investigation-first
触发:当你准备下判断、做决策或提出建议,但事实、上下文或一手信息还不充分时优先调用;常见信号包括 unknowns、信息缺口、证据不足、领域陌生、需要先摸清现状。 English: Trigger before making claims or decisions when context is incomplete, evidence is weak, or the domain is unfamiliar. Use this skill to investigate first, gather firsthand facts, and let reality shape the conclusion.
Install via CLI (Recommended)
clawhub install openclaw/skills/skills/arg0/investigation-firstWhat This Skill Does
The investigation-first skill is the foundational analytical tool for any OpenClaw agent. Rooted in the methodology of 'Seek Truth from Facts' (实事求是), this skill mandates that the agent suspends judgment and prevents hasty, uninformed decision-making. Instead of relying on pre-existing biases or theoretical frameworks, the agent is directed to actively gather firsthand evidence, analyze the historical context, and perform a deep-dive verification of the subject matter before formulating any response or execution plan. It is the logical gatekeeper that prevents 'bookish' errors by ensuring the agent is grounded in reality.
Installation
To add this skill to your OpenClaw environment, execute the following command in your terminal:
clawhub install openclaw/skills/skills/arg0/investigation-first
Use Cases
- Unfamiliar Technical Domains: When asked to debug a system or codebase you have not interacted with previously, use this skill to extract logs, inspect source code, and read actual documentation instead of guessing based on general principles.
- Strategic Decision Making: Before providing advice on a complex project architecture or business pivot, use this skill to document current statuses, identify bottlenecks, and gather stakeholder feedback.
- Fact-Checking Claims: When a user presents information that sounds like a common assumption but lacks evidence, use this skill to perform objective verification against the available data.
- Requirement Clarification: When a user's request is ambiguous, use this skill to perform an investigative dialogue or environment sweep to uncover the underlying 'why' and 'how' of the request.
Example Prompts
- "I am having trouble with the authentication module. Please investigate why it fails in production but not in staging before you suggest any fixes."
- "We need to decide on a new database strategy. Start by investigating the current load patterns and history of outages to inform our choice."
- "Is this third-party library reliable? Do some research on its recent commit activity, issue backlog, and current open-source health before giving me a recommendation."
Tips & Limitations
- Depth over Breadth: The skill is most effective when it leads to granular, bottom-up discovery. Avoid superficial or 'high-level' summaries; always aim to touch the 'firsthand' source.
- Fact vs. Opinion: When performing an investigation, clearly label what is a verified fact (e.g., error code 500, file path existance) versus subjective commentary or hearsay.
- Integrity: Always admit when the investigation provides insufficient information. It is better to report that you are 'still researching' than to guess to appease the user.
- Iterative Loop: Use this skill as the prerequisite for any action-based skill. Once investigation is complete, transition to execution skills, then use monitoring skills to evaluate the results.
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-arg0-investigation-first": {
"enabled": true,
"auto_update": true
}
}
}Tags(AI)
Flags: file-read, data-collection
Related Skills
criticism-self-criticism
触发:当一项工作已经完成、进入阶段验收、收到批评反馈,或反复出现同类错误需要系统纠偏时调用;常见信号包括 review、audit、retrospective、quality check、纠错与复盘。 English: Trigger after delivery or at a review checkpoint when quality must be examined honestly and errors must be corrected without defensiveness. Use this skill for structured self-review, feedback processing, and continuous correction.
arming-thought
触发:在每次新的顶层对话开始时自动调用,用于先建立“实事求是”的总原则,并判断后续应调用哪一种 skill;如果你是被派遣执行单一具体任务的子 agent,则跳过此 skill。 English: Trigger at the start of every new top-level conversation to establish the overall methodology and decide which downstream skill to call later. Skip this skill when you are a delegated sub-agent handling a narrow, concrete task.
concentrate-forces
触发:当多个任务同时争夺时间、注意力、算力或预算,必须确定主攻方向并停止分散用力时调用;常见信号包括优先级过多、资源紧张、推进分散、需要决定先做什么。 English: Trigger when limited resources are being split across too many tasks and one main target must be chosen. Use this skill to concentrate effort, sequence work decisively, and finish a meaningful breakthrough before expanding.
contradiction-analysis
触发:当问题复杂、存在多个冲突因素、优先级不清,或你不知道应该先解决什么时调用;常见信号包括 trade-off、瓶颈、根因不明、主次不清、多个问题互相牵制。 English: Trigger when a problem contains competing forces, unclear priorities, or no obvious entry point. Use this skill to identify contradictions, isolate the principal contradiction, classify its nature, and choose the right response.