Agent skill · AI & Agents

model-fallback

模型自动降级与故障切换。当主模型请求失败、超时、达到速率限制或配额耗尽时，自动切换到备用模型，确保服务连续性。支持多供应商、多优先级的智能模型选择，提供健康监控、自动重试和错误恢复机制。

majiayu000github.com/majiayu000GitHub ↗
claude-codecan modify filesMIT
Install
npx skills add majiayu000/claude-skill-registry --skill model-fallback-aaaaqwq-agi-super-skills --agent claude-code

Same command for any agent — swap --agent for codex, cursor, copilot.

Facts
Files in the skill folder: 2
SKILL.md size: 9 KB
Bundled scripts: none
Allowed tools: BashReadWriteEditExec
Path: skills/ai-llm/model-fallback-aaaaqwq-agi-super-skills/SKILL.md
Open the folder on GitHub →
Where it comes from
Stars: 534
Language: HTML

Weekly change comes from our own snapshots, not the repository page — it measures attention, not adoption.

From the SKILL.md

# 模型自动降级与故障切换 ## 概述 本技能提供完整的模型自动降级和故障切换解决方案，确保在主模型不可用时自动切换到备用模型，维持 AI 助手的持续服务能力。 ## 核心功能 ### 1. 智能模型选择 根据任务类型和模型状态智能选择最合适的模型： ```yaml 优先级顺序: 1. anapi/opus-4.5 # 最强能力，最高优先级 2. zai/glm-4.7 # 中文优化，性价比高 3. openrouter-vip/gpt-5.2-codex # 编码专用 4. github-copilot/claude-sonnet-4-5 # 免费备用 ``` ### 2. 故障检测与处理 自动检测以下故障并触发切换： - **超时错误** (timeout): 请求超过设定时间 - **速率限制** (rate_limit): API 调用频率超限 - **配额耗尽** (quota_exceeded): token 配额用尽 - **认证错误** (authentication): API 密钥失效 - **服务不可用** (service_unavailable): 供应商服务故障 - **网络错误** (network_error): 连接失败 ### 3. 重试机制 智能重试策略： ```yaml 重试配置: 最大重试次数: 3 初始延迟: 1000ms 最大延迟: 10000ms 退避倍数: 2.0 使用备用模型: true ``` 重试时间线： ``` 第1次失败 → 等待 1s → 重试 第2次失败 → 等待 2s → 重试 第3次失败 → 等待 4s → 切换模型 ``` ### 4. 健康监控 持续监控所有模型供应商的健康状态： ```bash # 每5分钟检查一次 检查项目: - API 端点连通性 - 响应时间 - 错误率 - 配额使用情况 ``` ## 快速开始 ### 1. 配置模型降级 配置文件：`~/.openclaw/agents/main/agent/agent.json` ```json { "model": "anapi/opus-4.5", "modelFallback": [ "zai/glm-4.7", "openrouter-vip/gpt-5.2-codex", "github-copilot/claude-sonnet-4-5" ], "retry": { "maxAttempts": 3, "initialDelayMs": 1000, "maxDelayMs": 10000, "backoffMultiplier": 2.0, "useFallbackOnFailure": true } } ``` ### 2. 启动监控 ```bash # 启动后台监控 ~/.openclaw/scripts/mo

What's inside
Steps it walks through
  1. 概述
  2. 核心功能
  3. 1. 智能模型选择
  4. 2. 故障检测与处理
  5. 3. 重试机制
  6. 4. 健康监控
  7. 快速开始
  8. 1. 配置模型降级
  9. 2. 启动监控
  10. 3. 手动触发切换
  11. 工作流程
  12. 正常请求流程
  13. 故障切换流程
  14. 监控流程
Ships with 1 file
  • metadata.json
Commands it runs
tail -f ~/.openclaw/logs/model-fallback.log
tail -f ~/.openclaw/logs/model-monitor.log
tail -f ~/.openclaw/logs/*.log
JSON 格式状态
cat ~/.openclaw/logs/model-status.json | python3 -m json.tool
cat ~/.openclaw/agents/main/agent/agent.json | grep modelFallback
tail -20 ~/.openclaw/logs/model-fallback.log
ps aux | grep monitor-models
cat ~/.openclaw/logs/model-monitor.pid
cat ~/.openclaw/agents/main/agent/auth-profiles.json
More from claude-skill-registry
All skills →
descriptive-statisticsSummarizing and visualizing data through measures of center, spread, shape, and position. Covers…Data & Analyticsperplexity-researcher-reasoning-proHighest level of research and reasoning capabilities for complex decision-making with significant…OtherretroBrutally honest engineering retrospective. Analyzes git history for what actually happened — not…Data & AnalyticsanalyzeUniversal multi-perspective analyzer for any topic, file, idea, or decision. Extract key points…Otherarize-prompt-optimizationINVOKE THIS SKILL when optimizing, improving, or debugging LLM prompts using production trace data…Data & Analyticscellxgene-contextGuide for integrating CellxGene Census single-cell data with ENCODE bulk experiments. Use when…Data & Analytics
About this skill
What does the model-fallback skill do?

模型自动降级与故障切换。当主模型请求失败、超时、达到速率限制或配额耗尽时，自动切换到备用模型，确保服务连续性。支持多供应商、多优先级的智能模型选择，提供健康监控、自动重试和错误恢复机制。

How do I install it?

Run `npx skills add majiayu000/claude-skill-registry --skill model-fallback-aaaaqwq-agi-super-skills --agent claude-code` — it drops the skill into your project so the agent can pick it up. Swap the --agent value for codex, cursor or copilot if you use one of those.

Where does this skill come from?

From majiayu000/claude-skill-registry, a repository with 534 stars. We read it straight from the repository tree rather than a submitted listing, so what you see here is what is actually published.

Is a popular skill a good skill?

Not necessarily. Stars measure attention, not adoption — a repository can trend for a week and be abandoned. That is why we show the weekly change from our own snapshots next to the total, instead of a single flattering number.

Keep going
All skills →
The full catalog, by category and by tool.
Open Source Radar →
The repositories these skills come from, watched daily.
The people behind them →
Makers and builders across the ecosystem.