earchibald

Use when creating features, building components, adding functionality, or modifying behavior - explores user intent, requirements and design before implementation

Use when facing 2+ independent tasks that can be worked on without shared state or sequential dependencies

Use when you have a written implementation plan to execute in a separate session with review checkpoints

Use when implementation is complete, all tests pass, and you need to decide how to integrate the work

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes

Use when receiving code review feedback, before implementing suggestions, especially if feedback seems unclear or technically questionable

Use when completing tasks, implementing major features, or before merging to verify work meets requirements

Use when executing implementation plans with independent tasks in the current session

Expert debugging and profiling for leaks, GPU/Visual Profiler, headless CI QA, orphan nodes, thread-safe logs, and custom Debugger monitors — not print/breakpoint tutorials. Trigger on OBJECT_ORPHAN_NODE_COUNT, ObjectDB growth, Visual Profiler GPU spikes,…

Expert GDScript landmine guidance: static typing opcodes, signal-up/call-down, %UniqueName/@onready lifecycle, Callable bind/unbind, await sequences, typed collections, and safe Dictionary iteration. Use for code review, refactoring hot paths, or project…

Expert blueprint for performance profiling and optimization (frame drops, memory leaks, draw calls) using Godot Profiler, object pooling, visibility culling, and bottleneck identification. Use when diagnosing lag, optimizing for target FPS, or reducing memory…

Expert blueprint for procedural content generation (dungeons, terrain, loot, levels) using FastNoiseLite, random walks, BSP trees, Wave Function Collapse, and seeded randomization. Use when creating roguelikes, sandbox games, or dynamic content. Keywords…

Expert blueprint for data-oriented design using Resource/RefCounted classes (item databases, character stats, reusable data structures). Covers typed arrays, serialization, nested resources, and resource caching. Use when implementing data systems OR…

Expert blueprint for save/load systems using JSON/binary serialization, PERSIST group pattern, versioning, and migration. Covers player progress, settings, game state persistence, and error recovery. Use when implementing save systems OR data persistence.…

Expert testing decision trees for GdUnit4: unit vs scene vs CI gates, headless runners, snapshots, and mock networks. Use when choosing test layers, wiring CI, or validating signals/physics without beginner assert catalogs. Keywords: GdUnit4, GdUnitTestSuite,…

Durable interactive report server with browser+chat interaction -- build HTML pages with forms, serve from a local HTTP server that stays alive for repeated submissions. Agent polls /last-response endpoint. Isolated port range 9100-9199 avoids sibling agent…

Use when sending push notifications via ntfy.sh topics. Sends arbitrary messages with optional title, priority, tags, click URL, and attachments via a single curl call. Also use when the user asks to send a notice, ping, or notification.

Self-terminating interactive report server with dual-channel browser+chat interaction — build HTML pages with forms, serve from a local HTTP server that auto-scans ports and self-terminates on submission. Output arrives in chat via notify_on_complete. Trigger…

Design SVG icons/avatars for AI agents: draft SVG concept variants, render PNGs via rsvg-convert, coordinate multi-agent review via vault, deliver multi-resolution icon sets.

Set up vault-based inter-agent coordination: inbox/broadcast/pool directories, watchdog crons, and webhook notification mesh for multi-agent ecosystems.

Operate the obsidian-projects issue tracker and agent orchestrator system — vault structure, issue lifecycle, agent dispatch, workflow modules, and plugin architecture. Load this when working on or with obsidian-projects issues, agent orchestration, or the OP…

Specialized knowledge for managing multi-environment Railway deployments. Use when: (1) Setting up Railway projects/environments/services, (2) Configuring deployments and builds (NIXPACKS/Railpack/Dockerfile), (3) Managing Railway CLI operations and logs, (4)…

Comprehensive guide for Yoto Smart Stream development - covering both API integration and service operations. Use when developing Yoto applications, integrating with Yoto API/MQTT, or operating the Yoto Smart Stream service.

Comprehensive testing guide for Yoto Smart Stream - covering authentication testing, functional testing, Playwright UI automation, and test-and-fix development loops. Use when writing tests, debugging test failures, or implementing test coverage.

Configure the Claude Code statusline managed by the statusline-plugin. Use whenever the user wants to add, remove, reorder, recolor, or otherwise change segments shown in their statusline — including the first-time install of the runtime into…

Play evolving-rpg in a repeatable, structured way and judge the results against the Covenant — use for any playtesting, balance check, or rule evaluation in this repo.

Use when presenting a wall of information or a multi-choice decision that would overload chat, when the user wants to see HTML/diagrams/wireframes in a browser before deciding, or when they say "let's go web", "report server", "dual-channel", or "interactive…

Run the Obsidian Projects workflow — scaffold new projects, create/work/resolve issues, and maintain schema-conformant notes in an Obsidian vault that follows the Projects schema. Use whenever the user invokes /op:* commands or references an Obsidian project…

Use when building, debugging, or iterating on an Obsidian plugin (TypeScript, `manifest.json` + `main.js`). Covers scaffolding a repo, the build/copy/reload deploy loop, registering commands and events, settings UI, vault I/O, `requestUrl` networking,…

Author, sign, and package macOS Shortcuts as binary plists for distribution as Claude Code plugins. Teaches agents to build production-quality .shortcut files using the full Shortcuts action library.

Run branch hygiene scan — stale branches, divergence, naming violations. Use /loop 30m /sweep for background monitoring.