New: 98,000+ skills indexed from GitHub repos with 100+ stars · every skill safety-checkedBrowse top skillsTop skills
Esc to closeBrowse all skills
Submit a skillBrowse skills
Submit a skillBrowse skills

Agent skill

Hypothesis Tree

by sruthir28 in sruthir28/enterprise-ai-skills

Build a Day-1 hypothesis tree — your best-guess answer to the governing question, broken into 2–3 supporting sub-hypotheses, with the test that would prove or kill each one.

MITAuto-check passed

Install Hypothesis Tree

skills CLI
$ npx skills add sruthir28/enterprise-ai-skills --skill hypothesis-tree -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install sruthir28/enterprise-ai-skills hypothesis-tree --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/sruthir28/enterprise-ai-skills.git skills-src && mkdir -p .claude/skills && cp -r skills-src/hypothesis-tree .claude/skills/hypothesis-tree && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
hypothesis-tree
GitHub stars
148
Token cost
~2k tokens
SKILL.md length
852 words
Files
1
Skills in repo
14
Repo updated
First seen
Licence
MIT

At a glance

Build a Day-1 hypothesis tree — your best-guess answer to the governing question, broken into 2–3 supporting sub-hypotheses, with the test that would prove or kill each one.

  • Works in 5 steps: Governing question (e.g., "Should we… → Your gut answer — if you had to decide… → What's the timebox — 2 weeks? 6 weeks?… → …
  • SKILL.md covers Issue tree vs. hypothesis tree, Design choices, Structure and Inputs needed (interview if…, plus 6 more sections
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Hypothesis Tree is an agent skill from sruthir28/enterprise-ai-skills. Build a Day-1 hypothesis tree — your best-guess answer to the governing question, broken into 2–3 supporting sub-hypotheses, with the test that would prove or kill each one. Different from an issue tree (which decomposes the problem space). This commits to an answer before you do the work, so the work targets what would actually change your mind. Use at the start of any analysis where you'd otherwise "boil the ocean."

Its SKILL.md is about 2k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

The repository describes itself as: Open-source AI skills for enterprise professionals. McKinsey consulting frameworks, PM workflows, and practical tools. Currently for Claude, expanding to other LLMs. The licence is MIT.

Example prompts

  • “d otherwise”
  • “/hypothesis-tree”

Workflow steps

5 steps, taken from the first numbered list in SKILL.md.

  1. Governing question (e.g., "Should we enter the European SMB market?")
  2. Your gut answer — if you had to decide today with no more data, what would you say?
  3. What's the timebox — 2 weeks? 6 weeks? Drives how many tests you can run.
  4. What do you already know — existing data, prior research, expert intuition.
  5. What would change your mind — even before testing, name the result that would flip your answer.

What it can do on your machine

Read from SKILL.md and the folder at commit ae8fe60. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    No scripts in the folder and no shell commands in SKILL.md.

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Hypothesis Tree loads about 2k tokens when it runs. Until then it costs about 109 tokens; SKILL.md has 852 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~109
When it runs · the whole SKILL.md, loaded when a task matches
~2k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from sruthir28/enterprise-ai-skills at commit ae8fe60, republished under its MIT licence (© sruthir28). 852 words, ~1,967 tokens.

Download SKILL.mdSave it as .claude/skills/hypothesis-tree/SKILL.md (or your agent's skills folder).
name
hypothesis-tree
description
Build a Day-1 hypothesis tree — your best-guess answer to the governing question, broken into 2–3 supporting sub-hypotheses, with the test that would prove or kill each one. Different from an issue tree (which decomposes the problem space). This commits to an answer before you do the work, so the work targets what would actually change your mind. Use at the start of any analysis where you'd otherwise "boil the ocean."

Hypothesis Tree

A hypothesis tree is your Day-1 best guess, structured so you can disprove it fast. Issue trees decompose the question; hypothesis trees commit to an answer and tell you what to go test.

The McKinsey discipline: don't start work without a hypothesis. Otherwise you research forever, find nothing surprising, and produce a "comprehensive overview" no one acts on.

Issue tree vs. hypothesis tree

Issue TreeHypothesis Tree
TopThe questionThe answer (your guess)
BranchesSub-questions (MECE problem space)Sub-claims that, if true, prove the top claim
BottomAreas to investigateSpecific tests that would kill the claim
Use whenYou don't know what matters yetYou have a strong prior and want to test it efficiently
Risk if skippedYou miss a dimensionYou waste 6 weeks on analysis that doesn't move conviction

Both belong in the consultant toolkit. Issue tree first (frame the space), hypothesis tree second (commit and test). Skipping the hypothesis tree is the #1 reason strategy work takes 3x longer than it should.

Design choices

  • You must commit to a Day-1 answer. "I don't know" is not a hypothesis. Make a guess. Be wrong loudly and fast.
  • 3 sub-hypotheses, not more. If you need 5, your top hypothesis isn't well-formed.
  • Every leaf is a test that could kill the branch. "Do more research" is not a test. "Pull pricing data for 4 competitors and compare to ours" is a test.
  • State conviction explicitly. Each sub-hypothesis gets a confidence (High / Med / Low). Tests focus on the low-conviction branches first — those are where you'll learn the most.
  • Disconfirmation > confirmation. Design tests to kill the hypothesis, not validate it. If you can't think of what would disprove it, you're not testing — you're rationalizing.

Structure

TOP HYPOTHESIS (your Day-1 answer to the governing question)
│
├─ SUB-HYPOTHESIS 1  [confidence: H/M/L]
│  └─ Test: [Specific analysis, named source, kill-criterion]
│
├─ SUB-HYPOTHESIS 2  [confidence: H/M/L]
│  └─ Test: [Specific analysis, named source, kill-criterion]
│
└─ SUB-HYPOTHESIS 3  [confidence: H/M/L]
   └─ Test: [Specific analysis, named source, kill-criterion]

PRIORITY: Test [low-conviction sub] first. Kill-criterion: [what result makes us abandon the top hypothesis].

Inputs needed (interview if missing)

  1. Governing question (e.g., "Should we enter the European SMB market?")
  2. Your gut answer — if you had to decide today with no more data, what would you say?
  3. What's the timebox — 2 weeks? 6 weeks? Drives how many tests you can run.
  4. What do you already know — existing data, prior research, expert intuition.
  5. What would change your mind — even before testing, name the result that would flip your answer.

If the user can't articulate a Day-1 answer, push back. Even a weak guess beats no guess.

Process

  1. Restate the governing question. Sharpen it. "Should we enter Europe?" → "Should we launch in UK + Germany SMB by end of FY?"
  2. State the Day-1 answer. One sentence. Specific. Falsifiable.
  3. Decompose into 3 sub-claims. If all three were true, the top claim must be true. Test the logic: if I prove all three, does the top hold? If I disprove any one, does the top fall?
  4. Assign conviction. H / M / L for each sub.
  5. Design tests. For each sub: what's the specific analysis, what data source, and what result would kill it.
  6. Sequence by conviction. Run low-conviction tests first. They have the most information value.
  7. Set a kill-criterion for the whole tree. What aggregate result makes you abandon the top hypothesis?
Show full SKILL.md (341 more words)Show less

Worked example

Governing question: Should we enter the European SMB market in FY26?

Day-1 Hypothesis: Yes — launch in UK and Germany only, via product-led growth (not sales), starting Q3 FY26. Skip France and Southern Europe in year one.

Tree:

TOP: Launch UK + DE SMB via PLG in Q3 FY26 (skip France / S. Europe year 1)
│
├─ SUB-1: There is real SMB demand in UK + DE  [conviction: High]
│  └─ Test: Pull search volume for our top 5 product terms in UK + DE via SEMrush.
│          Kill if monthly search volume <30% of our US baseline.
│          Cross-check: 2 competitors' EU revenue trajectory from their 10-Ks.
│
├─ SUB-2: PLG works in UK + DE (not just enterprise sales)  [conviction: Low]
│  └─ Test: Stand up localized landing pages, run 2-week paid pilot ($10K).
│          Measure CAC and trial→paid conversion vs. US benchmark.
│          Kill if CAC > 2.5x US or conversion <40% of US.
│
└─ SUB-3: UK + DE specifically (not France/Italy/Spain) is the right wedge  [conviction: Medium]
   └─ Test: Compare 4 dimensions across UK/DE/FR/IT/ES — payment friction (SEPA vs. local),
          language overhead (EN penetration in SMB), regulatory friction (GDPR sub-cases),
          competitor share.
          Kill if France scores higher than DE on 3 of 4 — would force re-sequencing.

PRIORITY: Run Sub-2 first (lowest conviction, highest stakes). 2 weeks, $10K. If PLG fails,
the whole top hypothesis flips to "enter via partner-led sales or don't enter."

OVERALL KILL-CRITERION: If Sub-2 fails AND we can't articulate a sales-led model with <12-month
payback, abandon FY26 entry and revisit FY27 with a partnerships path.

Note how this works: 6 weeks of work become 2 weeks of work, because Sub-2 is the load-bearing assumption. If it fails, you stop — no point testing Subs 1 and 3.

Common mistakes to avoid

  • No top hypothesis. "I want to investigate Europe" is not a hypothesis. Pick an answer.
  • Sub-hypotheses that aren't load-bearing. If proving a sub doesn't change your conviction in the top, it's the wrong sub.
  • Tests that can't kill the branch. "Talk to customers" isn't a test. "Run 10 customer calls; kill if 7+ say price is the blocker" is a test.
  • Sequencing high-conviction first. Wastes the timebox. The whole point is to get to wrong fast.
  • No kill-criterion. Without it, you'll explain away any disconfirming data. Set the bar before you see results.
  • Confusing with issue tree. If your tree branches into sub-questions instead of sub-claims, it's an issue tree. Rewrite each branch as a statement.

When to use

  • Start of any strategic analysis (market entry, pricing, M&A, restructuring)
  • When you've already done an issue tree and need to commit to an answer
  • When the team is about to "go gather data" with no clear hypothesis
  • Before any board ask that begins "we recommend..."

When NOT to use

  • You genuinely don't know enough to guess (do an issue tree first)
  • The question is descriptive, not decision-driving ("what is happening?" vs. "what should we do?")
  • The decision is reversible and small (just try it, don't formalize)

Pairs well with

  • Issue Tree Builder — frame the problem space first, then commit to a hypothesis within it
  • Synthesis — use synthesis output as input to validate or kill specific sub-hypotheses
  • Decision Memo Builder — once you've tested and survived, the surviving hypothesis becomes the recommendation
  • McKinsey Critic — stress-test your tree before you start running tests; cheaper to fix bad framing than bad analysis

© sruthir28, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in hypothesis-tree of sruthir28/enterprise-ai-skills.

Open the folder on GitHubat commit ae8fe60

Compare with similar skills

Hypothesis Tree next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Hypothesis Tree compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Hypothesis Tree this skillsruthir28/enterprise-ai-skills148—~2kAutomated safety check: PassMIT
More Trees AutomationComposioHQ/awesome-claude-skills77k3 repos~742Automated safety check: PassNone
Pierre Trees File Treepierrecomputer/pierre6.2k—~473Automated safety check: PassApache-2.0
Day Booksickn33/agentic-awesome-skills47k1 repos~7kAutomated safety check: PassMIT
Hypothesis Formulationaiming-lab/AutoResearchClaw15k—~628Automated safety check: PassMIT
Hypothesis Generationspacering-net/codeg3.8k15 repos~3.6kAutomated safety check: NotesMIT

Similar skills

  • More Trees Automation

    ComposioHQ/awesome-claude-skills

    Automate More Trees tasks via Rube MCP (Composio). An agent skill from ComposioHQ/awesome-claude-skills.

    77k GitHub starsUsed in 3 repos~742 tokens
    Productivity & AutomationAuto-check passed

  • Pierre Trees File Tree

    pierrecomputer/pierre

    Use when an app uses @pierre/trees to render or control a file tree, including React, vanilla JavaScript, SSR, web components, selection, search, rename, drag…

    6.2k GitHub stars~473 tokensUpdated today
    Frontend & DesignAuto-check passed

  • Day Book

    sickn33/agentic-awesome-skills

    Daily cash, bank and digital day book: opening and closing balances per book, in/out movements, debit/credit presentation and reconciliation status.

    47k GitHub starsUsed in 1 repo~7k tokens
    Business, Finance & HRAuto-check passed

  • Hypothesis Formulation

    aiming-lab/AutoResearchClaw

    Guides turning an observation into testable, falsifiable hypotheses with null and alternative statements, competing explanations and predictions tied to experimental design.

    15k GitHub stars~628 tokensUpdated 1 mo ago
    Research & ScienceAuto-check passed

  • Hypothesis Generation

    spacering-net/codeg

    Structured hypothesis formulation from observations. An agent skill from spacering-net/codeg.

    3.8k GitHub starsUsed in 15 repos~3.6k tokens
    Research & ScienceAuto-check: notes

  • Hypothesis Generation

    foryourhealth111-pixel/Vibe-Skills

    Structured hypothesis formulation from observations. An agent skill from foryourhealth111-pixel/Vibe-Skills.

    3.6k GitHub stars~3.1k tokensUpdated 1 mo ago
    Research & ScienceAuto-check: notes

More from sruthir28/enterprise-ai-skills

All 14 skills in this repo

  • Storyline Builder

    sruthir28/enterprise-ai-skills

    McKinsey-style storyline framework for building presentation decks.

    148 GitHub starsUsed in 1 repo~1.9k tokens
    Auto-check passed

  • AI Use Case Scorer

    sruthir28/enterprise-ai-skills

    Score and prioritize AI use cases for your own job. An agent skill from sruthir28/enterprise-ai-skills.

    148 GitHub stars~1.5k tokensUpdated 1 mo ago
    Auto-check passed

  • Decision Memo Builder

    sruthir28/enterprise-ai-skills

    Builds a 1-page decision memo (context → options → recommendation → risks → ask) enforcing McKinsey memo DNA — brutal brevity, SCP storyline clarity, decision-forcing output, evidence density.

    148 GitHub stars~1.7k tokensUpdated 1 mo ago
    Auto-check passed

  • Deck Pipeline

    sruthir28/enterprise-ai-skills

    Multi-agent pipeline that builds a polished presentation deck from a single topic.

    148 GitHub stars~2.2k tokensUpdated 1 mo ago
    Auto-check passed

  • Issue Tree Builder

    sruthir28/enterprise-ai-skills

    McKinsey-style issue tree framework for breaking down complex problems into MECE (Mutually Exclusive, Collectively Exhaustive) components.

    148 GitHub stars~1.9k tokensUpdated 1 mo ago
    Auto-check passed

  • Mckinsey Charts

    sruthir28/enterprise-ai-skills

    Generate McKinsey-style consulting charts as native python-pptx objects (editable inside PowerPoint).

    148 GitHub stars~999 tokensUpdated 1 mo ago
    Auto-check passed

Questions about Hypothesis Tree

What does Hypothesis Tree do?

Build a Day-1 hypothesis tree — your best-guess answer to the governing question, broken into 2–3 supporting sub-hypotheses, with the test that would prove or kill each one. Hypothesis Tree is an agent skill from sruthir28/enterprise-ai-skills. Build a Day-1 hypothesis tree — your best-guess answer to the governing question, broken into 2–3 supporting sub-hypotheses, with the test that would prove or kill each one.

How do I install Hypothesis Tree in Claude Code?

Run `npx skills add sruthir28/enterprise-ai-skills --skill hypothesis-tree -a claude-code`. Or copy the skill folder (hypothesis-tree in sruthir28/enterprise-ai-skills) into .claude/skills/hypothesis-tree in your project. Claude Code loads it when a task matches its description.

How do I install Hypothesis Tree in Codex?

Run `npx skills add sruthir28/enterprise-ai-skills --skill hypothesis-tree -a codex`. Or copy the skill folder (hypothesis-tree in sruthir28/enterprise-ai-skills) into .agents/skills/hypothesis-tree in your project. Codex loads it when a task matches its description.

Can I use Hypothesis Tree in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add sruthir28/enterprise-ai-skills --skill hypothesis-tree -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/hypothesis-tree, .gemini/skills/hypothesis-tree, .github/skills/hypothesis-tree and .opencode/skills/hypothesis-tree in your project.

What does Hypothesis Tree need to run?

SKILL.md names no scripts, command-line tools or credentials: Hypothesis Tree is instructions for the agent only.

Does Hypothesis Tree access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Hypothesis Tree safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Hypothesis Tree use?

Hypothesis Tree is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Hypothesis Tree use?

About 2k tokens (SKILL.md is roughly 7.9k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Hypothesis Tree?

Skills that share tags, products or a category with Hypothesis Tree: More Trees Automation (ComposioHQ/awesome-claude-skills, 77k stars), Pierre Trees File Tree (pierrecomputer/pierre, 6.2k stars), Day Book (sickn33/agentic-awesome-skills, 47k stars) and Hypothesis Formulation (aiming-lab/AutoResearchClaw, 15k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Hypothesis Tree?

sruthir28 (a GitHub user) maintains it in sruthir28/enterprise-ai-skills, which has 148 GitHub stars. The repository holds 14 skills in this directory. The repository was last updated on September 1, 2026.

Source: sruthir28/enterprise-ai-skills on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.