instructa

instructa/viber3d

Cursor rule Cursor

Global Rule. This rule should ALWAYS be loaded.

instructa/viber3d

Cursor rule Cursor

Viber3D Coding Guidelines.

instructa/viber3d

Cursor rule Cursor

React Three Fiber Component Rules.

instructa/viber3d

Cursor rule Cursor

// Standard system pattern export function movementSystem(world: World) { const time = world.get(Time) if (!time) return world.query(Transform, Velocity).updateEach(([t, v]) => { t.position.addScaledVector(v.vector, time.delta) }) }.

instructa/viber3d

Cursor rule Cursor

Write all creation, destruction, or major trait updates in these functions.

instructa/viber3d

Cursor rule Cursor

Cursor rule "005-traits" from instructa/viber3d, covering trait definitions, core practices, examples, relationships and best practices.

instructa/viber3d

Cursor rule Cursor

Utility Function Patterns.

instructa/viber3d

Cursor rule Cursor

Tailwind CSS usage rules for styling (2025 best practices).

instructa/viber3d

Cursor rule Cursor

You are Levin, a specialized software development AI agent. Your primary goal is to fulfill all user stories.

instructa/viber3d

Cursor rule Cursor

PLANNING MODE is used to create stories, specification and update project plans.

instructa/viber3d

Cursor rule Cursor

Use this template to create a new story for tracking in the docs/stories directory.

instructa/viber3d

Cursor rule Cursor

use this ALWAYS to create/update a task in json.

instructa/viber3d

Cursor rule Cursor

Levin Builder Agent.

instructa/agent-skills

Skill Claude CodeCodex

Delegate a bounded task from a Codex session to a Fable-powered Cursor Agent in the same Herdr workspace, then wait for and collect the result. Use when Codex should bring in Fable for an independent read-only review or make Fable the sole writer for an implementation while Codex pauses and reviews afterward. Trigger…

instructa/agent-skills

Skill Claude CodeCodex

Delegate a bounded task from a Codex session to Grok 4.6 with xhigh reasoning in the same Herdr workspace, then wait for and collect the result. Use when Codex should ask Grok for a strong independent opinion, read-only review, architecture or debugging analysis, second opinion, or explicitly authorized…

instructa/agent-skills

Skill Claude CodeCodex

Delegate a bounded task from a Codex session to GPT-5.6 Sol in the same Herdr workspace, then wait for and collect the result. In review mode, require Sol to use parallel GPT-5.6 Terra subagents with medium reasoning for read-only context gathering before Sol makes the final judgment. Use for requests such as "ask…

instructa/agent-skills

Skill Claude CodeCodex

Build, critique, and iterate high-converting marketing or product landing pages using React + Vite + TypeScript + Tailwind and shadcn/ui components, with all icons sourced from Iconify. Use when the user asks for a landing page, sales page, signup page, CRO improvements, above-the-fold vs below-the-fold structure…

instructa/agent-skills

Skill Claude CodeCodex

Live-test any Electron desktop app with native-devtools-mcp, Chrome DevTools Protocol, screenshots, OCR, and accessibility tools. Use when the user asks for Electron UI verification, MCP-driven app control, renderer CDP interaction, native desktop automation, screenshots, or OCR-driven checks.

instructa/agent-skills

Skill Claude CodeCodex

Determine runtime owner, first-fix layer, and canonical long-term module or package owner in layered codebases. Use when placing code across UI vs platform shell vs runtime orchestration vs domain or application vs shared core vs adapter or integration layers, debugging ownership issues, removing duplicate policy…

instructa/agent-skills

Skill Claude CodeCodex

Turn complex, technical, ambiguous, or verbose material into clear language without losing important detail. Use when the user asks to simplify an answer, identify what matters, compare options, recommend an action, or make the next step explicit.

instructa/agent-skills

Skill Claude CodeCodex

Decide where durable test coverage belongs and clean up temporary test probes. Use while testing a bug fix or architectural change, or before finishing work that added tests, fixtures, snapshots, diagnostics, or temporary assertions. Select one owning layer, reuse canonical suites, merge unique signal, and remove…

instructa/agent-skills

Skill Claude CodeCodex

Find duplicate ownership, hidden second sources of truth, and contract drift in layered codebases. Use when reviewing normalization, validation, defaulting, canonicalization, persistence mapping, runtime-vs-durable state, duplicated helpers, query or cache ownership, or any "who owns this rule?" architecture question.…

instructa/agent-skills

Skill Claude CodeCodex

Enforce a hard-cut cleanup policy: keep one canonical implementation and delete compatibility, migration, fallback, adapter, coercion, and dual-shape code. Use for pre-release or internal-draft refactors where the goal is one final shape, especially when changing schemas, contracts, persisted state, routing…

instructa/agent-skills

Skill Claude CodeCodex

Performs root-cause-first debugging and review by tracing expected behavior to the first unintended side effect before changing contracts, parsing, or types. Use when debugging protocol errors, deserialization failures, null payloads, missing fields, restore or hydration issues, state-ownership bugs, unexpected…