vladyslav-skills

Use when adding a feature to a production project. Full cycle: brainstorm, plan, implement, docs.

Use when fixing a bug in a production project. Full cycle: diagnose, fix, regression test, review, docs.

Use to batch-validate all skills in this plugin. Runs deterministic repo-wide static checks (frontmatter, command delegation, cross-references, Architect model= rule, orphan references, README<->MemPalace sync) and reports pass/fail per skill.

Use when creating a new project. Bare AI shell by default; interactive menu adds docs / backend-infra / agents on demand.

Use after init-project to fill docs/product/start-project.md with AI research on competitors, monetization, valuation, and marketing.

Use when unsure which skill to use. Lists all vladyslav skills, workflow, and integration.

Quick-save the latest decision/problem/milestone to MemPalace with zero questions — derives everything from the current conversation. Use for a fast mid-session capture, or accept it when offered at task completion.

Use after docs/design/system.md is approved to design app screens in Pencil. Dispatches one subagent per screen, draws against the design system contract.

Use when an existing UI project has no docs/design/system.md or when design tokens have drifted. Scans the codebase, extracts canonical tokens, writes docs/design/system.md.

Use for iOS projects to pre-validate against Apple App Store Review Guidelines before development. Fills the rejection-risk checklist in start-project.md.

Use on an existing project to scan code once and produce both architecture docs and a MemPalace seed pass.

Use when human-readable docs are needed. Generates README, onboarding, and deployment guides from code/architecture.

Use when test docs are missing or outdated. Generates test plan and manual QA checklist from PRD and user stories.

Save a knowledge record (decision, preference, milestone, or problem) to MemPalace for the current project wing. Use at end of session or any time after a key insight — no compaction needed.

Use when adding Claude Code structure to an existing project. Auto-detects stack, creates only missing files.

Use before any production deployment. Verifies tasks, tests, configs, docs, translations, and iOS Apple-review readiness.

Use when product or QA needs implemented features as user stories. Generates from code and docs with acceptance criteria.

Snapshot current task state to MemPalace before context compaction. Triggered by PreCompact hook or manually.

Use when reviewing SwiftUI code. Checks best practices, modern APIs, maintainability, and performance.