Analyze any codebase or workflow and recommend specific automations — hooks, skills, MCP servers, cron jobs, and agent pipelines.
Executes approved shell commands, manages backups, and safely retrieves secrets from Bitwarden.
Create and maintain automation scripts and modules for pilot workflows and integrations. Use when automating repetitive tasks, integrating APIs, or generating reliable, repeatable…
Sets guidelines for creating or modifying automation scripts within the project.
Front door for agent automation — decide the SHAPE (Workflow vs ATM vs skill), then hand off. Triggers: "build automation", "convert skills to workflows", "which shape".
Core QA engineering mindset for test planning and prioritization. Use when analyzing what to test, designing test cases, prioritizing by risk, or determining coverage strategy.
Klausel-Spezialskill für Automatische Verlängerung: prüft, redlined und entwirft die Klausel mit Risikoampel, Verbraucher-/B2B-Unterscheidung und praxistauglicher Ersatzfassung.
Prüft installierte Community-Skills auf Updates. Zeigt einen vollständigen Diff und erfordert eine explizite Genehmigung vor der Anwendung.
Erläutert das Verbot ausschließlich automatisierter Einzelentscheidungen nach Art. 22 DSGVO, Ausnahmen, Einwilligungserfordernisse und konkrete Anwendungsfälle in Kanzleien wie…
Erklärt vollständig automatisierte Verwaltungsakte, Plausibilitätsfehler, Datenbasis und Widerspruch.
Automattic WordPress Remote MCP connects MCP clients to live WordPress sites using OAuth, JWT, or application passwords.
Automerge CRDT for Git-like branching, independent editing, and automatic merge of agent state without a central server.
Automizy integration. Manage data, records, and automate workflows. Use when the user wants to interact with Automizy data.
Эксперт AutoML. Используй для automated machine learning, hyperparameter tuning и model selection.
Author, validate, and migrate Claude Code autoMode blocks at the project level. Models the four official autoMode sections (environment, allow, soft_deny, hard_deny — all arrays…
Configure trusted infrastructure entries for the auto mode classifier — GitHub orgs, internal domains, and hosting providers.
Expert guidance for writing automotive manufacturing business processes, work instructions, and standard operating procedures.
Expert guidance for writing automotive manufacturing business processes, work instructions, and standard operating procedures.
Automox integration. Manage data, records, and automate workflows. Use when the user wants to interact with Automox data.
Set the Claude Code session title from the conversation — a rename only, with no task snapshot and no memory write.
Prüft autonome Lieferroboter im öffentlichen Raum: Verkehrsrecht, Sondernutzung, Haftung, Datenschutz und kommunale Genehmigungen.
Transforma agentes IA de seguidores de tarefas em parceiros proativos que antecipam necessidades e melhoram continuamente.
Self-initiated autonomous actions. Profile setup, content creation, and proactive tasks.
Kerangka kerja untuk mengubah model bahasa menjadi agen AI otonom yang mampu merencanakan, mengeksekusi, dan memverifikasi tugas di lingkungan sandbox.
Panduan komprehensif untuk mengubah diri Anda menjadi autonomous agent yang dapat merencanakan, mengeksekusi, dan memperbaiki tugas secara mandiri menggunakan Antigravity di PC.
Design patterns for building autonomous coding agents, inspired by [Cline](https://github.com/cline/cline) and [OpenAI Codex](https://github.com/openai/codex).
Design patterns for building autonomous coding agents. Covers tool integration, permission systems, browser automation, and human-in-the-loop workflows.
Assess a codebase's readiness for autonomous agent development and provide tailored recommendations. Use when asked to evaluate how well a project supports unattended agent…
Autonomous agents are AI systems that can independently decompose goals, plan actions, execute tools, and self-correct without constant human guidance.
Autonomous PyWry application building using LLM sampling, elicitation, and progress reporting.
Ensures Claude verifies both local tests AND remote CI before claiming completion. Use BEFORE any completion claims, commits, or pull requests.
Build autonomous coding agents with CLI integration. Use when creating automated coding workflows, managing multi-session development, or building CI/CD code generation pipelines.
Use when delegating coding, PR review, or implementation work to external coding-agent CLIs such as Claude Code, Codex, or OpenCode from Hermes.
Full autonomous execution from idea to working code — from yeaight7/agent-powerups
Autonomes Fahren und Strassenrecht: § 1d StVG, autonomes Fahren in Level 4, Genehmigung der zustaendigen Landesbehoerden, Betrieb auf festgelegter Strecke.
Use to enable safe one-shot autonomous execution for an approved slice. Defines the pre-approved command list, the auto-continue rules, and the human-confirmation boundary so the…
Автономное выполнение git операций — коммит, пуш, обновление конфигов без лишних вопросов
Use when starting any work session - establishes autonomous operation mode, overriding token limits and time pressure to work until goal is achieved — from general/general-misc
Autonomous homelab operations using OODA loop (Observe, Orient, Decide, Act) - use when reviewing system state, planning autonomous actions, or investigating operational issues
Use when user requests autonomous operation across multiple issues. Orchestrates parallel workers, monitors progress, handles SLEEP/WAKE cycles, and works until scope is — from…
Otonom PR yasam dongusu. PR olustur, CI bekle, hata varsa duzelt, review feedback'i uygula, merge'e hazirla.
Use to perform an end-to-end PR review and reach an approve/request-changes verdict — including verifying acceptance criteria, running E2E tests via browser automation, resolving…
Use when user wants to execute long-running tasks. Trigger phrases: "autonomous", "自主執行", "long-running task".
Meta-skill que busca de forma óptima en el ecosistema nuevas skills, las adapta al flujo de trabajo del usuario, las almacena en un directorio Vault centralizado y prepara la…
Autonomous UI inspection using a dual channel: (1) visual screenshots via Playwright MCP tools, (2) numeric layout metrics via Puppeteer scripts.
Build and operate the "Autonomous Workflow Authoring for supply chain resilience" capability for supply chain resilience.
Build and operate the "Autonomous Workflow Authoring for urban planning and mobility" capability for urban planning and mobility.
Review an agent workflow for where it may act autonomously, where it must ask, and where human approval is required.
Autonomous session-orchestration loop. Chains session-start → session-plan → wave-executor → session-end for N iterations with kill-switches (SPIRAL, FAILED wave, carryover > 50%,…
autopilot design 阶段需求探索专用。在写设计文档前通过逐个澄清问题理解用户意图，提出 2-3 方案让用户选择，输出共识总结到 brainstorm.md 后交回主 skill。当 autopilot skill 在 design 阶段委托调用时使用。
Run an autonomous /loop iteration -- check progress, work on next task, schedule next wake
Use when the user wants to check the campaign operations autopilot — see health scores for active campaigns, auto-corrections taken, current guardrails, and campaigns needing…
Self-producing skill system combining ruler enforcement with skill self-evolution. Implements trifurcation-first imperative via nbb sexp invocation for idempotent agent…
Post-mortem analysis for incidents — timeline reconstruction, 5 Whys root cause, action items
Schreibt freundliche, klare Autor:innenkommunikation fuer Nachforderungen, Korrekturen, Freigaben, Rechtefragen, Fristen und Eskalationen.
AI email auto-responder — monitors inbox, drafts context-aware replies, never sends without approval
Auto Review closeout. Codex review is the default when no engine is set and is the recommended reviewer.
Run the autorun pipeline in DRY_RUN mode against a fixture spec and assert each expected artifact landed.
See the main Infrastructure Sizing skill for comprehensive coverage of right-sizing and autoscaling strategies.
Run one iteration of the automated chess-training parameter-tuning loop. Propose a parameter change, run a time-limited training run, analyze results vs.