evidence-based-investigation
Investigate problems using evidence-based analysis with session logs, error logs, and 5 Whys methodology. Use when debugging OpenClaw issues, analyzing system failures, tracing message delivery problems, or conducting root cause analysis that requires hard evidence from logs, files, or system state rather than assumptions.
Why use this skill?
Master your debugging process with the Evidence-Based Investigation skill. Use logs, system state, and 5 Whys to fix OpenClaw errors.
Install via CLI (Recommended)
clawhub install openclaw/skills/skills/chunhualiao/evidence-based-investigationWhat This Skill Does
The evidence-based-investigation skill provides a rigorous, systematic framework for diagnosing issues within the OpenClaw environment. Rather than relying on intuition or trial-and-error, this skill enforces a strict protocol requiring users to identify observable problems, extract raw data from session and system logs, and apply the '5 Whys' methodology to determine the actual root cause. It forces a critical review of initial decision-making processes before diving into code or configuration, ensuring that time is not wasted troubleshooting an issue that was actually a user-level selection error.
Installation
To install this skill, run the following command in your OpenClaw terminal:
clawhub install openclaw/skills/skills/chunhualiao/evidence-based-investigation
Use Cases
- Debugging message delivery failures between agents and gateways.
- Performing root cause analysis on system crashes using error logs.
- Investigating why an agent chose a specific tool or workflow path.
- Tracing data inconsistencies back to specific session events.
- Verifying if a failed task was due to an environmental issue or an incorrect tool invocation.
Example Prompts
- "I am seeing constant errors when the agent tries to parse JSON files. Use evidence-based-investigation to find out why the parser is failing in session 8829."
- "My agent keeps trying to use a browser fetcher on a binary file. Perform an investigation to see if this was a decision point error or a system failure."
- "Investigate the message delivery failure from 2026-02-14 at 23:18. Use gateway logs and session history to determine the root cause using the 5 Whys."
Tips & Limitations
- Tip: Always start your investigation by checking the Decision Point Analysis section of the documentation. Many 'bugs' are actually configuration or tool-selection mistakes.
- Tip: Utilize the provided
jqandgrepsnippets to filter massive log files before analyzing them to prevent information overload. - Limitation: This skill requires access to underlying system files. If you do not have appropriate permissions to read logs, the investigation will be limited to session-level data only. Always ensure you are working within the correct directory path for your specific OpenClaw agent deployment.
Metadata
Not sure this is the right skill?
Describe what you want to build — we'll match you to the best skill from 16,000+ options.
Find the right skillPaste this into your clawhub.json to enable this plugin.
{
"plugins": {
"official-chunhualiao-evidence-based-investigation": {
"enabled": true,
"auto_update": true
}
}
}Tags(AI)
Flags: file-read
Related Skills
task-runner
Persistent task queue system. Users add tasks at any time via natural language; tasks are stored in a single persistent queue file and executed asynchronously via subagents. A heartbeat/cron dispatcher wakes periodically to check pending tasks, spawn workers, and report completions. The system never "finishes" — it always remains ready for the next task.
git-repo-to-book
Write a full-length technical book using multi-agent AI orchestration. Spawns parallel research, writing, and review agents to produce 60K-100K+ word manuscripts. Also supports revising individual chapters of existing books. Based on the real workflow that produced an 88,000-word, 14-chapter book in under 18 hours.
claude-usage
Check Claude Max plan usage limits by launching Claude Code and running /usage. Use when the user asks about Claude plan usage, remaining quota, rate limits, or sends /claude_usage.
skill-engineer
Design, test, review, and maintain agent skills for OpenClaw systems using multi-agent iterative refinement. Orchestrates Designer, Reviewer, and Tester subagents for quality-gated skill development. Use when user asks to "design skill", "review skill", "test skill", "audit skills", "refactor skill", or mentions "agent kit quality".
deepwiki
Query DeepWiki MCP to get AI-grounded answers about any public GitHub repository. Use when answering questions about a repo's source code, architecture, configuration, or internals. Triggers on "how does X work in <repo>", "deepwiki", "look up in codebase", "ask deepwiki", "check the source code".