为 OpenClaw 配置硅基流动 (SiliconFlow) 作为模型源。SiliconFlow 是国内领先的 AI 模型推理平台，提供 98+ 个 chat 模型，包含多个免费模型（Qwen3-8B、DeepSeek-R1-8B 等）。使用标准 OpenAI 协议（openai-completions）。包含 provider…
Use when executing implementation plans via dispatched subagents with code review between tasks.
Write a HarnessTarget so harness-core can evaluate an existing agent. Use when the user has an openai-agents agent (or any tool-using agent) and wants to wire it into harness-core…
Use Zep as an external context layer for agents that need to store events, assemble temporal graph context, and retrieve relevant memory before model calls.
Use in the BuilderIO/skills repo whenever adding, updating, publishing, documenting, validating, or wiring a public skill.
Implement a new Packmind AI agent rendering/deployer pipeline (single-file or multi-file) with type and registry wiring, frontend UI/docs updates, and thorough unit/integration…
Merge agent-specific tool sets (MCP clients + fetched tools) into the parent context without disrupting the parent’s existing pool.
Use when the user asks to address Gemini review comments, handle gemini-code-assist bot feedback, triage Gemini's automated code review suggestions, or respond to…
Discovers and invokes agent skills. Use when starting a session or when you need to discover which skill applies to the current task.
Discovers and invokes agent skills. Use when starting a session or when you need to discover which skill applies to the current task.
Manage, troubleshoot, configure, analyze, and review AdGuard Home DNS server. Use when working with AdGuard Home, DNS blocking, ad blocking, network-wide filtering, DNS q — from…
Build production-ready AI agents using Google's Agent Development Kit with Claude integration, React patterns, multi-agent orchestration, and comprehensive tool libraries
Diagnose và fix các vấn đề liên quan đến Google ADK agents, tools, session state, multi-agent communication trong dự án MemRAG.
Build RAG (Retrieval-Augmented Generation) agents with Google ADK and Vertex AI RAG Engine. Use when implementing document Q&A, knowledge base search, or citation-backed — from…
Build RAG (Retrieval-Augmented Generation) agents with Google ADK and Vertex AI RAG Engine. Use when implementing document Q&A, knowledge base search, or citation-backed — from…
Diagnose and repair failing MCP servers. Captures real launch tracebacks, identifies stale tool/config references, prunes the bad entries, and reconnects.
Validate live MCP provider health — separate config issues from auth and connectivity failures
Orchestrate teams of agents — DAG execution, routing, state sharing, failure recovery. Use when coordinating parallel agents in task pipelines with dependencies or distributing…
Optimize context usage for the session by reducing bloat, improving token efficiency, and focusing on relevant areas.
Audit corpus distribution by source type and repo; identify coverage gaps and underindexed topics
Manually improve corpus quality by adding missing docs and filling retrieval gaps
Detect and fix stale chunks (files that changed or were deleted since last indexing)
Semantic-search personal knowledge (memory, plans, handoffs, skills, Codex rules) via the local RAG index at ~/.claude/rag-index/.
Use when working with Affinity CRM via MCP tools - find entities, manage workflows, log interactions, prepare briefings, find warm intros.
Vorstandsvertrag AG vorbereiten: §§ 84 ff. AktG, Bestellung und Anstellung trennen, Vergueng (fix, variabel, ESG-LTI), D and O Versicherung, Tantieme Caps nach VorstAG,…
AGB im Anwaltsvertrag und Allgemeine Mandatsbedingungen. Skill klaert die AGB-rechtliche Prüfung typischer Mandatsbedingungen Verguetungsklauseln Verzugsregelungen Versch — from…
AGB im Anwaltsvertrag und Allgemeine Mandatsbedingungen. Skill klaert die AGB-rechtliche Prüfung typischer Mandatsbedingungen Verguetungsklauseln Verzugsregelungen Versch — from…
Branchen-Fachmodul für Formulararbeitsvertrag: prüft typische AGB-Risiken des Vertragstyps und erzeugt Klauselarchitektur, Red Flags und bessere Bedingungen.
AGB im Selektivvertrieb: AGB-Kontrolle §§ 305 ff. BGB im B2B, BGH-Klauselverbote, Verbots- und Konditionsklauseln, MFN-Klauseln nach Coty II, Vertragsstrafe-Bemessung.
Arbeitsvertrags-AGB nach § 310 Abs. 4 BGB. Skill vertieft die AGB-Kontrolle im Arbeitsrecht: Anwendbarkeit der §§ 305 ff.
AGB-Kontrolle im Bankvertrag. Skill behandelt die Banken-AGB Sparkassen-AGB und Allgemeinen Geschäftsbedingungen der Volks- und Raiffeisenbanken Klauseln zu Entgelten Änd — from…
AGB-Kontrolle der VOB-B im Bauvertrag. Skill klaert die BGH-Linie zur AGB-rechtlichen Behandlung der VOB-B insgesamt und einzelner Klauseln.
AGB im Leasingvertrag. Skill klaert AGB-Klauseln in Operating- und Finance-Leasing Verteilung der Sach- und Rechtsgefahr Maengelhaftungs-Drittinanspruchnahme (Drittabtret — from…
AGB Kontrolle Factoringklauseln B2B: prüft die einschlägigen Voraussetzungen, Dokumente, Risiken und Ausnahmen. Norm-/Quellenanker: KWG § 1 Abs. 1a Satz 2 Nr.
AGB im Leasingvertrag. Skill klaert AGB-Klauseln in Operating- und Finance-Leasing Verteilung der Sach- und Rechtsgefahr Maengelhaftungs-Drittinanspruchnahme (Drittabtret — from…
Build or scaffold a fabri multi-agent AI agency from a plain-English business or workflow idea. Use when asked to "build an AI agency for X", "scaffold a specialist team for X",…
Expert photography prompt engineer specializing in crafting detailed, evocative prompts for AI image generation.
Create Claude Desktop skills from descriptions, SOPs, or existing agents. Three modes - create from scratch, convert SOPs to skills, or migrate agents to skill format.
Guide du protocole Agent-to-Agent (A2A) de Google pour l'interopérabilité entre agents IA — découverte, communication et collaboration inter-agents.
Use when an agent task needs done criteria, evidence rules, source rules, tool rules, blocked outputs, and verification before work starts.
Tiered stranger access control for AI agents. Use when setting up contact permissions, handling unknown senders, managing approved contacts, or configuring stranger deflection on…
Track every commitment from assignment to completion, chasing what is late and escalating what is stuck, so work finishes rather than fading.
Design Invocable Apex actions that return deterministic, agent-friendly errors instead of surfacing raw exceptions to the LLM.
Use when designing how an Agentforce agent extracts structured input parameters (slots) from a user's natural-language utterance to invoke an action.
Use when an agent proposes a write, send, deploy, publish, payment, CRM update, permission change, or other side effect.
Use when designing or reviewing Agentforce actions, including Flow actions, Apex invocable actions, prompt-template actions, action naming, input and output contracts,…
Add a new rule, convention, or instruction to the project's agent configuration. Analyzes the rule and helps decide placement: root CLAUDE.md (universal rules), docs/agents/ files…
Query and manage Shipwright agents via the admin API — cron jobs, env vars, tool permissions, API tokens, and plugins.
Observabilité complète pour agents IA — distributed tracing, métriques custom, log correlation et dashboards de supervision.
Expert agent organizer specializing in multi-agent orchestration, team assembly, and workflow optimization.
USE WHEN agent alignment, delegation alignment, agent handoff, multi-agent delegation, agent-to-agent task transfer.
Turn business data into answered questions with agents that define the metric, pull it consistently, check it against a second source, and state what it does not prove.
Use when scaffolding a new AI agent's project folder, or when an existing agent's files (prompt, tools, procedures, scheduled jobs, integrations) are scattered in one directory…
Use when a human reviewer needs the evidence packet for approving, rejecting, or escalating an agent action.
Skill: agent-arena-skill. See SKILL.md body for details. Use when this domain is relevant.
2-layer parallel agent hierarchy. Layer 1 deploys 3-50+ agents, each with independent context. Layer 2 adds 2+ sub-agents per member. No upper limit on either layer.
Use when the user wants to design, build, code, or deploy an AI agent on DataRobot; mentions agent_spec.md, dress rehearsal, the DataRobot agent template, LangGraph, CrewAI,…
Agent assistance skill that provides stuck detection, memory management, and session learning capabilities for AI agents — from general/ai-tooling
Agent assistance skill that provides stuck detection, memory management, and session learning capabilities for AI agents — from majiayu000/claude-skill-registry-data
Validates agent configurations for model selection, tool permissions, focus areas, and approach quality.