home / skills / falkicon / mechanic / s-working

s-working skill

safe

This skill guides you through Mechanic/Fen WoW addon development, providing tooling, context, and best practices for everyday addon work.

npx playbooks add skill falkicon/mechanic --skill s-working

Review the files below or copy the command above to add this skill to your agents.

Files (1)

SKILL.md

2.5 KB

---
name: s-work
description: >
  General-purpose skill for Mechanic/Fen ecosystem work. Covers ecosystem context,
  development tools, component overview, and AFD principles. Use for everyday addon
  work, exploration, or when unsure which specialized skill to use.
  Triggers: work, build, develop, create, mechanic, fen, fencore, fenui, ecosystem, addon.
---

# Fen Ecosystem

Expert guidance for working in the Mechanic/Fen WoW addon development ecosystem.

## The Reload Loop (MANDATORY)

After ANY addon code change, you MUST verify the changes in-game:

1. **Ask** the user to `/reload` in WoW (or trigger via keybinding CTRL+SHIFT+R)
2. **Wait** for the user to confirm the reload is complete
3. **Then** use the `addon.output` MCP tool (agent_mode=true) to get errors, tests, and console logs

> **CRITICAL**: Do NOT call `addon.output` immediately after changes. The timing between reload and SavedVariables sync is unpredictable. Always wait for user confirmation before pulling output.

## Ecosystem Components

| Component | Purpose | Key Tools |
|-----------|---------|-----------|
| **Mechanic** | Development hub | `env.status`, `addon.output`, `reload.trigger` |
| **FenCore** | Pure logic library | `fencore.catalog`, `fencore.search`, `fencore.info` |
| **FenUI** | UI widget library | `Layout`, `Panel`, `Tabs`, `Grid`, `Buttons` |
| **MechanicLib** | Bridge library | `RegisterAddon`, `Print`, `RegisterTest` |

## Essential MCP Tools

| Task | MCP Tool |
|------|----------|
| Get Addon Output | `addon.output` (agent_mode=true) |
| Lint Code | `addon.lint` |
| Run Tests | `addon.test` |
| Search APIs | `api.search` |
| Search FenCore | `fencore.search` |
| Env Status | `env.status` |

## AFD Core Principles

Mechanic follows **Agent-First Development (AFD)** — [github.com/Falkicon/afd](https://github.com/Falkicon/afd)

1. **Tool-First**: All functionality must exist as an MCP tool before being added to any UI.
2. **Structured Results**: All tools return predictable JSON schemas with `success`, `data`, and `error`.
3. **Agent Mode**: Use `agent_mode=true` for distilled, AI-optimized output.

## Routing Logic

| Request type | Load reference |
|--------------|----------------|
| Component details, architecture | [references/components.md](references/components.md) |
| Daily workflows, patterns | [references/workflow.md](references/workflow.md) |
| Quick API reference | [references/quick-api.md](references/quick-api.md) |
| MCP tool reference | [../using-mechanic/references/afd-commands.md](../using-mechanic/references/afd-commands.md) |

Overview

This skill is a general-purpose assistant for development inside the Mechanic/Fen World of Warcraft addon ecosystem. It centralizes guidance for everyday addon work: debugging, testing, performance checks, and navigation of core libraries. Use it when you need a reliable, agent-first workflow or when you are unsure which specialized tool to use.

How this skill works

I guide you through the Mechanic workflow and recommend MCP tools for tasks like getting addon output, linting, and running tests. For code changes I enforce the Reload Loop: ask you to /reload in-game, wait for your confirmation, then run addon.output with agent_mode=true to collect errors and logs. I also map requests to appropriate FenCore, FenUI, and Mechanic tools and return structured, actionable steps.

When to use it

After making code changes to verify behavior and capture runtime errors
When you need to gather logs, run tests, or lint Lua addon code
Exploring FenCore APIs or locating UI components in FenUI
Performing routine performance checks and debugging in-game
When you are unsure which specialized skill or tool to invoke

Best practices

Always perform the Reload Loop: ask user to /reload, wait for confirmation, then call addon.output (agent_mode=true)
Prefer MCP tools first: make functionality available as a tool before adding UI
Expect and parse structured JSON responses with success, data, and error fields
Run addon.lint and addon.test regularly during development
Use fencore.search and api.search to find stable APIs before implementing logic

Example use cases

You changed a widget in FenUI: trigger the Reload Loop, then collect addon.output to see errors and runtime traces
Investigating a logic bug: run fencore.search for functions and use addon.test to run unit checks
Performance regression after a patch: use env.status and addon.output to capture CPU/memory peaks
Building a new addon feature: register core functionality as an MCP tool, then expose a FenUI panel for QA
Quick API lookup: use api.search to find Blizzard API signatures and fencore.info for library details

FAQ

Why must I wait to call addon.output after a reload?

SavedVariables and internal state can lag immediately after a reload. Waiting for your confirmation ensures logs and saved data are synchronized so addon.output returns accurate results.

What does agent_mode=true do?

agent_mode=true requests distilled, AI-optimized output from MCP tools using the AFD conventions, producing predictable JSON suited for automated processing.