reality-skill

Reality Skill

Reality Skill turns attractive screens into usable product workflows. It does not ask "does this look like an app?" It asks "can the intended user complete the job, recover from problems, and trust what the UI claims?"

Use this skill aggressively whenever a request says app, tool, dashboard, portal, editor, workflow, CRUD, form, checkout, onboarding, settings, upload, export, invite, generate, sync, connect, save, publish, deploy, analyze, or review.

Command Interface

Use references/command-interface.md.

Primary commands:

reality --audit [target]
reality --fix [target]
reality --build [brief-or-target]
reality --harden [target]
reality --judge [target]
reality --verify [target]
reality -e --audit [target]

Short flags:

• -a, --audit: find dead actions, fake data, missing states, weak workflows.
• -f, --fix: make the smallest workflow-real implementation.
• -b, --build: build the real workflow model while creating a new app surface.
• --harden: add durability, recovery, validation, accessibility, and edge-state coverage.
• -j, --judge: score the app against the reality gates.
• --verify: prove the primary workflow by tests, build checks, and browser checks when possible.
• -e, --economy: skip live judge agents and use deterministic checks plus local review.

Default mode:

• Existing UI target: --fix.
• New app brief: --build.
• Review-only request: --audit.

First Action

Load steps/step-00-command-router.md.

Step 00 parses the command, discovers project shape, loads only the needed references, and routes to audit, fix, build, harden, judge, or verify.

Core References

Load only what the task needs:

• references/command-interface.md: grammar, mode precedence, output contracts.
• references/reality-gates.md: the twelve gates that define "not demoware."
• references/app-archetypes.md: workflow expectations for dashboards, CRUD, editors, checkout, AI tools, integrations, onboarding, settings, and auth-like surfaces.
• references/implementation-playbook.md: concrete patterns for data models, actions, state machines, validation, persistence, optimistic updates, undo, and honest mocks.
• references/truth-boundaries.md: how to represent sample data, unavailable services, auth, payments, exports, AI, analytics, and integrations without lying.
• references/verification-playbook.md: build, test, browser, persistence, accessibility, responsive, and smoke-test proof.
• references/judge-system.md: reality judge protocol and scoring gates.