feat: euclid mode — pipeline-paired skills + dedicated euclid wiki (#73)#74
Merged
Conversation
…73 phase 1) Adds the euclid_<task>.md domain-mode skill family pairing euclid_strong_lens_modeling_pipeline to the assistant: - euclid_setup_pipeline — install, dataset layout, black-box start_here.py - euclid_prepare_data — segmentation validation, binary masks, extra-galaxy GUI tools, hand-assembled dataset folders - euclid_model_lens — the staged pipelines (initial MGE+SIE, Sersic photometry, lens-only subtraction, multi-waveband, full SLaM) and when to use each - euclid_workflow_products — workflow/ csv/fits/png aggregator products - euclid_hpc_runs — hpc/sync config + SLURM batch-array submission Registers the family in skills/README.md (new naming convention line + index section), adds .claude/skills symlinks, a euclid-mode routing note in AGENTS.md (skills layer + fourth sub-wiki), and the pipeline repo in sources.yaml so Project:path citations resolve. The wiki/euclid/ pages the skills reference land in the phase-2 commit. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
Fourth sub-wiki, same schema as wiki/literature/, paired with the euclid_* skills family: - entities: euclid-mission, vis, nisp, euclid-wide-survey, ext-surveys (HSC/CFIS/Pan-STARRS/DES), q1-dr1-releases, ou-phz - concepts: euclid-psf (per-tile/per-position), zero-point-corrections, psf-homogenisation (Boucaud kernels), euclid-photo-z - sources: euclid-strong-lensing (Q1 Discovery Engines A-F, ERO, NGC 6505, in-prep DR1 series), euclid-mission-data, euclid-forecasts (Ma06/Huterer06/Amara-Refregier07/Kitching08), euclid-dr1-image-processing (Fogliardi 2026 in-prep ablation — content ingested, values marked preliminary, draft PDF NOT committed) - bibliography: 21 entries verbatim from the Euclid Collaboration's shared euclid.bib (keys kept canonical), 9 external classics verified against public arXiv/Crossref metadata; bibkey_aliases.yaml maps author-year names and autolens_literature.bib keys Registers the sub-wiki in wiki/README.md. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Summary
Phases 1+2 of #73: extend the assistant with euclid mode — a domain layer pairing the collaboration's
euclid_strong_lens_modeling_pipelineto the assistant, plus a dedicated Euclid literature sub-wiki. Companion cleanup PR: PyAutoLabs/euclid_strong_lens_modeling_pipeline#27.Phase 1 —
euclid_*skills family (new naming convention registered inskills/README.md; symlinked into.claude/skills/; routing note inAGENTS.md; pipeline repo added tosources.yaml):euclid_setup_pipeline— install,dataset/<sample>/<dataset>/layout, black-boxstart_here.pyeuclid_prepare_data— segmentation validation, binary masks, extra-galaxy GUI tools, hand-assembled datasetseuclid_model_lens— the staged pipelines (initial MGE+SIE → Sersic photometry → lens-only subtraction → multi-waveband → full SLaM) and when to use eacheuclid_workflow_products—workflow/csv/fits/png aggregator productseuclid_hpc_runs—hpc/syncconfig + SLURM batch arraysPhase 2 —
wiki/euclid/(fourth sub-wiki, schema shared withwiki/literature/):euclid.bib(collab keys kept canonical), 9 pre-Euclid classics verified against public arXiv/Crossref metadata, alias map toautolens_literature.bibkeysPrivacy: in-prep DR1 drafts are summarised with values marked preliminary; no draft PDFs committed, no bib entries fabricated.
python -m autoassistant.literature validate-citationspasses.Scripts Changed
sources.yamlonly; no runnable workspace scripts touched.Test Plan
autoassistant.literature validate-citationspassesGenerated by the PyAutoLabs agent workflow.
🤖 Generated with Claude Code