AstartesSkills

Use when the user asks to report, summarize, audit, or present the implementation result of a plan, roadmap, PRD, engineering plan, refactor plan, migration plan, release plan, or task list. Produces evidence-based completion reports with overall, stage, and module completion percentages; goal-to-result verification tables; explicit concrete engineering benefits; unfinished-work impact analysis; and concrete next actions, using tables and charts instead of vague prose.

Use when the user asks for a software engineering plan, implementation plan, refactor plan, migration plan, rollout plan, bug-fix plan, performance optimization plan, security change plan, DevOps / CI/CD plan, technical execution plan, or review of an existing engineering plan. Produces phased, executable, independently verifiable, reviewable, rollback-aware plans with strict phase gates, plan-to-code completeness, benefit validation, and chain-state logging evidence for software engineering work.

Use when a task needs independent adversarial review during vibe coding, design work, implementation, testing, release planning, documentation, skill creation, or agent workflow design. It uses fresh internal subagents, or a user-approved local CLI reviewer fallback when internal subagents are unavailable, to attack artifact assumptions, happy paths, implementation completeness, target benefit realization, user-perspective usability, failure scenarios, and evidence gaps through formal /vs_review/ reports and mandatory response closure.

Use when Codex needs to design, reorganize, audit, or maintain a repository's documentation system: docs/ directory hierarchy, global vs version-level documents, version PRDs, technical designs, engineering plans, document versioning, naming conventions, link/index management, archive policy, or automated docs structure validation.

Use when debugging medium or large bugs, regressions, flaky failures, production symptoms, repeated failed fixes, or user-explicit requests where the agent must combine persistent /coe case tracking, independent multi-path root-cause investigation, and a hard diagnostic evidence gate before repair design or implementation.

Use when a user brings a new product, feature, app, website, internal tool, automation, workflow, or other product requirement that needs multi-round clarification before implementation. The skill keeps the conversation focused on product logic, user experience, interaction design, rules, edge cases, and acceptance criteria, then writes a Draft or Ready PRD.

Build a maintainable three.js character-animation system with state graphs, clip conventions, retargeting, skeletal reuse, and optional IK. Use when gameplay depends on character or object animation beyond simple clip playback.

Define and enforce a three.js game asset pipeline around glTF/GLB, compression, validation, naming conventions, runtime prefab assembly, and loader setup. Use when importing or normalizing 3D assets for real-time gameplay.

Create or refactor a three.js game runtime into a maintainable project structure with a renderer factory, game loop, resize flow, lifecycle hooks, and service boundaries. Use for new projects or when a demo needs production-grade runtime structure.

Design a device-agnostic input abstraction and camera-control baseline for a three.js game, including keyboard, mouse, pointer lock, gamepad, touch, and mode switching. Use when gameplay input must stay stable across devices and states.

Implement world interaction, picking, triggers, HUD coordination, and world-space UI patterns for a three.js game. Use when scene objects must become robust interactive gameplay entities instead of raw meshes.

Implement custom materials, TSL, procedural shaders, particle systems, and advanced visual effects for a three.js game while keeping WebGL and WebGPU paths explicit. Use when built-in materials are no longer sufficient.

Set budgets and profiling workflows for a three.js game, covering draw calls, memory, lifecycle cleanup, streaming, batching, and CPU/GPU bottlenecks. Use when performance work needs to become systematic rather than reactive.

Design a collision and physics layer for a three.js game, including character movement, collision layers, scene queries, and engine-adapter boundaries. Use when gameplay needs robust contact, blocking, triggers, or rigid-body behavior.

Set a three.js game rendering baseline for color management, PBR, lighting, environment maps, shadows, transparency, and post-processing. Use when visual consistency, performance budgets, and WebGL/WebGPU boundaries need to be defined.

Define save/load, snapshot, replay, and networking boundaries for a three.js game. Use when game state must be serialized, restored, synchronized, or replayed rather than existing only inside the current scene graph.

Route a three.js game-development task to the right specialized skills. Use for planning a full game workflow, upgrading demos into maintainable game codebases, or choosing between runtime, asset, rendering, input, physics, animation, performance, networking, and XR tracks. Do not use for generic non-game three.js pages.

Create a quality workflow for a three.js game with tests, asset validation, visual regression, browser coverage, and release checklists. Use when a project needs repeatable verification rather than ad-hoc manual checking.

Add WebXR support to a three.js game with controller mapping, interaction design, comfort rules, and XR-specific rendering constraints. Use when building or extending a game for VR, MR, or other XR platforms.

Use when the user needs to design, implement, audit, or govern Storybook stories for frontend components, design systems, page states, interaction tests, accessibility checks, visual baselines, or component-driven UI workflows.

Use when a frontend redesign or legacy CSS refactor is blocked by global style pollution, selector collisions, unstable DOM reuse, or the need to migrate a page or module to a new UI without breaking the old system.

Use when the user wants to introduce, package, present, or pitch a repository for investors, users, demos, landing pages, README upgrades, or PR materials. Extract product value, architecture, highlights, risks, and commercialization narratives from repo evidence.

Use when the user wants an internal repository summary that captures architecture, directory responsibilities, core code paths, and code-backed logic evidence so other engineers can understand the project quickly.

Use when the user needs a concise explanation of when this skill should trigger and what it does.