jolars

Implement or debug Panache's TeX math parser and formatter internals, including the lossless CST, semantic model, diagnostics, and Badness parity. Use when modifying math implementation code or regression tests. Do not use for explanatory questions,…

Incrementally migrate Panache's Pandoc-dialect inline parsing onto the unified inline IR (currently CommonMark-only) one bounded sub-task at a time, verifying every CST divergence against pandoc-native before fixing or deferring.

Grow Panache's CommonMark spec conformance under `Flavor::CommonMark` by running every `spec.txt` example through the shared parser, comparing rendered HTML against the spec's expected HTML (byte-equality after list-item whitespace normalization), and…

Incrementally make Panache's CST shape for HTML-block / raw-HTML conform to pandoc's AST shape under `Flavor::Pandoc`, so downstream consumers (linter, salsa anchor index, LSP, formatter) see the same structural decisions pandoc would have made. The `pandoc…

Profile-driven performance work on the panache parser or formatter. Measure first with perf + the right harness; classify hotspots into one of a small set of buckets; apply the matching cheap fix; verify median wall-time moved before committing.

Triage and fix panache smoke-test regressions (idempotency, losslessness, parse/format checks) from CI debug-format reports and linked issues.

Add a new built-in lint rule to the Panache linter — wire it into the registry, gate it on the right extension/flavor, add a regression fixture with focused assertions, and document it.

Add a new block-level or inline-level syntax construct to Panache's parser and formatter — confirm the pandoc-native shape first, add SyntaxKinds for every byte category, gate it behind an extension or flavor, slot the block parser at the right precedence in…

Add or change a Badness language-server code action, editor quick fix, or syntax-aware refactoring. Use when asked to expose a linter fix in editors; add a `textDocument/codeAction` for LaTeX or BibTeX; implement a standalone refactor such as changing table…

Use when the user wants to check or analyze badness's LaTeX parse concordance against texlab — "run parse-compat", "parse concordance vs texlab", "analyze parse-compat divergences", or after a parser/CST change that might shift the differential gauge. Runs…

Use when the user wants to (re)run the formatter/linter speed benchmark, compare LSP memory with texlab, or refresh the docs benchmark page — "run the benchmark", "task bench", "task bench:memory", "memory vs texlab", "update the benchmark numbers", "refresh…

Grow badness's formatter fixture coverage one LaTeX construct at a time, seeded from the latexindent gate corpus. You surface representative inputs, draft the canonical formatting under the tenets, check it against latexindent as a reference implementation…

Add a new built-in lint rule to the Badness LaTeX linter — implement the Rule trait (id/severity/description/examples + check), register it in the three lockstep lists, add unit + integration tests with a losslessness-safe fix, and regenerate the living-docs…

Use when the user wants to check or analyze badness's BibTeX parse concordance against texlab — "run bib-parse-compat", "bib parse concordance vs texlab", "analyze bib divergences", or after a `.bib` parser/CST change. Runs the soft gauge and triages any…

Investigate badness's linter (and, secondarily, its parser) against a real-world LaTeX codebase. Clone a target repo, lint it, and triage the diagnostics for false positives, incorrect spans, and unsafe autofixes (fixes that change typeset output); parse…

Profile-driven performance work on the badness parser, formatter, or linter. Measure first with the in-process micro-bench + perf/flamegraph on a real document; classify hotspots into a small set of buckets; apply the matching cheap fix; verify the median…

Add a new built-in lint rule to the fatou linter—implement it against the single-walk dispatch, register it in the one source of truth, add TDD behavior tests (plus autofix coverage when the rule ships a fix), and wire up the snapshot-pinned generated rule…

Profile-driven performance work on Fatou's formatter, parser, or linter. Measure with bench/profile.sh first, read the phase split before the leaf list, classify the hotspot, apply the smallest matching fix, and prove median wall time moved before committing.…

Grow Fatou's own Julia formatter, one construct at a time, against hand-authored fixtures. rules::lower (crates/fatou-formatter/src/formatter/rules.rs) lowers the CST into the layout IR (ir.rs) printed by printer.rs; the gate in…

Investigate fatou's linter (and, secondarily, its parser) against a real-world Julia codebase. Clone a target repo, lint it, and triage the diagnostics for false positives, incorrect spans, and unsafe autofixes; parse failures on valid Julia are caught along…

Grow Fatou's Julia parser toward JuliaSyntax.jl using the differential oracle. The projector at crates/fatou-parser/src/parser/sexpr.rs walks the CST and emits JuliaSyntax's s-expression shape; the harness in crates/fatou-parser/tests/juliasyntax_oracle.rs…

Triage and fix fatou smoke-test regressions (idempotency, losslessness, format-error, timeout) from CI debug-format reports and linked issues.

Grow arity's roxygen2 + markdown CST toward roxygen2 itself using a strict differential oracle (parser work, not formatting). roxygen2 renders #' blocks to .Rd. Use this skill to pick the next gap from the corpus, add the grammar plus projector support, lock…

Add a new built-in lint rule to the arity linter—implement it against the single-walk dispatch, register it in the one source of truth, add TDD fixtures plus the autofix-correctness (parse-clean) case, and wire up the snapshot-pinned generated docs and the…

Investigate arity's linter (and, secondarily, its parser) against a real-world R codebase. Clone a target repo, lint it, and triage the diagnostics for false positives, incorrect spans, and unsafe autofixes; parse failures on valid R are caught along the way.…

Profile-driven performance work on arity's parser, formatter, linter, or language server. Measure with scripts/profile.sh first, read the phase split before the leaf list, classify the hotspot, apply the smallest matching fix, and prove median wall time moved…

Triage and fix arity corpus smoke-test regressions (losslessness, idempotence, format-error, panic) reported by the weekly scan of real R package repos and the GitHub issues it files.

Add one research-grounded numerical optimization solver to Basin, including its public API, state and math integration, backend tests, rustdoc references, and solver-catalog synchronization. Use for a new concrete solver, not for routine fixes to an existing…