skills/react/SKILL.md
React 18/19 patterns and anti-patterns — hooks discipline, component architecture, state management
npx skillsauth add xoai/sage reactInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
Layer 2 — Framework Pack
React-specific patterns and anti-patterns for React 18/19. Hooks discipline, component architecture, state management, and the mistakes agents make from stale training data.
React is the framework where LLM training data is most polluted. Fifteen years of blog posts, Stack Overflow answers, and tutorials mix class components with hooks, lifecycle methods with effects, Redux boilerplate with context, and pre-React-19 patterns with post-React-19 patterns. An agent trained on all of this produces code that "works" but uses outdated idioms.
This pack corrects the most common stale-training-data mistakes and establishes the modern React mental model as the baseline for all React code in the project.
| Type | Files | Coverage | |------|-------|----------| | Patterns | 7 | Component composition, hooks discipline, state management, data fetching, error boundaries, forms, testing | | Anti-patterns | 6 | useEffect abuse, derived state in useState, prop drilling, index keys, class components, inline object props | | Constitution | 1 | 5 React-specific principles |
When nextjs is also installed, it overrides the data-fetching and
routing patterns from this pack, since Next.js handles those differently
(server components, App Router).
development
Branch-per-initiative git discipline for all delivery workflows. Defines branch naming by workflow, the propose-confirm creation protocol, dirty-tree and detached-HEAD handling, the always user-gated merge protocol, worktree support for parallel sessions, and abandonment cleanup. Activates only in git repositories — silently inactive everywhere else. Use when starting /build, /fix, /architect, or /build-x at Standard+ scope, when resuming an initiative, when offering a merge at a completion checkpoint, or when the user wants a second concurrent initiative.
development
Drives task-by-task execution from an approved plan with quality gates between each task. Reads the plan, finds the next incomplete task, dispatches implementation, validates, updates progress, and continues. Use after a plan is approved and the user says "go", "start building", "execute the plan", or "implement the feature".
testing
Preserves and restores context across agent sessions using plan file checkboxes as source of truth. Use when starting a new session, resuming previous work, ending a session, or when the user says "continue from last time", "what was I doing", or "save progress".
tools
Captures agent mistakes, corrections, and discovered gotchas so they are not repeated. Use when: (1) a command or operation fails unexpectedly, (2) the user corrects the agent, (3) the agent discovers non-obvious behavior through debugging, (4) an API or tool behaves differently than expected, (5) a better approach is found for a recurring task. Also searches past learnings before starting tasks to avoid known pitfalls. Activate alongside the sage-memory skill — they share the same MCP backend but serve different purposes (sage-memory = codebase knowledge, sage-self-learning = agent mistakes and gotchas).