complex-task-methodology
A structured three-step methodology evaluating task complexity from quick rule checks to deep planning and phased execution with quality control for diverse...
semantic-router
让 AI 代理根据对话内容自动选择最合适的模型。四层识别（系统过滤→关键词→指示词→语义相似度），四池架构（高速/智能/人文/代理），五分支路由，全自动 Fallback 回路。支持 trigger_groups_all 非连续词组命中。
deep-memory
One-click clone of a production-grade semantic memory system: HOT/WARM/COLD tiered storage + Qdrant vector DB + Neo4j graph DB + qwen3-embedding. Enables cro...
brand-marketing-workflow
Structural documentation for the brand-marketing-workflow skill. Use when the user wants to understand, audit, or review the workflow design without exposing...
openclaw-guardian-suite
一键安装包含配置安全、容灾、监控和上下文优化的 OpenClaw 系统全链路守护套件。
skill-safe-install-l0
L0 级技能安全安装流程。触发“安装技能/安全安装/审查权限”时，强制执行 Step0-5（查重→检索→审查→沙箱→正式安装→白名单）。
config-preflight-validator
OpenClaw 配置预校验工具。在执行 config.patch 或修改 openclaw.json 前进行本地 Schema 验证，提供具体的错误字段描述。
heartbeat-ollama-guard
Switch OpenClaw heartbeat model to local Ollama and deploy a guard to prevent unauthorized changes, avoiding paid cloud token usage.
halfmoon82-brand-marketing-workflow
端到端品牌营销自动化工作流。从品牌输入到营销内容生产、竞品分析、 效果评估的完整闭环。支持小红书/微博/抖音多平台内容生成。
config-modification
Enforces a two-layer guarded process for modifying critical JSON config files with immediate syntax checks and periodic health validation to prevent faulty c...
gateway-auto-rollback
Automatic configuration rollback mechanism for OpenClaw Gateway. Provides three-layer protection: pre-modification backup, post-modification validation, and...
skill-priority-setup
Scans installed skills, suggests L0-L3 priority tiers, and auto-configures skill injection policy. Use when: setting up skill priorities, optimizing token bu...
web-intel
网络搜索与信息提取统一入口。整合 content-extraction、Jina Reader、Firecrawl、web-access CDP。自动选最经济工具链。可被 BMW（brand-marketing-workflow）、wealth 子代理等直接调用。
model-failover-doctor
Diagnose and fix OpenClaw "All models failed" errors by detecting invalid model IDs, provider mismatches, and session fallback issues with optional auto-repair.
multi-agent-team-by-halfmoon82
Set up and manage 2–10 agent dev teams with customizable roles, workflows, multiple parallel teams, and auto-assigned AI models for collaborative software de...
skill-trigger-v2
Framework-only skill trigger reference. Runtime matching implementation has been removed from the published artifact.
skill-quick-index
Build a wide-trigger, precise-match index for local OpenClaw skills (L1-L3), then quickly route by intent/category/keywords.
openclaw-health-audit
OpenClaw 系统健康审计与自动修复 — 监控 prompt 体积、Cron 合规、Session 清理、Token 消耗
model-usage-monitor
监控并统计模型调用次数和成本，计算缓存命中率，支持实时监控与每小时自动告警。
content-extraction
OpenClaw-native executable content extraction skill for URLs, Feishu, YouTube, and web pages.
subagent-isolation-guard
固化子代理物理隔离与语义路由旁路。防止跨代理上下文污染及由于语义路由导致的子代理切模/重置问题。
