agentleFS
itzcullitzcull/thinking-skills/skills/issue-trees/SKILL.md

issue-trees

Skill3 starsChanged 6 months agoMITView on GitHub

Use issue trees to break complex problems into mutually exclusive and collectively exhaustive branches. Use when structuring problem solving, root cause analysis, solution exploration, or consulting-style decomposition.

The file

We split this skill into the rules it gives an agent

2 rules. About 0 are common, 2 are distinctive, and 0 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈2

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 0

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Ask "How might we improve/fix this?"

    line 38
  2. Distinctive:

    Don't believe feature helps them

    line 58

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Issue Trees

Overview

Category: Problem Solving Tool Purpose: Structure and solve problems systematically by breaking them down into manageable parts

What Are Issue Trees?

Issue trees are "maps of problems" that help break down complex challenges into smaller, more actionable components. They provide a systematic approach to understanding and solving problems through a "divide and conquer" strategy.

Types of Issue Trees

  1. Problem Trees - Created by asking "Why?"
  2. Solution Trees - Created by asking "How?"

How to Create an Issue Tree

Problem Tree Principles

  1. Break the problem into separate categories/branches
  2. Use MECE principle:
    • Mutually Exclusive: No overlap between branches
    • Collectively Exhaustive: Covers the entire problem
  3. Focus on broad categories, not small details
  4. Apply 80/20 rule: Concentrate on most impactful problem areas

Solution Tree Steps

  1. Select a specific problem part
  2. Ask "How might we improve/fix this?"
  3. Map potential solution categories
  4. Generate ideas within each category

Example

Scenario: Low Product Feature Adoption

Initial Tree:

  • Low adoption of feature X
    • Customers don't know about the feature
    • Customers know about it but don't use it

Expanded Tree:

  • Low adoption of feature X
    • Customers don't know about the feature
      • Feature not discoverable in product
      • Customers unaware outside product
    • Customers know about it but don't use it
      • Haven't tried the feature
        • Don't believe feature helps them
      • Tried but rejected feature
        • Not usable
        • Not working properly
        • Doesn't support needs

Key Takeaways

  • Provides systematic problem-solving approach
  • Helps prioritize problem areas
  • Facilitates clear communication about complex challenges

Source

"The Definitive Guide to Issue Trees" on Crafting Cases


Source: https://untools.co/issue-trees/

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.