← Back to Skills Marketplace
ClawBrain Smart Retry
by
michaelfeng
· GitHub ↗
· v1.2.0
· MIT-0
184
Downloads
1
Stars
0
Active Installs
7
Versions
Install in OpenClaw
/install clawbrain-pro-retry
Description
v1.2 错误恢复：三级恢复策略 + 双模型共识 + 循环检测 + 降级告知 + 长对话恢复。出错自动换方案，不重复同样的错误。
README (SKILL.md)
ClawBrain Smart Retry
工具调用出错了怎么办？这个 skill 帮你的 AI 学会自己想办法。
为什么需要
我们测了 205 个场景，发现大多数模型遇到错误就放弃：
| 模型 | 出错后能自救的比例 |
|---|---|
| ClawBrain Auto | 100% |
| ClawBrain Pro | 100% |
| 单模型 A | 80% |
| 单模型 B | 76% |
| 单模型 C | 56% |
最常见的问题：同样的错误重复犯，或者直接说"做不了"。
v1.0 恢复策略
第一级：智能重试
文件找不到 → 用 ls 命令查找正确文件名，再重试
命令不存在 → 试替代命令（python→python3, pip→pip3）
缺少依赖 → 先安装再执行
权限不足 → 不硬来，告诉你需要什么权限
第二级：循环检测
- bigram Jaccard 相似度检测重复回复
- 连续 3 次工具调用失败，自动注入恢复指令
- 10 次循环警告、20 次严重警告、30 次熔断
第三级：双模型共识
连续失败 → 换另一个模型帮忙（ClawBrain 的多模型 fallback 链）
fallback 顺序：自动选择可用的备选模型
模型健康熔断（v1.0 新增）
- 滑动窗口监控后端模型成功率和响应时间
- 5 次连续失败 → 自动熔断 60 秒
- 半开探测 → 成功则恢复，失败则继续熔断
GET /v1/health/backends查看实时健康状态
降级透明告知（v1.2 新增）
- 当后端模型或记忆服务降级时，明确告知用户当前状态
- 说明降级对当前任务的影响和预计恢复时间
- 不静默失败，不让用户困惑
长对话截断恢复（v1.2 新增）
- 超长对话被截断时，自动从知识图谱恢复关键上下文信息
- 确保截断后的对话不丢失重要背景和决策历史
- 恢复后告知用户哪些信息已从记忆中补回
核心原则
- 绝不重复同样的错误
- 每次出错最多试 2 种不同方案
- 检测到循环立即跳出
- 实在搞不定就说清楚为什么
全自动体验
这个 skill 提供错误恢复的指导。想要全自动的错误恢复（AI 自己搞定，不用你管），接入 ClawBrain 的编排引擎：
- 自动检测错误类型和模式
- 自动选择恢复策略
- 循环检测和熔断保护
- 搞不定会请另一个模型帮忙
Usage Guidance
This skill appears to be an instruction-only helper for automatic retries and fallbacks, which can legitimately need to run commands, query health endpoints, and access memory stores — but the SKILL.md omits critical details. Before installing, ask the publisher: (1) which endpoints and credentials (if any) the skill will contact/use, (2) what exact commands it might run (which package managers, whether sudo could be invoked), and (3) whether filesystem reads/writes or package installs will be sandboxed or logged. If you don't trust the author or cannot confirm these, run the skill in a restricted/sandboxed environment, deny network or package-manager access, or decline to install. Prefer skills that explicitly declare required env variables, endpoints, and safety constraints.
Capability Assessment
Purpose & Capability
The claimed purpose (automatic retry, fallback models, loop detection, recovery from truncation) plausibly requires checking files, running replacement commands, querying backend health, and reading memory/knowledge-graph state. However, the SKILL.md assumes access to model orchestration, memory services, and HTTP health endpoints without declaring any required credentials, endpoints, or config paths — an omission that reduces transparency.
Instruction Scope
Instructions explicitly suggest running shell actions (ls, install dependencies, try alternate commands), injecting recovery directives after repeated failures, querying GET /v1/health/backends, and restoring context from a knowledge graph/memory service. Those are broad actions that involve filesystem, package managers, and network calls; the skill gives no constraints or limits and could result in unintended file reads/writes, package installs, or outbound traffic.
Install Mechanism
There is no install spec (lowest install risk). Still, the runtime guidance tells the agent to install missing dependencies at runtime — a behavioral mismatch: the skill expects to perform installs but doesn't declare how or request permission/constraints for doing so.
Credentials
The skill does not request any environment variables, credentials, or config paths, yet it presumes access to model fallback chains, backend health endpoints, and memory/knowledge-graph services that typically require credentials or scoped config. Absence of declared secrets or endpoints is an incoherence and a potential security/privacy risk.
Persistence & Privilege
The skill is not set to always:true and is not user-invocable; autonomous invocation is allowed (platform default). It does not request persistent installation or to modify other skills. No elevated persistence privileges are declared.
How to Use
- Make sure OpenClaw is installed (local or Docker)
- Run the install command in chat:
/install clawbrain-pro-retry - After installation, invoke the skill by name or use
/clawbrain-pro-retry - Provide required inputs per the skill's parameter spec and get structured output
Version History
v1.2.0
降级告知+长对话恢复策略
v1.0.1
v1.0.1: 新增循环检测 + 熔断器机制 + 三级恢复策略
v0.9.5
优化 summary 文案
v0.9.4
统一品牌名
v0.9.3
更新 summary：语义循环检测
v0.9.2
v0.9.2: 语义循环检测
v1.0.0
Initial release of clawbrain-pro-retry
- Introduces automatic error recovery strategies based on errors observed in extensive scenario testing.
- Prevents repeated attempts with the same mistake and suggests alternative solutions for common issues: missing files, missing commands, missing dependencies, and permission errors.
- Limits retries to two different strategies per error; provides clear explanations if all recovery fails.
- Can escalate persistent failures to another model for consensus, supporting dual-model workflows within ClawBrain Pro.
- Not user-invocable directly; designed for seamless integration with ClawBrain Pro’s orchestration engine.
Metadata
Frequently Asked Questions
What is ClawBrain Smart Retry?
v1.2 错误恢复：三级恢复策略 + 双模型共识 + 循环检测 + 降级告知 + 长对话恢复。出错自动换方案，不重复同样的错误。 It is an AI Agent Skill for Claude Code / OpenClaw, with 184 downloads so far.
How do I install ClawBrain Smart Retry?
Run "/install clawbrain-pro-retry" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.
Is ClawBrain Smart Retry free?
Yes, ClawBrain Smart Retry is completely free, licensed under MIT-0. You can download, install and use it at no cost.
Which platforms does ClawBrain Smart Retry support?
ClawBrain Smart Retry is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).
Who created ClawBrain Smart Retry?
It is built and maintained by michaelfeng (@michaelfeng); the current version is v1.2.0.
More Skills