Dev & Coding

Splits a task into atomic PRs, builds each in its own git worktree, and loops through CI and bot review gates until merged.

Judges slow, flaky, redundant or brittle tests by the real failure they protect, and trims feedback cost to the smallest verification that covers the risk.

Runs a three-layer, parallel multi-agent review of all unpublished changes before an npm publish and returns a SAFE/CAUTION/RISKY/BLOCK verdict plus a version-bump recommendation.

An evidence-driven skill for finding and safely removing accidental complexity — dead code, duplicate state, redundant layers — within an authorized scope.

An interactive, resumable eight-phase journey that measures, untangles, and speeds up a working-but-slow codebase while logging every decision in docs/.

Official skill that walks you through researching, implementing, testing, and evaluating high-quality MCP (Model Context Protocol) servers in TypeScript or Python.

Convenes each git worktree and PR as its own agent in a shared markdown room, then drives rounds until one consolidation plan emerges.

Maps a codebase into feature-grouped Mermaid flowcharts, hunts duplicated concerns with file:line evidence, and proposes the simplest unified architecture before a refactor.

Typing 'ultrawork' or 'ulw' flips the agent into a strict failing-first, evidence-driven engineering mode with mandatory cleanup receipts.

Triggered by the keyword 'ultrawork' or 'ulw', it forces a failing-proof-first, real-surface-QA, cleanup-receipt workflow before anything can be called done.

Debugs a LazyCodex or upstream Codex CLI defect in a throwaway workspace and ships it as a fork PR or a patch-embedded verified-fix issue.

Strips AI-generated code slop from branch changes category by category — but only after regression tests lock the current behavior.

Splits a task into the smallest mergeable PRs, builds each in its own git worktree with evidence-backed manual QA, then loops on CI and review-bot gates until merged and cleaned up.

Grounds itself in your codebase, asks only the questions exploration can't answer, and after your explicit okay writes one decision-complete work plan a worker can execute with zero follow-up interview.

A 6-phase refactoring protocol: clarify intent, build a codemap, gauge test coverage, plan atomic steps, and verify after every change.

Switches NanoClaw off the OneCLI credential gateway and injects Anthropic API keys or OAuth tokens straight from .env into the agent container.

A step-by-step playbook for tracing NanoClaw agent container failures through host logs, the two session DBs, mounts, and heartbeats.

Routes a NanoClaw agent group to a local Ollama model instead of the Anthropic API via env overrides and a model setting.

Extracts your NanoClaw fork's customizations into a replayable migration guide, then upgrades by reapplying them on a clean upstream checkout — no merge conflicts.

Wires OpenCode (OpenRouter, DeepSeek, Zen, Anthropic) in as a per-group agent backend for NanoClaw instead of the Anthropic Agent SDK.