← Back to Skills Marketplace
157
Downloads
0
Stars
0
Active Installs
8
Versions
Install in OpenClaw
/install openclaw-diag
Description
OpenClaw 系统诊断和性能分析工具。分析 agent 推理耗时、Token 用量、工具调用统计、 Run 时间线、Gateway 重启历史。支持多种模式：批量分析（默认）、实时跟踪（-f）、 摘要统计（-s）、高级诊断（--advanced）。支持多 Agent 过滤。 使用场景：当用户询问 OpenCla...
Usage Guidance
This skill appears to implement a legitimate diagnostics tool, but review before enabling: (1) inspect scripts/openclaw-diag.sh yourself — it reads ~/.openclaw and /tmp logs and can modify openclaw.json and restart the Gateway; (2) be aware the skill will send raw script output back to the user (may contain PII or secrets); (3) the manifest did not declare the config paths or binary dependencies (python3, openclaw CLI) — that's an inconsistency; (4) advanced mode performs privileged actions and uses interactive prompts (/dev/tty) which may hang in non-interactive agent runs; (5) if you install, consider restricting autonomous invocation, require explicit human confirmation before running advanced options, run initially on a non-production/staging host, and only enable summary (-s) mode until you trust the code and behavior.
Capability Analysis
Type: OpenClaw Skill
Name: openclaw-diag
Version: 1.0.7
The bundle provides diagnostic tools with high-risk capabilities, including a Bash script (openclaw-diag.sh) that can modify the system's 'openclaw.json' configuration and restart the OpenClaw Gateway service. The SKILL.md instructions direct the AI agent to pass user-provided arguments directly to the shell script ('参数透传') and use a 'Direct Output' mode that bypasses model summarization and suppresses further agent responses using 'NO_REPLY'. While these features are aligned with the stated diagnostic purpose, the combination of system-level configuration access, service control, and instructions to bypass AI safety/summarization logic creates a significant surface for prompt injection and unauthorized system manipulation.
Capability Assessment
Purpose & Capability
Name/description match a local diagnostics tool and the included script implements that. However registry metadata claims no required config paths or credentials while the script explicitly reads session files (~/.openclaw, /root/.openclaw, /etc paths) and can modify openclaw.json and restart the Gateway — those resource requirements should have been declared.
Instruction Scope
SKILL.md instructs the agent to execute the bundled script and to send the script stdout 'raw' via message(action="send"). The script reads session logs (which can contain full user/tool messages and possibly secrets), system config files, and may write/restore openclaw.json and restart the gateway. It also uses interactive prompts (/dev/tty) which may block in non-interactive agent runs. Sending raw logs back to chat without model filtering can leak sensitive data.
Install Mechanism
No install spec (instruction-only with a script). Low installation risk because nothing is downloaded or extracted; code is bundled in the skill. Still review the bundled script before use.
Credentials
The skill declares no required env vars or config paths, yet the script accesses multiple system paths (~/.openclaw, /root/.openclaw, /etc/openclaw/openclaw.json, /tmp logs) and requires python3 and an 'openclaw' CLI. The lack of declared file/config access is an inconsistency and reduces transparency about what secrets/data the skill may access.
Persistence & Privilege
always:false (good), but the script can modify system config and restart the OpenClaw Gateway (privileged actions). Advanced mode requires interactive confirmation, but the agent could still be scripted to invoke those actions. Combined with autonomous invocation capability, this raises operational risk if the agent runs the skill without a human in the loop.
How to Use
- Make sure OpenClaw is installed (local or Docker)
- Run the install command in chat:
/install openclaw-diag - After installation, invoke the skill by name or use
/openclaw-diag - Provide required inputs per the skill's parameter spec and get structured output
Version History
v1.0.7
恢复 /root/ + $HOME/ 双路径搜索，兼容 root 和非 root 用户
v1.0.6
移除重复的路径搜索条目（openclaw.json×2, sessions×2）
v1.0.5
修复实时跟踪agent过滤：无sessionKey事件通过current_agent上下文继承最近agent，避免漏显或误丢事件
v1.0.4
修复实时跟踪模式agent过滤失效（AGENT_FILTER_ENV未export到管道python端）; Python最低版本声明3.6→3.7（fromisoformat依赖）
v1.0.3
移除自定义 agent 名称（waicode/wairesearch/waidesign/waiqa），改用通用占位符
v1.0.2
移除硬编码 /root 路径，改用 $HOME，确保多用户环境兼容
v1.0.1
修复ClawHub扫描告警：重命名 first_token→first_recv_ts, session_key→sess_ref, childSessionKey→child_sess_id, token→tok 显示标签
v1.0.0
初版：6种诊断模式、/diag指令触发、多Agent过滤、session数据驱动、直出模式、推理耗时分析、工具统计、错误追踪
Metadata
Frequently Asked Questions
What is Openclaw Diagnostics?
OpenClaw 系统诊断和性能分析工具。分析 agent 推理耗时、Token 用量、工具调用统计、 Run 时间线、Gateway 重启历史。支持多种模式：批量分析（默认）、实时跟踪（-f）、 摘要统计（-s）、高级诊断（--advanced）。支持多 Agent 过滤。 使用场景：当用户询问 OpenCla... It is an AI Agent Skill for Claude Code / OpenClaw, with 157 downloads so far.
How do I install Openclaw Diagnostics?
Run "/install openclaw-diag" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.
Is Openclaw Diagnostics free?
Yes, Openclaw Diagnostics is completely free, licensed under MIT-0. You can download, install and use it at no cost.
Which platforms does Openclaw Diagnostics support?
Openclaw Diagnostics is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).
Who created Openclaw Diagnostics?
It is built and maintained by Garming (@wujiaming88); the current version is v1.0.7.
More Skills