Add AI-generated model summaries, JSON index, and RuleHub explanation skills

[Psuedonerd]

Motivation

• Provide machine-generated, human-readable explanations for RuleHub models and tutorials to support browsing and curation by biologists and coders.
• Expose a compact JSON index for site integration and programmatic discovery of model summaries via data/ai_summaries.json.
• Add a coder-facing skill to generate technical BNGL/YAML explanations and improve the existing biologist-facing skill to standardize summary output.

Description

• Added a JSON index at data/ai_summaries.json containing summarised entries (model id, paths, one-line summary, and key_events) for models and tutorials.
• Added many AI-generated Markdown summaries under data/summaries/ and data/tutorial_summaries/ to document individual published models and tutorial examples (new *_aigenerated.md files).
• Introduced a new coder-facing skill under skills/explain-rulehub-model-coders/ including SKILL.md and an agents/openai.yaml descriptor to support technical BNGL/YAML explanations for experienced modelers.
• Updated the existing biologist-facing skill skills/explain-rulehub-model/SKILL.md to align guidance and output structure with the generated summaries and JSON index expectations.

Testing

• No automated tests were added or executed as part of this change.

---

Codex Task

[chatgpt-codex-connector]

💡 Codex Review

Here are some automated review suggestions for this pull request.

Reviewed commit: 5356cc0660

ℹ️ About Codex in GitHub

Your team has set up Codex to review pull requests in this repo. Reviews are triggered when you

• Open a pull request for review
• Mark a draft as ready
• Comment "@codex review".

If Codex has suggestions, it will comment; otherwise it will react with 👍.

Codex can also answer questions or update the PR. Try commenting "@codex address that feedback".

[chatgpt-codex-connector]

Use metadata ids for summary entries

When consumers join this new index to the existing RuleHub manifest/gallery by model id, this entry will not match: Published/Dreisigmeyer2008/metadata.yaml defines id: "Dreisigmeyer_2008", and manifest.json/gallery.json are keyed by that metadata id, but the summary index uses the BNGL basename here. The same mismatch occurs for the Gardner, Goldstein, Harmon, Hlavacek 1999, and Hlavacek 2001 entries, so those summaries become orphaned in site integration or programmatic lookup by the repository's canonical ids.

Useful? React with 👍 / 👎.