feat: add LLM catalogue layer (HowToFit is now talkable)#10
Merged
Conversation
Ship the same generated-catalogue layer the workspaces use, so an assistant can route a learner to the right lecture: - llms.txt — hand-authored routing layer (start here, learning path by chapter, "I want to understand…", and an outward route to autofit_workspace for real analysis). - llms-full.txt / workspace_index.json — generated by PyAutoBuild's navigator (regenerate_navigator.py howto…); the per-tutorial catalogue. - .github/workflows/navigator_check.yml — thin caller of PyAutoBuild's reusable navigator_check workflow (project: howtofit); keeps the catalogue from drifting. - .navigator_check_ignore — exempts the CLAUDE.md sibling-autofit_workspace cross-refs (prose pointers to the separate workspace repo, not local paths). Verified locally: check_navigator passes (paths + banners) and the catalogue regenerates with zero drift. Co-Authored-By: Claude Opus 4.8 (1M context) <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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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
Ship the same generated-catalogue layer the workspaces use, so an assistant can route a learner to the right lecture in HowToFit.
llms.txt— hand-authored routing layer (start here, learning path by chapter, "I want to understand…", and an outward route toautofit_workspacefor real analysis).llms-full.txt/workspace_index.json— generated by PyAutoBuild's navigator; the per-tutorial catalogue..github/workflows/navigator_check.yml— thin caller ofPyAutoLabs/PyAutoBuild/.github/workflows/navigator_check.yml@main(project: howtofit)..navigator_check_ignore— exempts the CLAUDE.md sibling-autofit_workspacecross-references (prose pointers to the separate workspace, not local paths).Verification
Locally:
check_navigatorpasses (paths + banners) and the catalogue regenerates with zero drift. Thenavigatorjob on this PR exercises the reusable workflow end-to-end against PyAutoBuild@main.Depends on PyAutoLabs/PyAutoBuild#105 (lecture titles, merged).
🤖 Generated with Claude Code