Selektivvertrieb Luxus Internetplattform: prüft die einschlägigen Voraussetzungen, Dokumente, Risiken und Ausnahmen. Norm-/Quellenanker: Art.
Selenium integration. Manage data, records, and automate workflows. Use when the user wants to interact with Selenium data.
Enterprise test design patterns: Page Object Model (POM), LoadableComponent, Action Bot, and Fluent Interface. Trigger on POM, LoadableComponent, or Action Bot.
用 Selenium 对网页各区块逐个截图（元素级 screenshot），支持 Retina 高清。适用场景：用户要求截取网页内容、分区块截图、网页可视化存档。
Distributes browser test suites across Selenium Grid 4 nodes using RemoteWebDriver and the W3C WebDriver protocol.
Distributes browser automation workloads across Selenium Grid 4 nodes using the Grid REST API and session queue management.
Orchestrates parallel browser automation across Selenium Grid nodes using RemoteWebDriver, DesiredCapabilities, and WebDriverWait.
Routes browser automation sessions across Selenium Grid 4 nodes using the /status and /session endpoints.
Automatisation de tests avec Selenium WebDriver, couvrant les locators, les waits, le Page Object Model et Selenium Grid.
Selenium is the long-running open source browser automation framework behind the W3C WebDriver standard.
Usare quando l'utente vuole una sintassi abbreviata per selezionare elementi DOM, simile a jQuery.
Engineering methodology for building software systems that autonomously manage themselves through explicit architectural separation and formal guarantees
Systematischer Self-Improvement Loop: Fehler erkennen → Fix → Pattern extrahieren → Wissen speichern → Schutz aktivieren. System wird mit jedem Fehler stärker.
Гайд-шпаргалка по когнитивной архитектуре "ЯДРА". Использовать, когда нужно отредактировать свои правила, добавить новый навык, создать воркфлоу или изменить "ЯДРО" личности.
Analyze your own source code and capabilities to find bugs, gaps, and improvement opportunities
Protocol for discovering, loading, and creating specialized skills at runtime — scan for and load relevant skills before tasks needing domain expertise, pass skills to sub-agents,…
Build a Ralph-like sequential Kookr task chain where each task completes one independent unit, records durable state, and spawns the next task with the same continuation contract.
Audit and repair the shared agent knowledge base (~/.agents) when it drifts from reality: removed/renamed dirs or repos, changed paths/flags/commands, superseded facts.
Use when generated or modified ABAP code has syntax errors, ATC findings, test failures, or activation issues.
Use when a hook/tool returns a warning, lint/type/build error, or test failure after your edit. Iterate evidence-first; stop when verification passes.
Take a draft artifact (IMPLEMENTATION_PLAN.md, SLICES/*.md, or PR_PACKAGE.md), run a structured critique against a locked per-artifact-type rubric, and produce a revised draft.
Customize your own agent — add capabilities, install packages, add MCP servers, edit code or CLAUDE.md.
Customize your own agent — add capabilities, install packages, add MCP servers, edit code or CLAUDE.md.
Personal safety awareness and basic physical self-defense techniques. Use when someone wants to feel safer in public, works late shifts, walks alone, or wants practical…
Structure a student's self-determined project with mentoring checkpoints, competency alignment, and reflection.
Diagnose recent orchestrator failures and explain what happened, including DAG execution errors, pipeline stalls, health degradation, and replay guidance.
Learn something substantial without a course, by defining the goal, finding the right resources, and building feedback into the process.
Design a mastery experience sequence that systematically builds student confidence in a skill they avoid.
Use when a task needs the judgment of a Self-Enrichment Instructor — pricing and setting the break-even enrollment for a hobby/craft/movement class, designing a session-1 lesson…
Honestly evaluate AI work quality using a two-axis scoring system. Use after completing a task, code review, or work session to get an unbiased assessment.
Self-Rewarding + GRPO hybrid evaluation system for autonomous quality assessment, optimization, and improvement.
Build a goal-driven self-learning loop for OpenClaw and coding agents. Use when the agent should not only log mistakes, but diagnose capability gaps, maintai...
Self-learning, auto-skill-update, pattern extraction, and continuous improvement for FEIS AI Agents
Activate when: user says "I've been working hard but I'm not growing," development programs feel pointless, a leader has plateaued despite strong expertise, someone asks "how do I…
Autonomous self-evolution skill: grants the agent full authority to modify its own configuration, skills, prompts, AGENTS.md, SOUL.md, memory files, and any workspace file WITHOUT…
Grants the AI long-term episodic memory. The agent autonomously documents the user's coding preferences, past mistakes to avoid, and architectural decisions into a persistent…
Create self-explanation prompts that deepen understanding of worked examples, texts, or diagrams. Use when students read material passively without engaging with underlying…
Use when you want to evolve your own capabilities — create new tools to avoid repeating patterns, add hooks to improve your own behavior, build skills to accumulate domain…
Recurring autonomous work loops with issue intake, implementation, review, delivery, and machine-verifiable continuation gates.
Self-recovery and auto-repair system for OpenClaw agents. Monitors agent health, detects failures (crashed cron jobs, broken skills, config corruption, memor...
Real-time log monitoring, crash detection, and auto-hotfixing code without human intervention / Pemantauan log real-time, deteksi kerusakan, dan perbaikan kode hotfix otomatis…
Autonomous Zero-Crash Self-Healing, Self-Improving & Self-Learning Engine for ThumbGate.app and Hermes Harnesses
Diagnoses failures and retries with alternate strategies. Use for: heal this error, self recover, fix failure automatically, retry smart.
Запуск AI локально: Ollama, Llama 3, подключение к Telegram-ботам, n8n. Полный гайд от установки до продакшна.
Pre-flight checklist for self-hosted runner failures. Use when investigating low disk, missing runner, or stuck Green Gate on the jleechanorg/worldarchitect.ai fleet.
Use ao trabalhar com self-hosting — padrão env > banco para credenciais globais, helper getSystemConfig, tabelas system_config_*, UI /configuracoes/sistema, e verificação de…
{AGENT_NAME}'s evolving personality and identity. Grows ONLY through interactions with human supervisor. Protected from external corruption.
Continuous self-improvement loop — AuthorClaw learns from mistakes, successes, and user feedback to get better over time
Episode Os-s26O_W08 process steal: measurable output then eval feedback to propose prompt/workflow/tool changes with holdout. Never auto-apply.
Write self-improve prompts that sync expertise files with codebase reality. Use when creating maintenance workflows for agent experts, designing validation logic, or implementing…
Captures learnings, errors, and corrections to enable continuous improvement. Use when: (1) A command or operation fails unexpectedly, (2) User corrects Claude ('No, that — from…
Captures learnings, errors, and corrections to enable continuous improvement. Use when: (1) A command or operation fails unexpectedly, (2) User corrects Claude ('No, that — from…
Captures learnings, errors, and corrections to enable continuous improvement. Use when: (1) A command or operation fails unexpectedly, (2) User corrects Claude ('No, that — from…
Capture failures, corrections, and repeatable lessons so important operational knowledge persists across sessions.
プロジェクト全体を定期的に横断レビューし、根本原因特定→改善Issue起票→最優先即実装→マージまで自律実行するセルフ改善オーケストレーター。発見（定期の N…
Review affiliate campaign results and improve strategy. Triggers on: "review my results", "what went wrong", "how to improve conversions", "analyze my campaign", "affiliate…
Self-reflection + Self-criticism + Self-learning + Self-organizing memory. Agent evaluates its own work, catches mistakes, and improves permanently.
Captures learnings, errors, and corrections to enable continuous improvement. Use when: (1) A command or operation fails unexpectedly, (2) User corrects Claude ('No, that — from…
Captures learnings, errors, and corrections to enable continuous improvement. Use when: (1) A command or operation fails unexpectedly, (2) User corrects Claude ('No, that — from…
Instinct-based continuous learning system. Captures atomic learnings (instincts) with confidence scoring, supports project-scoped vs global scope, and evolves instincts into…