zigrivers

Work the project's Beads task queue end-to-end - claim a bead, build in an isolated worktree, verify, review, merge, close, report. Use when the user says "/work-beads", "/work-beads 5", "work the next N beads", "work on <bead-id>", "pick up some open tasks", or asks to work the backlog. Applies to every coding agent (Claude Code, Codex, OpenCode, Antigravity, Cursor, Grok).

Work the project's Beads task queue end-to-end - claim a bead, build in an isolated worktree, verify, review, merge, close, report. Use when the user says "/work-beads", "/work-beads 5", "work the next N beads", "work on <bead-id>", "pick up some open tasks", or asks to work the backlog. Applies to every coding agent (Claude Code, Codex, OpenCode, Antigravity, Cursor, Grok).

Static reference for scaffold pipeline ordering, dependencies, and phase structure. Use ONLY for questions about pipeline design, step ordering, or dependency constraints — NOT for status, progress, or "what's next" queries (those go through scaffold-runner).

Interactive wrapper for the scaffold CLI that surfaces a pipeline step's decision points before executing it and manages the step lifecycle. Use when the user asks to run a scaffold step ("run scaffold <step>", "scaffold <step>", "what's next?"), to start building, or works in a project with a .scaffold/ directory.

Static reference for scaffold pipeline ordering, dependencies, and phase structure. Use ONLY for questions about pipeline design, step ordering, or dependency constraints — NOT for status, progress, or "what's next" queries (those go through scaffold-runner).

Interactive wrapper for the scaffold CLI that surfaces a pipeline step's decision points before executing it and manages the step lifecycle. Use when the user asks to run a scaffold step ("run scaffold <step>", "scaffold <step>", "what's next?"), to start building, or works in a project with a .scaffold/ directory.

Run multi-model code review with the MMR CLI (`mmr review`) before merging or finishing a change, or a multi-model design critique (`mmr critique`) of a design doc, plan, or proposed approach before building it. Use when the user asks to review code, a PR, a diff, or staged changes, or to critique/second-opinion a design or approach.

Run multi-model code review with the MMR CLI (`mmr review`) before merging or finishing a change, or a multi-model design critique (`mmr critique`) of a design doc, plan, or proposed approach before building it. Use when the user asks to review code, a PR, a diff, or staged changes, or to critique/second-opinion a design or approach.

Static reference for scaffold pipeline ordering, dependencies, and phase structure. Use ONLY for questions about pipeline design, step ordering, or dependency constraints — NOT for status, progress, or "what's next" queries (those go through scaffold-runner).

Interactive wrapper for the scaffold CLI that surfaces decision points, manages pipeline execution, and provides a seamless scaffold workflow inside Claude Code.

Static reference for scaffold pipeline ordering, dependencies, and phase structure. Use ONLY for questions about pipeline design, step ordering, or dependency constraints — NOT for status, progress, or "what's next" queries (those go through scaffold-runner).

Interactive wrapper for the scaffold CLI that surfaces decision points, manages pipeline execution, and provides a seamless scaffold workflow inside Claude Code.

Use the local AI stack for a second opinion on the current git diff or project state

Create or validate a plan, then delegate execution to the local multi-agent stack

Check whether the local AI stack endpoints and MCP bridge are working

Use when a user describes a Surface UI audit, capture, explain, backlog, validate, gate, status, next-step, or trace intent in natural language and needs it mapped to the correct surface CLI or MCP command with confirmation before action.

Static reference for scaffold pipeline ordering, dependencies, and phase structure. Use ONLY for questions about pipeline design, step ordering, or dependency constraints — NOT for status, progress, or "what's next" queries (those go through scaffold-runner).

Interactive wrapper for the scaffold CLI that surfaces decision points, manages pipeline execution, and provides a seamless scaffold workflow inside Claude Code.

Behavioral guidelines to reduce common LLM coding mistakes. Use when writing, reviewing, or refactoring code to avoid overcomplication, make surgical changes, surface assumptions, define verifiable success criteria, and stay transparent on multi-step work.

Use whenever the user wants to generate a 2D image, a 3D game asset, prepare a 3D asset for 3D printing, run a model bake-off, inspect or upscale textures, or submit jobs to the two-machine queue on their local pipeline. Auto-detects the active project (Unity, Unreal, or any directory with a .asset-pipeline.json config) and routes outputs into that project's assets/ folder. Falls back to ~/3d-pipeline/workspace/ when run outside any project. Reads ~/3d-pipeline/.config to detect the hardware tier (laptop vs studio) and behaves accordingly. Triggers on requests like "generate a 3D model from this image", "make me a 2D concept", "create a 3D asset for my game", "convert this image to 3D", "prepare this for 3D printing", "make an STL for my Snapmaker", "compare SF3D vs SPAR3D", "run a benchmark", "upscale this texture", "queue this job on the other Studio", or any mention of SF3D, SPAR3D, TRELLIS.2, FLUX, Z-Image, mflux, Real-ESRGAN, concept art, or the Snapmaker U1. Handles text-to-2D (mflux), 2D-to-3D (SF3D /

Provides pipeline ordering context for the scaffold prompt pipeline. Auto-activates when users ask about scaffolding sequence, which command to run next, or pipeline ordering.