MadAppGang/magus

agent-model

Picks the browser-use agent brain LLM per task. Use when choosing a model for retry_with_browser_use_agent or a cloud session, or the user mentions a cheap, slow, or smart model.

原文の言語: 英語

tui

Build, review, or debug OpenTUI terminal UIs — React JSX or core constructs, Yoga flexbox, gradient meters, colour screenshots. Any Bun/TypeScript TUI. Only Bun is tested; Node/Deno at own risk.

原文の言語: 英語

statusline-customization

Configuration reference and troubleshooting for the statusline plugin — sections, themes, bar widths, and script architecture

原文の言語: 英語

release

Release one or more Magus plugins. Infers the version bump from git history, bumps plugin.json and marketplace.json, commits, and after the PR merges tags the merge commit with one explicit ref per tag; CI gates the PR and publishes the dist repos. Use…

原文の言語: 英語

claudish-usage

Runs models through the claudish MCP tools — team, create_session, run_prompt — and resolves model IDs against the live catalog. Use when the user mentions claudish, OpenRouter, or external AI models.

原文の言語: 英語

deep-analysis

Audits a codebase across seven dimensions, from architecture to code health, scoring each finding with evidence. Use for a full codebase review, tech-debt assessment, or post-incident analysis.

原文の言語: 英語

investigate

Routes a code investigation to one of four modes — bug, test gap, architecture, implementation — and runs the query sequence that mode needs. Use when asked to investigate, trace, or debug code.

原文の言語: 英語

search

Finds code by meaning, structure or exact text, then reads only the spans returned. Use when searching a codebase, locating a symbol, tracing callers, or about to open three or more files.

原文の言語: 英語

browser-use-integration

Detects the browser-use@magus plugin and captures screenshots of URL-based references. Use when designer agents need browser screenshot capture and claude-in-chrome is unavailable.

原文の言語: 英語

design-references

Provides design system references — Material 3, Apple HIG, Tailwind UI, Ant Design, Shadcn/ui. Use when reviewing UI against an established design system.

原文の言語: 英語

review-services

Judges a screen with an external vision model resolved live via claudish, and detects the project's review services (axe, Lighthouse, Percy, Chromatic, Applitools). Use when judging a design or a screenshot.

原文の言語: 英語

ui-analyse

Reviews a UI screenshot — usability, WCAG, design-system consistency, design-vs-implementation diff. Prompting patterns, depth tiers and severity guidelines. Analysis only; pair with dev:frontend-implement to apply.

原文の言語: 英語

context-detection

Detects the project stack from its config files, then names the one or two dev skill files to read for this task — it loads none of them. Use at the start of any coding task, or on an unfamiliar or multi-stack repo.

原文の言語: 英語

aggregate-reviews

Merges independent reviews of one target into one report with a consensus tag per finding and a verdict from supplied thresholds; also synthesises research findings. Use when several reviews or votes must become one file a gate reads.

原文の言語: 英語

team-gate

Runs a multi-model review gate to a verdict: start the claudish team panel with input_file only, poll until settled, read every ballot, apply the minimum ballot count, log every skip. Use at any plan-review, code-review, verify or fix gate.

原文の言語: 英語

testing-strategies

Testing pyramid, AAA structure, test doubles, fixtures, assertions and coverage targets, in any language. Use when writing, reviewing or setting up tests. Do not use for the write-test-first loop — that is test-driven-development.

原文の言語: 英語

universal-patterns

Code organization, error handling, data flow, naming and anti-patterns in any language. Use while writing or reviewing everyday code. Do not use to choose a system shape or a design pattern — read the architecture skill instead.

原文の言語: 英語

systematic-debugging

Root-cause debugging — reproduce, localize, explain, verify — with depth routing and a technique catalogue for stack traces, wolf fence and data-flow tracing. Use when anything errors, crashes or misbehaves, even on a bare pasted trace.

原文の言語: 英語

plugin-sdk-patterns

Patterns and templates for building Claude Code plugins. Use for plugin development — creating a plugin, skill and agent templates, plugin architecture, or standardizing structure.

原文の言語: 英語

ui-playwright

Writes Playwright UI tests — role locators, page objects, fixtures, network stubs, snapshot policy, one test per Storybook story state. Use when testing a screen, component, or user flow in a browser.

原文の言語: 英語

madbench-evals

Authors, runs and debugs madbench benches natively — bench YAML, checks, metrics with module/, red-state testdata, the two controls, exit codes; drafts an upstream issue instead of a wrapper. Use when writing, reviewing or debugging any bench.

原文の言語: 英語

agent-enforcement

Multi-agent orchestration enforcement for /team command. Validates session directory paths and ensures /team Tasks use a valid agent from the routing whitelist. Use when debugging /team orchestration failures.

原文の言語: 英語

error-recovery

Handle errors, timeouts, and failures in multi-agent workflows. Use when dealing with external model timeouts, API failures, partial success, user cancellation, or graceful degradation.

原文の言語: 英語

hierarchical-coordinator

Prevents goal drift in long multi-agent runs by validating outputs against the original objective at checkpoints. Use when orchestrating 3+ agents or multi-phase work.

原文の言語: 英語

hooks-system

Lifecycle hook patterns — PreToolUse, PostToolUse, UserPromptSubmit, Stop, SubagentStop. Use when configuring hooks, writing validation, auto-format on save, stdin payloads, exit-2 blocking, or debugging a hook.

原文の言語: 英語

multi-agent-coordination

Coordinate multiple agents in parallel or sequential workflows. Use when running agents simultaneously, delegating to sub-agents, switching between specialized agents, or managing agent selection.

原文の言語: 英語

multi-model-validation

Runs the same task across multiple AI models in parallel and aggregates verdicts. Use when the user wants a second opinion, multi-expert validation, or consensus from Grok, Gemini, GPT-5, or Kimi.

原文の言語: 英語

performance-tracking

Track agent, skill, and model performance metrics for optimization. Use when measuring agent success rates, tracking model latency, analyzing routing effectiveness, or optimizing cost-per-task.

原文の言語: 英語

quality-gates

Implement quality gates, user approval, iteration loops, and test-driven development. Use when validating with users, implementing feedback loops, classifying issue severity, running test-driven loops, or building multi-iteration workflows.

原文の言語: 英語

session-isolation

Use when orchestrating workflows that generate multiple files (designs, reviews, reports) to prevent file collisions across concurrent or sequential sessions with unique session directories.

原文の言語: 英語

terminal-interaction

Slot-addressed tool patterns for interactive terminal access. Use when running interactive commands, starting dev servers, watching tests, querying databases, or working beside the user.

原文の言語: 英語

tui-navigation-patterns

Provides key sequences and navigation patterns for common TUI apps. Use when navigating vim, nano, htop, less, psql, lazygit, k9s, tig, btop, or sending keystrokes to a database shell.

原文の言語: 英語

go-tui

Build, review, or debug Go terminal UIs with the Charm stack — Bubble Tea, Lip Gloss, Bubbles, ntcharts. Use for any Go TUI, dashboard, or full-screen CLI, including colour-accurate screenshots.

原文の言語: 英語

framework-signals

Provides pass/fail/running/idle output markers for 15+ test, build, and deploy tools. Use when monitoring terminal output for jest, vitest, pytest, go test, cargo, webpack, vite, or vercel.

原文の言語: 英語

tdd-workflow

Drives a Red-Green-Refactor state machine for TDD with terminal test watchers. Use when running TDD in watch mode or iterating on failing tests with jest, vitest, cargo watch, or pytest-watch.

原文の言語: 英語

workspace-setup

Orchestrates tmux workspaces — dashboards, watch/entr monitors, one command on many hosts — on numbered helper slots. Use for a multi-pane dashboard, an ambient monitor, a command across hosts, or a startup script for the user.

原文の言語: 英語

bunjs-architecture

Provides Bun.js clean architecture patterns — routes/controllers/services/repositories, camelCase conventions, Prisma schemas. Use when designing layered Bun.js apps or planning structured workflows.

原文の言語: 英語

bunjs-production

Provides Bun.js production patterns — Docker, AWS ECS/Fargate, Redis caching, security hardening, CI/CD. Use when deploying or operationalizing a Bun.js service.

原文の言語: 英語

index-skills

Walks every skill reachable from this project and writes a browsable markdown index, plus a small deterministic index spliced into CLAUDE.md. Explicit invocation only — run /setup:index-skills.

原文の言語: 英語

skill-authoring

Writes and reviews SKILL.md files for this repo — a description that triggers, a body that fits, and a visibility choice that does not starve a preload consumer. Use when adding, editing or auditing any skill. Not for commands or agents.

原文の言語: 英語