Find deepening opportunities in a codebase, informed by the domain language in CONTEXT.md and the decisions in docs/adr/. Use when the user wants to improve architecture, find refactoring opportunities, consolidate tightly-coupled modules, or make a codebase more testable and AI-navigable.
This listing is imported from SkillsMP metadata and should be treated as untrusted until upstream source review is completed.
Install skill "improve-codebase-architecture" with this command: npx skills add MrWaip/skillsmp-mrwaip-mrwaip-improve-codebase-architecture
This source entry does not include full markdown content beyond metadata.
This detail page is rendered from real SKILL.md content. Trust labels are metadata-based hints, not a safety guarantee.
Related by shared tags or category signals.
Port the next explicit unchecked use case from a Svelte compiler spec to the Rust implementation. Use when a feature already has a spec and Claude should fully close one use case, or a small group of use cases that naturally close together, while keeping strict parser/analyze/codegen boundaries. If the selected use case is too large to close cleanly, decompose it in the spec and stop.
Gap analysis for an existing feature vs reference Svelte compiler. Use when the user asks what is missing in our implementation of a feature, asks to audit a feature, or wants to check feature completeness against the reference compiler.
Diagnose a diagnostic mismatch or suspected false positive/negative against npm `svelte/compiler` by isolating the first owning failure, capturing it in `tasks/diagnostic_tests`, and recording the follow-up in the owning spec or in `specs/unknown.md`. Use when the problem is diagnostic parity rather than JS/CSS output parity.
Disciplined diagnosis loop for hard bugs and performance regressions. Reproduce → minimise → hypothesise → instrument → fix → regression-test. Use when user says "diagnose this" / "debug this", reports a bug, says something is broken/throwing/failing, or describes a performance regression.