This skill should be used when the user asks to "make a game", "build a game", "generate a game", or wants to generate or update a complete Godot game from a natural language description. --- # Game Generator — Orchestrator Generate and update Godot games from natural language. ## Capabilities Read each sub-file from `${CLAUDE_SKILL_DIR}/` when you reach its pipeline stage. | File | Purpose | |------|---------| | `visual-target.md` | Generate reference image anchoring art direction | | `decomposer.md` | Decompose game into a development plan (`PLAN.md`) | | `scaffold.md` | Design architecture and produce compilable Godot skeleton | | `asset-planner.md` | Decide what assets the game needs within a budget | | `asset-gen.md` | Generate PNGs (xAI Grok) and GLBs (Tripo3D) from prompts | | `rembg.md` | Background removal guide — read before any rembg operation | | `android-build.md` | Android APK export — read when user requests an Android build | ## Pipeline ``` User request | +- Check if PLAN.md exists (resume check) | +- If yes: read PLAN.md, STRUCTURE.md, MEMORY.md -> skip to task execution | +- If no: continue with fresh pipeline below | +- Generate visual target -> reference.png + ASSETS.md (art direction only) +- Decompose into tasks -> PLAN.md +- Design architecture -> STRUCTURE.md + project.godot + stubs | +- If budget provided (and no asset tables in ASSETS.md): | +- Plan and generate assets -> ASSETS.md + updated PLAN.md with asset assignments | +- For every task in PLAN.md: | +- Set `**Status:** pending` | +- Fill `**Targets:**` with concrete project-relative files expected to change | (e.g. scenes/main.tscn, scripts/player_controller.gd, project.godot) | inferred from task text + scene/script mappings in STRUCTURE.md | +- Show user a concise plan summary (game name, numbered task list) | +- Find next ready task (pending, deps all done) +- While a ready task exists: | +- Update PLAN.md: mark task status -> in_progress | +- Skill(skill="go
This skill should be used when the user asks to "set up OpenClaw", "get started", "onboard me", "plan my setup", or "help me choose channels". Conducts an interactive interview, then generates a tailored deployment plan.
Restructure and review engineering documents with source-fidelity-first rules. Preserve original meaning and useful source form, avoid adding new facts or forced decisions, and keep issue/risk-first feedback. Use for design docs, refactor plans, migration plans, PR narratives, and runbooks.
Use when you have a written plan and want it reviewed for architecture, scope, and test coverage before execution. Use when the user says "review this plan", "autoplan", "check my plan", "is this plan solid", or before running superpowers:executing-plans or superpowers:subagent-driven-development.
Use inside the plan plugin when the user wants to execute an existing implementation plan, continue from the authoritative Linear issue plan, or resume work after leaving Plan mode. Consumes the slim `plan-authority/1` pointer from the routed Linear issue plus the canonical linked-document `tracked-plan/1`, requires valid authority, tracked-plan, and plan-event helpers before execution, updates only tracked-plan runtime state, and appends validated progress events instead of inferring authority from chat.
Converts a Lousy Agents spec or master plan into a structured Beads (bd) dependency graph of epics and tasks. Use when asked to 'convert plan to issues', 'create beads from spec', 'populate beads', 'plan to graph', or 'break down spec into tasks'.
Multi-agent development workflow using Agent Teams. Supports five modes: plan (architect teammate + PM teammate debate → plan.md), dev (developer teammate + code-tester teammate + qa-tester teammate + reviewer teammate iterate → code), full (plan → approval gate → dev), auto (plan → dev, no gate), and bugfix (tester + developer + reviewer TDD triad → fix + PR). Use when tasks benefit from collaborative agent teammates with peer messaging.
