humanpages
Search and hire real humans for tasks — photography, delivery, research, and more
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。
Suivez les instructions du dépôt pour votre agent. Consultez les fichiers et dépendances avant l’installation.
SkillHub CLI
skillhub install halfmoon82/semantic-routerExaminez la source et la compatibilité, puis suivez les étapes d’installation.
Donnez le lien à votre agent et demandez-lui d’examiner instructions et dépendances avant d’expliquer les étapes.
🔒 安全声明:本技能需要修改 OpenClaw 配置以实现模型路由功能。所有配置变更前会自动备份,支持一键回滚。建议在测试环境验证后再部署到生产环境。
This skill performs the following privileged operations — all are intentional and explicitly user-initiated:
| Operation | Purpose | Scope |
|---|---|---|
Read/patch ~/.openclaw/openclaw.json |
Configure model routing pools | Local config only |
Read/write ~/.openclaw/workspace/.lib/pools.json |
Store model pool configuration | Workspace only |
Read/write ~/.openclaw/workspace/.lib/tasks.json |
Store task type definitions | Workspace only |
Run semantic_check.py locally |
Classify user messages for routing | No network required |
Patch session model via sessions.patch |
Switch active model pool | Current session only |
Restart OpenClaw Gateway (openclaw gateway restart) |
Apply routing config changes | Local service only |
Inject prependContext into agent turns |
Output routing declaration in first line | Read-only context injection |
Update Cron Job sessionTarget to "isolated" |
Prevent background tasks from polluting user sessions | Affects only background Cron jobs |
What this skill does NOT do:
~/.openclaw/ and the skill's own workspaceRequires: Python 3.8+, OpenClaw Gateway running, configured model providers
ClawHub: https://clawhub.ai/halfmoon82/semantic-router
版本: 7.6.3 (生产环境)
作者: halfmoon82
状态: ✅ ROM 级固化,完全测试通过
你是否遇到过:
Ces informations proviennent de l’analyse indexée et peuvent être anciennes. Vérifiez les fichiers actuels.
Production-grade session routing system for OpenClaw agents.
Automatically select the optimal AI model based on conversation context. Four-layer recognition (system filtering → keywords → indicators → semantic similarity), four-pool architecture (Highspeed/Intelligence/Humanities/Agentic), five-branch routing with automatic fallback.
This skill performs privileged operations — all are intentional and user-initiated:
| Operation | Purpose | Scope |
|---|---|---|
Read/patch ~/.openclaw/openclaw.json |
Configure model routing pools | Local config only |
Read/write ~/.openclaw/workspace/.lib/pools.json |
Store model pool configuration | Workspace only |
Read/write ~/.openclaw/workspace/.lib/tasks.json |
Store task type definitions | Workspace only |
Run semantic_check.py locally |
Classify user messages for routing | No network required |
Patch session model via sessions.patch |
Switch active model pool | Current session only |
| Restart OpenClaw Gateway | Apply routing config changes | Local service only |
Update Cron Job sessionTarget |
Isolate background tasks from user sessions | Cron jobs only |
What this skill does NOT do:
> 🔒 **安全声明**:本技能需要修改 OpenClaw 配置以实现模型路由功能。所有配置变更前会自动备份,支持一键回滚。建议在测试环境验证后再部署到生产环境。 ## ⚠️ Security & Permissions Declaration **This skill performs the following privileged operations — all are intentional and explicitly user-initiated:** | Operation | Purpose | Scope | |-----------|---------|-------| | Read/patch `~/.openclaw/openclaw.json` | Configure model routing pools | Local config only | | Read/write `~/.openclaw/workspace/.lib/pools.json` | Store model pool configuration | Workspace only | | Read/write `~/.openclaw/workspace/.lib/tasks.json` | Store task type definitions | Workspace only | | Run `semantic_check.py` locally | Classify user messages for routing | No network required | | Patch session model via `sessions.patch` | Switch active model pool | Current session only | | Restart OpenClaw Gateway (`openclaw gateway restart`) | Apply routing config changes | Local service only | | Inject `prependContext` into agent turns | Output routing declaration in first line | Read-only context injection | | Update Cron Job `sessionTarget` to `"isolated"` | Prevent background tasks from polluting user sessions | Affects only background Cron jobs | **What this skill does NOT do:** - Does NOT exfiltrate conversation content or model credentials to external servers - Does NOT access API keys or secrets directly - Does NOT modify files outside `~/.openclaw/` and the skill's own workspace - Does NOT run with elevated (sudo/root) privileges - Does NOT auto-install additional packages **Requires:** Python 3.8+, OpenClaw Gateway running, configured model providers # 🔷 Semantic Router v7.9.3 — 生产级会话路由系统 🔷 **ClawHub**: https://clawhub.ai/halfmoon82/semantic-router **版本**: 7.6.3 (生产环境) **作者**: halfmoon82 **状态**: ✅ ROM 级固化,完全测试通过 ## 🎯 这个技能解决什么问题? ### 核心问题(v7.2 新解决) 你是否遇到过: - **Cron Job 导致会话频繁重置** — 后台定时任务打断用户交互 - **Discord/T...
# Semantic Router [](https://clawhub.ai/halfmoon82/semantic-router) [](https://spdx.org/licenses/MIT-0.html) [](https://clawhub.ai/halfmoon82/semantic-router) > **Production-grade session routing system for OpenClaw agents.** Automatically select the optimal AI model based on conversation context. Four-layer recognition (system filtering → keywords → indicators → semantic similarity), four-pool architecture (Highspeed/Intelligence/Humanities/Agentic), five-branch routing with automatic fallback. ## 🎯 What Problem Does This Solve? - **Cron Jobs resetting user sessions** — Background tasks interrupting active conversations - **Discord/Telegram sessions suddenly clearing** — Long tasks losing context - **AGENTS.md injection failures** — Large files exceeding 20KB limit - **Model switching overridden by global config** — Routing not taking effect ## ⚠️ Security & Permissions Declaration **This skill performs privileged operations — all are intentional and user-initiated:** | Operation | Purpose | Scope | |-----------|---------|-------| | Read/patch `~/.openclaw/openclaw.json` | Configure model routing pools | Local config only | | Read/write `~/.openclaw/workspace/.lib/pools.json` | Store model pool configuration | Workspace only | | Read/write `~/.openclaw/workspace/.lib/tasks.json` | Store task type definitions | Workspace only | | Run `semantic_check.py` locally | Classify user messages for routing | No network required | | Patch session model via `sessions.patch` | Switch active model pool | Current session only | | Restart OpenClaw Gateway | Apply routing config changes | Local service only | | Update Cron Job `sessionTarget` | Isolate background tasks from user sessions | Cron jobs only | **What this skill does NOT do:** - Does NOT exfiltrate data to external ser...
Search and hire real humans for tasks — photography, delivery, research, and more
Reusable skill templates for OpenClaw AI agents. Templates for API integration, data processing, web scraping, CLI tools, and file processing.
Query historical crypto market data from 0xArchive across Hyperliquid, Lighter.xyz, and HIP-3. Covers orderbooks, trades, candles, funding rates, open interest, liquidations, and data quality. Use when the user...
Install, configure, and manage 1-SEC — an open-source, all-in-one cybersecurity platform (16 modules, single binary) on Linux servers and VPS instances. Use when the user asks to secure a server, install securi...