Scans an existing KMP project for design-system usage violations, fixes them file-by-file with per-file confirmation, then re-runs Roborazzi screenshot tests and uses Claude vision to verify each fix looks correct before moving on.
KMP Agent Skills — build a new KMP feature end-to-end, layer by layer, with the full Koin 4 / Ktor 3 / SQLDelight 2 / CMP 1.11 stack wired correctly from the start.
KMP Agent Skills — keep repo documentation, docs/ reference material, agent docs, command docs, and skill routing text aligned with the actual repository.
Migrates an existing project from the owned kmp-compose-design-system (App components) to the published shadcn-compose library (Shadcn components). This is a full library swap, not an incremental fix — get explicit confirmation of the experimental-API risk before touching any code, same as /kmp-new-project's Step 6a…
Records Roborazzi golden screenshot baselines for the design system and all feature screens. Run this once after the design system is stable, then on CI any screenshot that drifts from baseline fails the build.
KMP Agent Skills — refine a project-owned skill (one your own project authored under its own skills/ /) against agentskills.io's real qualitative best practices. Complements, not duplicates, kmp-audit's mechanical detectprojectskillstandards check (frontmatter presence, 500-line cap) — this command is about whether…
KMP Agent Skills — file a bug, improvement request, or feature request against the ronjunevaldoz/kmp-agent-skills repo directly from your current session.
KMP Agent Skills — raise a well-formed GitHub issue for a skill gap, bug, pattern improvement, or new skill request. Applies structured rules so every issue is immediately actionable.
KMP Agent Skills — scan all skills for quality gaps and generate a numbered list of actionable fix prompts you can paste directly into the chat to trigger each fix.
Compares the current KMP project's :core:designsystem/components against the reference implementations in the kmp-compose-design-system skill and applies safe updates.
KMP Agent Skills — verify that a KMP change is correct by running the full validation pipeline: architecture audit, style, static analysis, unit tests, and Roborazzi screenshot regression.
Runs before the agent uses a tool for mcp__computer-use__.*, Edit and Write tool calls, executing block-computer-use-for-compose.sh and block-edit-vendored-skills.sh (2 commands). From ronjunevaldoz/kmp-agent-skills.