Retrieve real-time hardware metrics from Apple Silicon Macs using mactop's TOON format. Provides CPU, RAM, GPU, power, thermal, network, disk I/O, and Thunderbolt bus information.
Four-step Claude + Codex collaboration for producing artifacts (code, drafts, analyses). Independent drafts → cross-review → revisions → merge.
Decompose a design document into ordered milestones, then generate idea.md files for each using agent teams
Execute the implementation plan by processing and executing all tasks defined in tasks.md — from tmalcolm-0607/mad-council-claw
Execute the implementation planning workflow using the plan template to generate design artifacts — from tmalcolm-0607/mad-council-claw
Create or update the feature specification from a natural language feature description — from tmalcolm-0607/mad-council-claw
MadKudu integration. Manage data, records, and automate workflows. Use when the user wants to interact with MadKudu data.
Use when brainstorming ideas, generating raw material, or starting the creative phase of a writing project.
Use when creating a Markdown Architectural Decision Record in MADR 4.0 format. — /docs:madr, \"MADR 작성\", \"결정 사항 기록\
Analyze current session for architectural decisions and generate/update mADR documents
Navigate Madrid as visitor, resident, tech worker, student, or entrepreneur with neighborhoods, transport, costs, safety, and local insights.
Операционный навык для слоя изменений ветки в MADSpec. Использовать, когда нужно инициализировать базовую точку сравнения ветки, предложить, показать, применить, экспортировать…
Операционный навык для слоя контрольных проверок в MADSpec. Использовать, когда нужно показать статус через `madspec gate status`, объяснить блокировку перехода, выполнить…
Операционный навык для межветочного сравнения, подготовки предложений на слияние, разрешения конфликтов и продвижения знаний на уровень проекта через `madspec memory ...`.
Операционный навык для жизненного цикла проектных правил в MADSpec. Использовать, когда нужно показать, предложить, применить, объяснить или проверить проектные правила через…
Diagnóstico de madurez IA de la participada y clasificación bajo EU AI Act. Identifica casos de uso (producto y operaciones), evalúa datos, gobierno, sesgo, transparencia.
Erstellt Mängelanzeige, Abnahmeprotokoll oder begründete Abnahmeentscheidung aus Vertrag und dokumentierter Prüfung.
Für Verl-011 · Mängelexemplare, Remittenden und Preisbindung: ordnet Norm, Beweislast und Gegenargument; Ergebnis: Prüfprodukt mit Risiko und nächstem Schritt.
Maengelhaftung: Verhandlung, Vergleich und Eskalation: Maengelhaftung: Verhandlung, Vergleich und Eskalation.
HOAI-Praxis: ordnet Mangelanzeige, Frist, Ersatzvornahme, Dokumentation und Gewährleistung; für Architekten, Ingenieure, Bauleiter, Bauunternehmen, Anwälte, Sachverständige und…
Norm- und Dogmatik-Skill für Mängelrechte 309: prüft die AGB-Kontrolle quellenstreng entlang BGB §§ 305 bis 310 und ordnet Rechtsfolge, Risiko und bessere Fassung.
Für Mängelrechte Paragrafen 633 und 634 BGB: ordnet Norm, Beweislast und Gegenargument; Ergebnis: Prüfprodukt mit Risiko und nächstem Schritt.
Prüft Mängelrechte im Werk- und Bauvertrag vor und nach Abnahme, bestimmt Erfüllungs- oder Abrechnungsstadium, Beweislast und Rechtsbehelf und erstellt eine konsistente…
Prüft Untersuchungs- und Rügeobliegenheit, offene/verdeckte Mängel, Rechtzeitigkeit und Rechtsverlust.
Maestra integration. Manage Organizations, Users. Use when the user wants to interact with Maestra data.
Orchestrate long-horizon Maestri agent teams with hook-backed mission state, shared notes, worktree isolation, validation loops, and autonomous continuation.
Investigate why a Maestro mobile test on the iOS Simulator failed. Use after a mobile/simulator test fails and you need the cause.
Capture iOS Simulator screens via Maestro to compare the app against design references. Use when you want screenshots of the mobile app.
Use to plan mobile end-to-end and smoke tests with Maestro — critical device flows on emulator/simulator, resilient to timing, covering happy path plus key error and…
Auto-repair loop for failing Maestro mobile tests on the iOS Simulator, one flow at a time. Use when you want mobile/simulator tests fixed automatically.
Author Maestro YAML flows — selectors, gestures, assertions, app launch/state setup.
Onboarding guiado do Sistema Maestro. Apresenta o sistema, configura o projeto e orienta os primeiros passos.
Conductor agent pattern that decomposes complex tasks, dispatches specialist sub-agents, manages dependencies, and synthesizes results into a unified deliverable.
Run the app's mobile UI tests on the iOS Simulator with Maestro. Use when you want to run mobile tests on a simulator.
View and change Maestro toggles (terse, frontier, context-bar, discipline) via the settings CLI
Configura a barra de status do Maestro no terminal. Toggle on/off inteligente: se desligada liga com defaults, se ligada oferece desligar ou configurar.
Use when improving Maestro token efficiency, Codex fit, benchmark context hygiene, or agent orientation without weakening verification quality.
Provides validation, setup guidance, and a local test harness simulator to run skills within the Microsoft Agent Framework (MAF).
Analyzes and retrieves catalog information from Magento 2. Use when analyzing product catalogs, retrieving catalog data, assessing catalog health, or optimizing catalog…
Analyzes order data and order processing in Magento 2. Use when analyzing orders, retrieving order information, assessing order processing performance, or troubleshooting order…
Conducts comprehensive Magento 2 performance analysis and optimization. Use when analyzing performance bottlenecks, profiling applications, optimizing database queries, or…
Write safe, fast SQL in Magento 2 — Select builder, placeholders, batch ops, transactions, composite indexes, db_schema.xml best practices, whitelist, and MySQL 8 / MariaDB…
Maggy is a local AI engineering command center bundled with claude-bootstrap. AI-prioritized inbox across issue trackers (GitHub Issues/Asana), one-click TDD execute with iCPG…
Commit the current change set with optional drift backfill (sprint mode) or as a generic Conventional Commits commit (standalone mode).
Execute the next undone task(s) from a sprint's TASKS.md by dispatching the magi-developer subagent (Sonnet by default). Updates WORKS.md as a development log.
Enforce engineering rigor and verification loop for coding tasks using multi-agent debate
Review the current git diff and produce DRIFT.md when a sprint context exists. **Mandatory before /magi.commit in sprint mode** — DRIFT.md is required input for the commit step's…
Run a multi-CLI MAGI review of a sprint's PLAN.md / SPEC.md. **Optional step** — can be skipped to save tokens if you trust the plan; human review of the doc is a valid…
First-run onboarding wizard for magi-workflow. Runs healthchecks on installed CLIs (claude/gemini/codex), records the user's preferred reviewer roster and weights into…
Decompose a confirmed PLAN.md or SPEC.md into a TASKS.md milestone+checklist file in the same docs/-/ folder. Coordinator-only — does not write production code.
Headless / walk-away mode. Two modes — fresh (`/magi.yolo ""`) creates a new sprint and runs the full pipeline; resume (`/magi.yolo --resume`) continues an existing…
AI-powered animation tool for creating motion in logos, UI, icons, and social media assets.
magic-api 国产接口快速开发框架。通过 Web UI 编写脚本自动映射为 HTTP 接口，无需 Controller/Service/Dao。Use when 需要API集成、接口对接、Webhook配置、系统连接时使用。不适用于逆向工程闭源API。适用于独立开发者、企业团队和自动化工作流场景。
Building Informer Apps with local Vite development. Covers the dev/publish workflow, the centerpiece "Accessing Your Dependencies" model (typed slots + three patterns), and the…
Turn ideas into fully formed designs through collaborative dialogue. Do NOT write any code until the user approves the design.
Autonomous inbox agent. Scores emails, drafts replies, archives noise, Slack summaries. Uses Gmail + Calendar + Slack + your context.
Evaluates Magic Model (Triangle) frameworks for BlackBelt coaches using Ed Dale's frameworks. Produces Facebook-ready feedback comments.
Replace unexplained literal values with named constants that carry their meaning, without over-formalizing the obvious. Use when a bare number or string encodes a rule.
Write a comprehensive plan to fix bugs with TDD tasks. Every step has real code, no placeholders.
Write a comprehensive plan to implement new features with TDD tasks. Every step has real code, no placeholders.