Ingeniero de software autónomo. Controla VS Code, terminal e instala dependencias.
Используй только когда пользователь явно просит запустить Codex Project Autopilot, продолжить проект из .codex-agent или в текущем workspace уже есть активный .codex-agent.
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…
5-phase repeatable structure for autonomous agent sessions: context-load, tiered work-selection, coordination claim, execute, and persist-learning.
Walk a user through configuring an unattended core-agent — single-agent monitor or multi-agent team. Use when the user asks to "set up an autonomous agent", "run core-agent…
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…
Elevates the AI from a single-threaded agent into a Swarm Director. Teaches the agent how to break down complex tasks and autonomously invoke and orchestrate multiple subagents in…
Persistent task queue system. Users add tasks at any time via natural language; tasks are stored in a single persistent queue file and executed asynchronously via subagents.
Autonomous UI inspection using a dual channel: (1) visual screenshots via Playwright MCP tools, (2) numeric layout metrics via Puppeteer scripts.
Autonomous job discovery and execution loop. Scans for open jobs, evaluates them against safety guardrails, and executes the full reserve-claim-complete lifecycle without human…
Design or run a long-lived allowlisted worker plus watchdog for multi-hour agentic work without human babysitting.
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.
Hand a multi-day job to your agent and walk away — for real. You set the rails once (what it can touch, what it can never touch, how long it runs, what pulls it back to you), then…
Core autonomy protocol for Vilona (BerkahKarya AI GM). Defines how Vilona operates 24/7 without human prompts
Evaluate whether an autonomous, always-on, scheduled, headless, or self-evolving workflow is ready to run safely.
Time-windowed autonomous task queue. Autonomy works only during specific time windows (e.g., 8 AM - 8 PM UTC), while cron jobs run overnight.
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。
Decide which of your recurring rituals to put on autopilot — and which to keep manual. Use when asked what to automate, how to set up recurring AI runs, which reports or briefings…
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…
Self-modifying AI agent configuration via ruler + MCP + DuckDB. All behavior mods become one-liners.
Post-mortem analysis for incidents — timeline reconstruction, 5 Whys root cause, action items
Für Verl-003 · Autor, Herausgeber, Mitwirkende: Rechtekette im Sammelwerk: ordnet Norm, Beweislast und Gegenargument; Ergebnis: Prüfprodukt mit Risiko und nächstem Schritt.
Für Autorenkommunikation: Compliance-Dokumentation und Aktenvermerk: ordnet Akte, Belege und Lücken; Ergebnis: Prüfprodukt mit Risiko und nächstem Schritt.
Schreibt freundliche, klare Autor:innenkommunikation fuer Nachforderungen, Korrekturen, Freigaben, Rechtefragen, Fristen und Eskalationen.
Für Verl-026 · Autorenkündigung, Bestseller und Nachvergütung: ordnet Norm, Beweislast und Gegenargument; Ergebnis: Prüfprodukt mit Risiko und nächstem Schritt.
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.
Autenticação e autorização na API da Tray. Utilize quando o desenvolvedor precisar implementar o fluxo OAuth 2.0, gerar chaves de acesso (access_token), renovar tokens expirados…
Run the autorun pipeline in DRY_RUN mode against a fixture spec and assert each expected artifact landed.
AUTOSAR Classic SWC expert that operates in five modes: (1) Component design — decompose a feature into SWC types (Application / Sensor-Actuator / Service / CDD / Composition),…
See the main Infrastructure Sizing skill for comprehensive coverage of right-sizing and autoscaling strategies.
Design autoscaling on the right metric with velocity controls, warm capacity, and flap prevention. Use when configuring autoscaling or diagnosing oscillation, lag, and cost spikes…
AutoScraper — scraping web automático con IA, aprende patrones de selección y extrae datos sin código.
Werken met de Autotask REST API in JUICT-projecten — authenticatie via Azure Key Vault (met lokale env-var fallback), base URL/zone, geverifieerde endpoints, env vars, data…
Use when instrumenting with trace/span/track, reviewing code for logging and observability patterns, converting console.log to wide events, adding structured errors, setting up…
Run one iteration of the automated chess-training parameter-tuning loop. Propose a parameter change, run a time-limited training run, analyze results vs.
One eval-tune round. Applies approved fixes, selects tasks, runs eval, analyzes results, and updates loop state.
Use when after AutoTuner has completed EICparams extraction and parameter estimation on raw untargeted metabolomics data (mzML, mzXML, or CDF format), and you need to pass those…
Automatically update Clawdbot and all installed skills once daily. Runs via cron, checks for updates, applies them, and messages the user with a summary of what changed.
Top-of-stack autonomous shipping orchestrator. One invocation handles the full goal-audit→plan→execute→code-council→ship loop, or routes trivial work directly to /ship quick.
Automatic exploratory data analysis and visualization with a single line of code - generates comprehensive charts, detects patterns, and exports to HTML/notebooks
Создаёт и настраивает компонентные приложения на фреймворке Autumn (ОСень) для OneScript с DI и аннотациями.
Создаёт консольные приложения с командами и подкомандами на autumn-cli для OneScript. Использовать при CLI на OneScript, командах приложения, аргументах и опциях.
Descobre e documenta endpoints HTTP dos três produtos AUVP (Finanças, Analítica e Comunidade) usando Scrapling, para implementar tools no MCP mcp-auvp.
Audio/video studio production — multi-track editing, color grading, motion graphics, compositing, live streaming, screen recording, YouTube publishing.
Submit software to antivirus vendors to prevent false positive detections. Use when releasing new software that triggers AV warnings, submitting binaries for whitelisting, or…
Guide for using Ava's MCP tools effectively for task management and progress reporting. Use when working with Ava MCP server to report progress on coding tasks, including starting…
AVADA Commerce integration. Manage data, records, and automate workflows. Use when the user wants to interact with AVADA Commerce data.
How schedules, weekly rules, date overrides, travel schedules, and out-of-office entries combine to determine when someone is bookable.
How the booking system works: checking availability, managing booking links, configuring availability settings, and the public booking URL pattern.
Assist with Avalanche C-Chain transactions, AVAX transfers, subnets, and cross-chain bridges.
Use when working with health check, rates, or making API calls to https://avalara.augur-api.com.
Estrutura avaliação de impacto e RIPD para solução de IA em serventia, documentando tratamento de dados, necessidade, proporcionalidade, decisões automatizadas, riscos,…
Analisa viabilidade, risco, manutenção e licenciamento de uma dependência externa antes de adotá-la. Use quando o arquiteto avalia incluir uma nova biblioteca ou serviço de…