Save Money

Auto-detect task complexity for Claude models (Haiku + Sonnet). Route simple tasks to Haiku, escalate complex ones to Sonnet. Save 50%+ on API costs. | 適用 Claude 模型（Haiku + Sonnet），自動偵測任務難度，簡單用 Haiku，複雜升級 Sonnet，輕鬆省下 50% 以上的費用。— RULES: Before responding, classify the task. If it matches an escalation trigger, call sessions_spawn with the full task and model anthropic/claude-sonnet-4-20250514 IMMEDIATELY. Do NOT answer complex tasks yourself. ESCALATE: analysis, comparisons, planning, strategy, c

Agent manager

Manage Clawdbot agents: discover, profile, track capabilities, define routing hierarchy, and assign tasks. Use when: (1) Listing available agents, (2) Profiling agent capabilities and communication methods, (3) Defining agent routing (can_assign_to, reports_to, escalation_path), (4) Assigning tasks to appropriate agents, (5) Tracking agent performance and completed work, (6) Updating agent registry after changes.

One Skill To Rule Them All

Security auditing skill that detects malicious patterns like prompt injection, data exfiltration, obfuscation, and privilege escalation in OpenClaw SKILL.md...

Curriculum Generator

Intelligent educational curriculum generation system with strict step enforcement and human escalation policies

Customer Service Reply

客服回复模板。售前咨询、售后处理、退换货、投诉回复、好评引导、升级处理、行业FAQ、满意度挽回。Customer service reply templates for pre-sale, after-sale, returns, complaints, escalation, FAQ generation, s...

Alerts

Smart alerting patterns for AI agents - deduplication, routing, escalation, and fatigue prevention

opus

Auto-route tasks to the cheapest Claude model that works correctly. Three-tier progression: Haiku → Sonnet → Opus. Classify before responding. HAIKU (default): factual Q&A, greetings, reminders, status checks, lookups, simple file ops, heartbeats, casual chat, 1-2 sentence tasks. ESCALATE TO SONNET: code >10 lines, analysis, comparisons, planning, reports, multi-step reasoning, tables, long writing >3 paragraphs, summarization, research synthesis, most user conversations. ESCALATE TO OPUS: archi

Message

Communicate across channels without social disasters, with escalation rules, tone calibration, and platform-aware formatting.

Anti Panic Protocol

Handle tool failures under pressure with bounded retries, clean user communication, and safe escalation. Use when commands/tools fail, when repeated retries...

Dual Thinking

Second-opinion consultation plus automatic skill-engineering escalation for reviews, rewrites, hardening, weak-model optimization, packaging, testing, and pu...

consensus-permission-escalation-guard

Pre-execution governance for IAM and permission escalation changes. Use when an agent or workflow proposes granting, expanding, or assuming higher privileges...

Compliance Qa

Compliance-specific Q&A with regulatory interpretation guardrails, source attribution, confidence scoring, and escalation triggers when context is insufficie...

MidOS Memory Cascade

Auto-escalating multi-tier memory search that cascades from in-memory cache through SQLite, grep, and LanceDB vector search to find the best answer with mini...

Call Center

Handle customer calls with scripts, issue resolution, escalation protocols, and interaction logging.

Stigmem

Persistent federated memory for OpenClaw agents — boot handshake, handoff, decision, and escalation surfaces backed by a Stigmem node.

Chatbot Designer

Design customer service chatbot conversation flows for ecommerce — order status, returns, product recommendations, and escalation rules — that reduce ticket...

Save Money 4.2.0

Auto-detect task complexity for Claude models (Haiku + Sonnet). Route simple tasks to Haiku, escalate complex ones to Sonnet. Save 50%+ on API costs. | 適用 Cl...

Polymarket Macro Crypto Geopolitics Trader

Trades the lag between geopolitical escalation markets and crypto price threshold markets on Polymarket. When Iran military action probability rises, BTC thr...

Polymarket Macro Fear Index Trader

Builds a custom fear index from ALL Polymarket markets by aggregating geopolitical escalation, falling crypto, extreme weather, and rising disease signals in...

Aftersale Sop

Provides standardized after-sales procedures covering returns, complaints, escalation, service recovery, compensation, quality metrics, and team training mat...

Skill Mcp Security Audit

Perform a security audit of MCP servers to detect data exfiltration, command injection, permission escalation, and supply chain vulnerabilities before use.

Umnix constitution for ai agents

Defines, manages, and enforces AI agent constitutions detailing mandates, permissions, prohibitions, performance, escalation, and succession protocols for go...

Openclaw Self Heal

Autonomously diagnose and fix OpenClaw system errors affecting UI, channels, gateway, memory, or pairing, escalating only if needed.

Alert Triage

Normalize and classify alerts by urgency, trust, and audience to decide send-now, batch-later, ignore, suppress-as-duplicate, or escalate actions.

Escalation Brief Writer

把复杂问题整理成升级说明，减少来回追问，突出背景、影响、已尝试和诉求。；use for escalation, support, brief workflows；do not use for 省略关键信息, 把个人情绪写成事实.

Bot Police

Detect, investigate, and contain malicious or compromised bots using behavior analysis, policy enforcement, and escalation protocols.

HengshuiClaw

Activate HengshuiClaw mode — a衡水-style pressure escalation system for AI coding agents. Use when you want the AI to push harder, exhaust every solution befor...

Incident.io

Manage incidents via the incident.io REST API. Create, view, update, escalate, and resolve incidents. Check severities, statuses, and post incident updates....

aurora-norfolk

produce a practical 3-day northern lights planning and live-update workflow for tim in dereham, norfolk, with alert-day escalation, north norfolk coast compa...

Cell Schema Generator

Generate a complete, valid CellOS YAML schema from a plain-text description of a team or organization, including roles, scope, escalation, and coordination d...

notify

Delivers user notifications with optimized channel, timing, formatting, batching, and escalation to prevent spam and ensure clarity.

Supabase Security Audit

Audit a Supabase + Vercel project for RLS coverage, privilege escalation, cross-customer data leaks, anonymous exposure, magic-link flow correctness, and HTT...

ReefWatch

Continuous local security monitoring daemon for Linux and macOS. Detects brute-force attacks, malware, privilege escalation, suspicious processes, file tampe...

Voice Care Speaking Day Plan

Builds a general, non-medical speaking-day routine for hydration, pacing, warmups, breaks, and recovery, with clear escalation for pain, voice loss, breathin...

Commitment Escalation Architect

Design commitment escalation sequences and detect when consistency pressure is being used against you. Use this skill when planning onboarding sequences, act...

Customer Service Escalation Kit

Provides structured workflows to clarify issues, build evidence timelines, draft calm messages, and prepare follow-ups for refunds, disputes, and escalations...

Demora

Use the Demora OpenClaw plugin for dementia-friendly companionship, medication reminders, caregiver escalation, Weixin intervention, and voice-safe patient r...

Ocean Desk

Backend human-agent desk infrastructure for OceanBus brand agents. Not customer-facing — used by brand agents to escalate to human operators. Responds to -hu...

Yoder Skill Auditor

The definitive security scanner for OpenClaw skills. 18 security checks including prompt injection detection, download-and-execute, privilege escalation, cre...

Smart Model Switching

Auto-route tasks to the cheapest Claude model that works correctly. Three-tier progression: Haiku → Sonnet → Opus. Classify before responding. HAIKU (default): factual Q&A, greetings, reminders, status checks, lookups, simple file ops, heartbeats, casual chat, 1-2 sentence tasks. ESCALATE TO SONNET: code >10 lines, analysis, comparisons, planning, reports, multi-step reasoning, tables, long writing >3 paragraphs, summarization, research synthesis, most user conversations. ESCALATE TO OPUS: archi

Browser Ladder

Climb the browser ladder — start free, escalate only when needed. L1 (fetch) → L2 (local Playwright) → L3 (BrowserCat) → L4 (Browserless.io for CAPTCHA/bot bypass).

Escalate

Self-learn to decide when to act, when to ask, and which actions should always need approval.

Professional Communication

Write effective professional messages for software teams. Use when drafting emails, Slack/Teams messages, meeting agendas, status updates, or translating technical concepts for non-technical audiences. Triggers on email, slack, teams, message, meeting agenda, status update, stakeholder communication, escalation, jargon translation.

Invoice Chaser

Automated invoice follow-up sequences that escalate from friendly to firm. Track unpaid invoices, send timed reminder emails with escalating tone, log payment interactions, and generate AR aging reports. Your agent handles the awkward conversations so you don't have to — preserving cash flow and client relationships while you focus on actual work. Configure invoice tracking, email templates per stage (friendly → firm → final notice), timing rules, and let your agent chase payments 24/7. Use when

PagerDuty

Manage PagerDuty incidents, services, schedules, escalation policies, users, and on-call data - powered by ClawLink.

ACC Error Memory

Error pattern tracking for AI agents. Detects corrections, escalates recurring mistakes, learns mitigations. The 'something's off' detector from the AI Brain series.

Historical Cost Analyzer

Analyze historical construction costs for benchmarking, trend analysis, and estimating calibration. Compare projects, track escalation, identify patterns.

Smart Model Routing for Z.AI

Auto-route tasks to the cheapest z.ai (GLM) model that works correctly. Three-tier progression: Flash → Standard → Plus/32B. Classify before responding. FLASH (default): factual Q&A, greetings, reminders, status checks, lookups, simple file ops, heartbeats, casual chat, 1–2 sentence tasks, cron jobs. ESCALATE TO STANDARD: code >10 lines, analysis, comparisons, planning, reports, multi-step reasoning, tables, long writing >3 paragraphs, summarization, research synthesis, most user conversations.