ai: rewrite 2ltt skill against original papers and reference impl - #115
Merged
Merged
Conversation
…tation Reviewed all sources from CREDITS.md (Kovács ICFP'22/'24 LaTeX sources, the staged demo Haskell code, KACC) and fixed the discrepancies: - Remove fabricated guardStage: the reference demo repairs stage mismatches via coercive subtyping (adjustStage/coe), it does not stage-check lookups - Untangle conversion checking from staging strictness: full object beta/eta is the 2022 design, no-beta/eta is the CFTT 2024 design; both documented as an explicit up-front decision - Add missing content: 2022 object-language variations (monomorphization, Rep indexing), subtyping rules, cofibrancy, intensional-analysis options, CFTT computation products, join points + SOP, generativity axiom, KACC kind grammar with mono-rep/mono-conv restrictions - Complete the demo notes: meta machinery, smart constructors, quote insertion, coe, zonk, README design notes - Deduplicate: one topic per file with cross-references; fold the redundant slides notes into the 2022 file; keep the skill generic (no project refs) Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
iljakuklic
commented
Jul 23, 2026
- Extract the glossary from implementation-guide.md into glossary.md and list it in SKILL.md for visibility (#3614753068). - Reword "memorialize" to "record" in the Downen notes (#3637774438). - Turn bare backtick .md cross-references into clickable markdown links across all skill files (#3638642647). Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
Explain, next to the arrow example, that the PtrR representation is that of the function value itself (a code pointer) and that the arity lists only the argument reps — the return type's representation deliberately never appears in the kind, which is what keeps return types rep/levity-polymorphic. (#3637766663) Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
The coe case summary was written as Haskell -- comments inside the same code block as the runnable adjustStage, making it read as disabled code. Lift it out into a bullet list so it is unambiguously a summary. (#3637848617) Co-Authored-By: Claude Opus 4.8 <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.
Reviewed all sources from CREDITS.md (Kovács ICFP'22/'24 LaTeX sources, the staged demo Haskell code, KACC) and fixed the discrepancies: