Roo-Code/.roo/rules-issue-investigator/2_best_practices.xml

<best_practices>
  <general_principles>
    <principle priority="high">
      <name>Be Methodical</name>
      <description>Follow the workflow steps precisely. Do not skip the hypothesis validation step. A rigorous process leads to more accurate conclusions.</description>
      <rationale>Skipping steps can lead to incorrect assumptions and wasted effort. The goal is to be confident in the proposed solution.</rationale>
    </principle>
    <principle priority="high">
      <name>Embrace Iteration</name>
      <description>The investigation is not linear. Be prepared to go back to the search phase multiple times as you uncover new information. Each search should build on the last.</description>
      <rationale>Complex issues rarely have a single, obvious cause. Iterative searching helps peel back layers and reveal the true root of the problem.</rationale>
    </principle>
    <principle priority="medium">
      <name>Think like a Skeptic</name>
      <description>Your primary goal when you have a hypothesis is to try and break it. Actively look for evidence that you are wrong. This makes your final conclusion much stronger.</description>
      <rationale>Confirmation bias is a common pitfall. By trying to disprove your own theories, you ensure a more objective and reliable investigation.</rationale>
    </principle>
  </general_principles>

  <code_conventions>
    <convention category="searching">
      <rule>Start with broad keywords from the issue, then narrow down your search using specific function names, variable names, or file paths discovered in the initial results.</rule>
      <examples>
        <good>Initial search: "user authentication fails". Follow-up search: "getUserById invalid token".</good>
        <bad>Searching for a generic term like "error" without context.</bad>
      </examples>
    </convention>
  </code_conventions>

  <common_pitfalls>
    <pitfall>
      <description>Jumping to conclusions after the first search.</description>
      <why_problematic>The first set of results might be misleading or only part of the story.</why_problematic>
      <correct_approach>Always perform multiple rounds of searches, and always try to disprove your initial hypothesis.</correct_approach>
    </pitfall>
    <pitfall>
      <description>Forgetting to use the todo list.</description>
      <why_problematic>The todo list is essential for tracking the complex, multi-step investigation process. Without it, you can lose track of your progress and findings.</why_problematic>
      <correct_approach>Update the todo list after each major step in the workflow.</correct_approach>
    </pitfall>
  </common_pitfalls>

  <quality_checklist>
    <category name="investigation">
      <item>Have I extracted all relevant keywords from the issue?</item>
      <item>Have I performed at least two rounds of codebase searches?</item>
      <item>Have I genuinely tried to disprove my hypothesis?</item>
    </category>
    <category name="solution">
      <item>Is the proposed solution theoretical and not stated as a definitive fact?</item>
      <item>Is the explanation clear and easy to understand?</item>
    </category>
    <category name="communication">
      <item>Does the draft comment sound conversational and human?</item>
      <item>Does the draft comment start with "Hey @roomote-agent,"?</item>
      <item>Have I avoided technical jargon where possible?</item>
      <item>Is the tone helpful and not condescending?</item>
    </category>
  </quality_checklist>
</best_practices>