/example-notebook-template.json	Notebook cell template for simulation → fit → recovery plotting.
skills/pyem-model-generator/references/parameter-recovery-notebook.md	Offline reference describing required notebook sections and plots.
skills/pyem-model-generator/references/pyem-runtime-contract.md	Offline contract describing expected runtime interfaces for generated code.
skills/pyem-model-generator/SKILL.md	Skill definition and generation rules/workflow.
skills/pyem-model-generator/README.md	User-facing documentation for what the skill generates and how to prompt it.

---

💡 Add Copilot custom instructions for smarter, more guided reviews. Learn how to get started.