Prüft Pauschalreise, Reisemangel, Abhilfe, Minderung, Kündigung, Schadensersatz und Entschädigung.
This is the required documentation for agents operating on the CloudBase Relational Database through MCP.
Relay messages to AI agents on any OpenAI-compatible API. Supports multi-turn conversations with session management. List agents, send messages, reset sessions.
Bump a plugin's version across all three host manifests (.claude-plugin, .cursor-plugin, .codex-plugin), draft a changelog entry, and prepare a release commit + tag.
Rentenantrag, Fristen und Startdatum: Antragstellung, Rückwirkung, fehlende Unterlagen, Online-/Papierweg und Zuständigkeitsfragen im Rentenpruefer.
Developer machine tool for replicating plugin source code between local project repositories. Use when you want to push plugin updates from agent-plugins-skills to a cons — from…
Audit and standardize a repository's agent-readable context, including AGENTS.md, CLAUDE.md, WARP.md, CONTRIBUTING.md, .agents/skills, and specs/ PRODUCT.md and TECH.md contracts.
Workflow pattern standards for creating multi-agent orchestrations including YAML frontmatter (name, description, tags, status, agents, parameters), execution phases…
Establish or audit a structural quality contract for any agent-operated engineering repository: app, library, CLI/tool, plugin, harness, or meta repo.
Use when finishing code changes, preparing review, or validating agent-produced work with concrete evidence instead of only saying it is done.
(ePost) Use when you need a full codebase overview, repo summary, or are unfamiliar with a repository structure
Transform messy prompts into well-structured, effective prompts — single or multi-agent. Use when: "reprompt", "reprompt this", "clean up this prompt", "structure my prompt",…
Use when Codex needs to diagnose, resolve, review, or document recurring agent incidents: subagent reward-hacking patterns, unsupported success claims, skipped validation, stale…
Design and run an agent-native, evidence-settled prediction market — the trust model (who proposes, trades, settles), the propose→open→settle lifecycle, machine-measurable…
Multi-agent dispatcher skill. Main agent acts as a pure coordinator — chatting with users and delegating all real work to 5 persistent sub-agents via round-robin scheduling with…
Polls IMAP inbox every 60 seconds, parses replies to agent-sent emails, dispatches actions to downstream agents.
Rates responses and plans against quality rubrics. Used for plan validation, response quality audits, and multi-agent consensus. — from oimiragieo/agent-studio
Rates responses and plans against quality rubrics. Used for plan validation, response quality audits, and multi-agent consensus. — from majiayu000/claude-skill-registry
Builds adaptive web interfaces using Flexbox, CSS Grid, and media queries with a mobile-first approach.
Run GitHub Agentic Workflow jobs behind a domain allowlist and optional API-key sidecar instead of giving repository agents broad outbound access.
Toolkit für Impulsvorträge zu Krisenfrüherkennung und StaRUG: Foliensatz-Gliederung, Talking-Points, juristische Kernbotschaften, Q-und-A-Fallnetz, Formathinweise für…
Agrégation et synthèse des résultats de multiples sous-agents en un résultat cohérent. Se déclenche avec "agréger résultats", "fusionner résultats", "combiner outputs", " — from…
Interactive setup wizard for retroscope retrospective reports. Creates or updates ~/.claude/retroscope.json and .claude-plugin/retroscope.json.
Stratégies de retry intelligentes pour sous-agents qui échouent — backoff, fallback, alternatives et recovery.
How to build and maintain a parameterized Personal Prompt Library in Raycast, Obsidian, or TextExpander to save 30 minutes of typing every day.
Use Hunk to keep a live terminal review UI open for agent-authored code changes, with Git, Jujutsu, Sapling, patch input, watch mode, and inline agent annotations.
Preferred agent harness patterns when not otherwise specified by the project. TRIGGER when you notice you or another agent had trouble completing work quickly and correctly and…
Review recent Claude Code and Codex sessions for the current project and propose improvements to the global and project AGENTS.md files, plus cleanup of Claude's auto memory.
Detect agentic coding infrastructure in a project: CLAUDE.md, AGENTS.md, installed skills, MCP servers, hooks, and cross-tool compatibility (Claude Code and Codex CLI).
AI-agent compatibility audit. Use when evaluating whether code changes are safely readable, analyzable, and modifiable by AI agents.
Review-3 (FULL) — final adversarial review of the BUILT product via a multi-agent fan-out assuming every feature is broken until a re-run check proves it (reconciliation,…
Review bounded MCP tool schemas, names, descriptions, action annotations, initialize capabilities, elicitation modes, and portable JSON Schema edge cases.
Use when a supervisor, swarm, graph, planner-worker system, or parallel agent workflow needs review for task boundaries, shared state, branch joins, retries, cancellation, context…
Capture and inspect file reads, writes, and shell activity from coding agents so developers can audit what actually happened after a session goes sideways.
Use Performance Studio when an MCP-compatible agent needs to parse SQL Server .sqlplan files, surface performance warnings, inspect missing-index suggestions, and turn…
Use when reviewing API changes, API design, technical docs, developer experience, or repo changes through junior engineer, senior engineer, platform engineer, and AI-agent…
Working playbook preloaded into the reviewer helper; the coach updates its Lessons after each round. Use only when acting as reviewer or coaching it.
Use when the user wants to review AI-agent instruction files (CLAUDE.md, skills, drift-log, hooks) for pollution, duplication, dead references, contradictions, or architectural…
Run supervised multi-agent reviews with the revmux CLI, report or act on findings, and re-review fixes.
rhwp 를 MCP 서버(mcp-serve)로 에이전트 호스트에 붙이고 세션·무상태 도구를 고르는 통합 규약입니다. .mcp.json 등록, 세션 도구(hwp_open→hwp_doc_*→hwp_close)와 무상태 도구의 선택 기준, resources(스키마·레시피·문서) 소비, capabilities --mcp 가…
RIC operating rules for coding agents. Use for any ric-skills or ric workspace task to enforce skill retrieval, Windows PowerShell preference, non-destructive execution,…
教大模型使用 Ridge 终端内置的 MCP server 在多个终端 pane 之间调度、派发任务给 teammate agent。当你运行在 Ridge/rdg 里（环境变量含 RIDGE_TEAMMATE_URL / RIDGE_TEAMMATE_TOKEN），需要拆分 pane、把子任务委派给其它 pane 的 agent、跨 agent…
Risk analysis using risk registers, probability/impact matrices, and mitigation planning. Identifies, assesses, and manages project, business, and technical risks with structured…
Calculate portfolio risk metrics including VaR, CVaR, Sharpe, Sortino, and drawdown analysis. Use when measuring portfolio risk, implementing risk limits, or building ris — from…
RITA — Österreichische Registerdaten (Firmenbuch, ÖNACE-Branchen, Bilanzen, AG-Veröffentlichungen, Kollektivverträge, Vereinsregister, EU-MwSt) als MCP-Tools.
Knowledge Curator agent skill for the RLM Factory. Auto-invoked when tasks involve distilling code summaries, querying the semantic ledger, auditing cache coverage, or maintaining…
Agent-powered RLM cache distillation. Replaces the slow local Ollama distiller with the agent's own summarization capability for both rlm_summary_cache.json and…
Agent-powered RLM cache gap-fill orchestration. Audits the cache, generates a Markdown task list, and spawns a Sub-Agent to read missing files, write summaries, and inject them…
Lebenszyklus einer Rulemap-Norm: Versionierung; Änderung im Builder per Drag-and-Drop; Evaluation nach NKRG und GGO; Wirkungskontrolle; Rueckkopplung aus dem Vollzug.
Lebenszyklus einer Rulemap-Norm: Versionierung; Änderung im Builder per Drag-and-Drop; Evaluation nach NKRG und GGO; Wirkungskontrolle; Rueckkopplung aus dem Vollzug.
Quick start guide for creating MCP servers with the rmcp crate - installation, concepts, and first server
Agent-agnostic PR review skill. Reviews a pull request diff and emits a structured 3-state verdict (APPROVE / REQUEST_CHANGES / UNCERTAIN).
Problem solving using Fishbone (Ishikawa) diagrams and 5 Whys technique. Identifies root causes systematically and recommends corrective actions.
Systematically trace bugs backward through call stack to find original trigger. Use when errors occur deep in execution and you need to trace back to find the original trigger.
Deep pre-execution analysis framework using four philosophers (Socrates, Aristotle, Feynman, Drucker) for structured critical thinking before implementing plans.
Multi-agent debate council — spawns 3 specialized sub-agents in parallel (Scholar, Engineer, Muse) for Round 1, then optional Round 2 cross-examination to challenge assum — from…
Use Shepherd Model Gateway to route OpenAI, Anthropic, Responses API, embeddings, and MCP tool traffic across self-hosted and cloud model backends with cache-aware policies and…
Use Plano when an agent application needs an out-of-process data plane for multi-agent routing, model agility, guardrails, traces, and OpenAI-compatible traffic instead of custom…
Run Claude Code through Claude Code Router to route coding-agent requests by task, provider, or model while preserving terminal workflows and adding provider-specific…
Run a local proxy that lets Codex and Claude Code use configured LLM providers, routed models, and account pools while keeping the normal coding-agent workflow.