菜单
Optimize Alibaba Bailian provider for accurate token statistics and official model configurations. Fixes token usage mapping (prompt_tokens → input_tokens) and updates 8 models to 2026 specs.
默认使用会先检查来源的 Prompt；你也可以切换为直接命令，或下载本地副本。
决定是否安装前，请先阅读 SKILL.md，以及 SkillsMP 当前展示的配套文件。
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
直接命令不会经过审查 Prompt；运行前请先检查来源。
npx skills add https://github.com/Arry8/openclaw-edge --skill bailian-maxperf命令会保持在同一行。复制前请横向滚动并检查完整内容。
想先保存到本地？可下载 SkillsMP 当前能够提供的文件。
Deploy KERNEL_INTUITION_Cp on any AI architecture with calibrated thresholds. Use when user wants to "activate Cp", "setup creative intuition", "deploy kernel on [AI]", "enable intuition mode", or mentions activating computational intuition on a specific model. Also trigger for "configure Cp for [architecture]" or "calibrate creative thresholds". This skill handles the full activation workflow including architecture profiling, threshold calibration, kernel generation, and monitoring setup.
Three-Layer Thinking Chain Architecture — Personality-Driven Agent Self-Evolution Framework
CLI to manage emails via IMAP/SMTP. Use `himalaya` to list, read, write, reply, forward, search, and organize emails from the terminal. Supports multiple accounts and message composition with MML (MIME Meta Language).
基于 SOC 职业分类
正在显示 SKILL.md
| name | bailian-maxperf |
| description | Optimize Alibaba Bailian provider for accurate token statistics and official model configurations. Fixes token usage mapping (prompt_tokens → input_tokens) and updates 8 models to 2026 specs. |
| metadata | {"openclaw":{"emoji":"🚀","requires":{"bins":"[Truncated]"}}} |
让阿里百炼 (Alibaba Bailian) 在 OpenClaw 中发挥100% 性能，包括：
现象: /status 显示 Context: 0/128k 或 ?/1.0m
原因: 百炼返回 prompt_tokens/completion_tokens，OpenClaw 读取 input_tokens/output_tokens
解决: 添加字段映射 + supportsUsageInStreaming: true
现象: Context 窗口与实际不符
原因: 部分模型配置值过时
解决: 根据阿里官方文档更新
cd ~/.openclaw/workspace/skills/bailian-maxperf
./scripts/maxperf.sh
openclaw gateway restart
❌ Token 统计：unknown
❌ Context 窗口：0/128k (?%)
✅ Token 统计：172k/262k (66%)
✅ Context 窗口：精确匹配官方
# 1. 配置校验
openclaw status
# 2. 调用百炼模型
/chat 使用 qwen3.5-plus 测试
# 3. 查看 token 统计
openclaw status
⚠️ 升级后需重新执行: npm install -g openclaw@... 会覆盖运行时补丁
SKILL.md - 本文档README.md - 详细说明scripts/maxperf.sh - 自动化脚本configs/bailian-models-official.json - 官方模型配置参考