rosepetal-ai

Build, refresh, or promote rows from `docs/initialDocs/derivedBibliography.md` — the auto-generated catalogue of references cited by the papers under `literature/papers/`. Use when the user asks to "extract references", "build the derived bibliography", "refresh derived refs", "what does paper X cite", "promote this derived ref to the main bibliography and download it", or to scan/aggregate citations from the local PDFs. Also: every time a new paper folder lands on disk, this refresh has to run so the derived list stays current.

Build the GPU Docker image and validate the runtime environment.

Build a dataset manifest and validate it against the manifest schema.

Build all paper figures and tables from registered runs and verify claim coverage.

Run an ablation grid and aggregate the results.

Run the end-to-end smoke pipeline (dummy model on the synthetic smoke dataset).

Add a single new paper or repository to docs/initialDocs/revisedBibliography.md and, when possible, materialise its `literature/papers/<slug>/` folder (PDF + shallow-cloned repo + notes.md + citation.bib) following docs/initialDocs/bibliographySpec.md. The folder is created only when at least one artefact (PDF or repo) was downloaded AND year + first author are known; otherwise the row is added with an empty Literature dir cell. Use when the user pastes a URL, BibTeX, or arXiv ID and asks to "add this paper", "save this reference", "track this in the bibliography", etc.

Build, refresh, or promote rows from `docs/initialDocs/derivedBibliography.md` — the auto-generated catalogue of references cited by the papers under `literature/papers/`. Use when the user asks to "extract references", "build the derived bibliography", "refresh derived refs", "what does paper X cite", "promote this derived ref to the main bibliography and download it", or to scan/aggregate citations from the local PDFs. Also: every time a new paper folder lands on disk, this refresh has to run so the derived list stays current.

Run the documentation environment validator standalone. Probes Node-RED, the toolkit install in ~/.node-red, the native addon, sharp, ffmpeg, the required MCP servers, fixture images, and filesystem permissions. Self-heals whatever can be fixed automatically; reports a structured JSON status. Use before a /document-node run if anything in the environment changed, or to debug why a doc run failed.

Find every node in @rosepetal/node-red-contrib-image-tools that lacks documentation (no docs/<cat>/<name>.md or no assets/nodes/<cat>/<name>-demo.gif) and run /document-node on each, sequentially. Reports a final table of successes and failures. Pass --include-existing to re-document every registered node, regardless of current state.

Autonomously generate complete documentation for a Node-RED node in @rosepetal/node-red-contrib-image-tools. Produces (1) the long-form Markdown at docs/nodes/<category>/<name>.md, (2) the inline <script data-help-name> block inside the node's HTML, and (3) the demo GIF at assets/nodes/<category>/<name>-demo.gif. Coordinates four specialist agents through a 5-phase pipeline with active environment validation, self-healing, and a reasoning post-review with up to 2 retries. All output is in English.