Skill Vault · Learn and understand
Map an idea before getting lost in details
Connect the central question, useful branches and next decisions.
A topic, idea or decision you want to untangle.
Skill name /semantic-tree
Your next step
Try it for yourself
You’ll need: A topic, idea or decision you want to untangle.
Paste into an AI conversation after adding your own context.
This is a one-off starter for the approach. Installing the full Skill adds its complete instructions.
Build a semantic tree for the topic below. Start with the central question, branch into the few dimensions that genuinely change the answer, connect evidence and assumptions, then end with the next three decisions or actions.
Topic: [describe the idea or decision]
What happens nextA structured map connects evidence and assumptions, then identifies next decisions.
Use it again
Add the full Skill.
The starter lets you try the approach. Installation adds the complete instructions to your AI coding tool.
Copy the setup instructionsFor Codex or Claude Code on your computer
Your next step
Ask your agent to help you install it
You’ll need: Node.js with npx, Git, and the agent you choose. A project folder where you want the Skill available.
Paste this into Codex or Claude Code with your project open. Your agent will help you review and install the package.
Review files and permissions before accepting an install. Adding a Skill does not run it.
Help me install /semantic-tree from MattEspo23/skills v0.1.2 in this project.
Review the package instructions and supporting files first. Include these Skills: semantic-tree.
Use the command for the agent I am using:
Add to Codex:
npx skills@latest add 'MattEspo23/skills#v0.1.2' --skill semantic-tree --agent codex --copy
Add to Claude Code:
npx skills@latest add 'MattEspo23/skills#v0.1.2' --skill semantic-tree --agent claude-code --copy
Show me where the files will go before making changes. Preserve existing Skills and customizations. Stop if the release, supporting Skills, or target agent cannot be verified. Do not run the Skill or change external services during setup.
After installation, explain how I can use /semantic-tree and what access it needs.
What happens nextYour agent should review and add /semantic-tree, then explain how to use /semantic-tree. Stop if a dependency or version cannot be verified.
No additional supporting Skill is required by this package. Source version: v0.1.2.
Prefer a terminal command?
Add to Codex
npx skills@latest add 'MattEspo23/skills#v0.1.2' --skill semantic-tree --agent codex --copy
Add to Claude Code
npx skills@latest add 'MattEspo23/skills#v0.1.2' --skill semantic-tree --agent claude-code --copy
Installing copies the instructions into your chosen agent. It does not run the Skill or configure project tools.
Keep the package’s supporting files, LICENSE and NOTICE together with the Skill instructions.
Full notes & source materialThe complete original text, examples and reference details.
These are the complete original notes. Planned videos and services mentioned here may not be available yet; the actions above reflect what you can use on this site now.
Turn a vague idea into a structured map of what matters, what connects, and what to decide next.
Watch
Skill Vault video planned · Video planned
Install
Public release v0.1.2 — install the latest source or pin the tested release.
Install latest
npx skills@latest add MattEspo23/skills --skill semantic-tree
Reproducible install
npx skills@latest add 'MattEspo23/skills#v0.1.2' --skill semantic-tree
Clean installs are verified for Codex and Claude Code. The installer copies editable files into the selected agent; review every Skill before giving it tool access.
This is a public EspoAI original. Its Skill Vault video is planned; the released source can be installed now.
What it does
semantic-tree turns a broad topic into a navigable structure before asking AI
to collapse it into an answer. It separates the branches that can change the
decision, connects evidence and assumptions to the right branch, and ends with
the few next choices that have the most leverage.
When to reach for it
Use it when a question feels bigger than the first answer, several ideas are tangled together, or research has produced more notes than direction. Skip it when the work is already narrow and the next action is obvious.
Prerequisites
Bring one topic, decision, or rough idea. No software setup is required.
The workflow
- Name the central question in one sentence.
- Separate it into decision-changing branches.
- Attach evidence, constraints, assumptions, and unknowns.
- Connect dependencies and conflicts across branches.
- Collapse the tree into the next three decisions or actions.
Common questions
Is this just a mind map?
No. A mind map can capture everything associated with a topic. A Semantic Tree keeps only the branches that change the answer and labels the evidence and uncertainty behind them.
Does every tree need a diagram?
No. Use Markdown when the hierarchy is enough. Use Mermaid only when the relationships are materially easier to understand visually.
It's working if
- The root is one real question rather than a broad subject label.
- Each branch can change the answer or the next action.
- Evidence and assumptions are visibly different.
- The result ends with fewer, clearer decisions than the original prompt.
Where it fits
Use semantic-tree before research, planning, or a consequential decision when
you need to understand the shape of the question first. Its output can feed
research, grill-me, to-spec, or a direct decision.
Try it once
Use the core behavior in one conversation before installation. The repeatable Skill package is the primary path when you want the behavior available across future work.
Build a semantic tree for the topic below. Start with the central question, branch into the few dimensions that genuinely change the answer, connect evidence and assumptions, then end with the next three decisions or actions.
Topic: [describe the idea or decision]
Source & license
Released in EspoAI Skills v0.1.2. The released package is skills/engineering/semantic-tree/SKILL.md.
The public package is MIT-licensed and pinned here to the exact release commit. View the released EspoAI source
Skill package files
The full Skill text as copied from content/skill-vault/skills/semantic-tree/. Supporting agent configuration files stay in that folder.
SKILL.md
---
name: semantic-tree
description: Turn a broad or tangled topic into a structured decision map that connects questions, evidence, assumptions, and next actions. Use when an idea feels larger than the first answer, several concerns are mixed together, or the user needs to see what actually changes the decision before choosing a direction.
---
# Semantic Tree
Build a navigable tree before collapsing a complex subject into an answer.
## Workflow
1. Restate the central question in one sentence. If several questions are
hiding inside it, name them and ask which one owns the tree.
2. Create only branches that can change the answer. Prefer a few meaningful
dimensions over an exhaustive taxonomy.
3. Attach evidence, constraints, assumptions, and unresolved questions to the
branch they affect. Mark which claims are observed, inferred, or unknown.
4. Show important relationships between branches. Call out dependencies,
conflicts, and decisions that unlock several downstream choices.
5. Collapse the tree into the next three decisions or actions. Explain why
those three have the highest leverage.
## Output
Return:
- the central question;
- a compact tree in Markdown or Mermaid when a visual materially helps;
- the evidence and uncertainty attached to each decision-changing branch;
- the three highest-leverage next decisions or actions;
- what should be verified before acting.
Keep the tree editable. Do not turn every note into a permanent branch and do
not hide uncertainty behind a polished diagram.