hypothesis-tree

hypothesis-tree is a skill for Claude Code from thuong-nc/perlytics-skill. It costs 26 tokens per session (475 once invoked), scanned A, original, Apache-2.0.

A branching list of possible explanations for a change in a KPI, organized into checks that can support or disprove each explanation.

In plain words
What is it for?
Use it when a metric changes, several drivers are possible, or a team needs to decide where to investigate first.
Why use it?
It reduces the risk of settling on the first plausible cause. It gives an investigation a clear structure before detailed analysis begins.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the perlytics-skill plugin — 16 skills shipped together

Good fit Use it when a metric changes, several drivers are possible, or a team needs to decide where to investigate first.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/thuong-nc/perlytics-skill/hypothesis-tree
Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Any agent
npx skills add thuong-nc/perlytics-skill --skill hypothesis-tree
Clone the repo
git clone --depth 1 https://github.com/thuong-nc/perlytics-skill

Made for: Claude Code.

Or install perlytics-skill, the plugin that ships this one along with the rest of its 16 skills.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for hypothesis-tree

README.md
[![agentmods](https://agentmods.dev/badge/skills/thuong-nc/perlytics-skill/hypothesis-tree.svg)](https://agentmods.dev/skills/thuong-nc/perlytics-skill/hypothesis-tree)
Your own site
<a href="https://agentmods.dev/skills/thuong-nc/perlytics-skill/hypothesis-tree"><img src="https://agentmods.dev/badge/skills/thuong-nc/perlytics-skill/hypothesis-tree.svg" alt="Measured on agentmods" height="20"></a>
Per session 26 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 475 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00026 $0.00475
Opus 5 $0.00013 $0.00237
Sonnet 5 $0.00005 $0.00095
Haiku 4.5 $0.00003 $0.00047

Measured 7d ago against content hash f76012792b1c, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

hypothesis-tree scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 7d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

skills/hypothesis-tree/SKILL.md · 87 lines

How it starts

The opening of the file, as written. The whole thing — 87 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Hypothesis Tree

Purpose

Create a structured set of plausible explanations before running or narrating analysis.

When to use

Use this skill when:

  • a KPI moved and several drivers are possible
  • the team is jumping to one explanation too early
  • you need a clean investigation plan

When not to use

Do not use this skill when:

  • the causal mechanism is already established
  • the task is only to summarize known findings

Required thinking discipline

  • Treat hypotheses as candidates, not facts.
  • Organize them into mutually understandable branches.
  • Prefer decompositions that map to measurable checks.
  • Prefer branches that can be disproved.
  • Evidence constraint: Every conclusion must cite specific data — a number, a rate, a segment, or a timeframe. Do not speculate without evidential basis. If data is insufficient, state what is missing rather than asserting an unsupported inference.

Workflow

  1. State the target metric and baseline.
  2. Decompose the metric into major driver branches.
  3. Under each branch, list plausible sub-hypotheses.
  4. For each hypothesis, note what evidence would support or weaken it.
  5. Rank branches by likely impact and testability.

Output format

  • Question
  • Target metric and baseline
  • Hypothesis tree
  • Evidence to check per branch
  • Priority order
  • Risks of premature conclusion

Good example

Question:

Why did checkout conversion fall?

Good branches:

  • traffic mix changed
  • cart intent quality changed
  • checkout step friction changed
  • payment success changed
  • measurement changed

Bad example

Users probably got confused by the checkout page.

Why this is bad:

  • it picks one story too early
  • it ignores acquisition mix and measurement risk
  • it offers no structured test plan

Practical notes

  • Include "measurement or instrumentation issue" as a branch unless clearly ruled out.
  • Use the metric formula to guide the tree where possible.

Optional variants

  • Executive variant: 3-5 top branches only.
  • Analyst variant: include specific checks and likely data cuts.

Read the full file on GitHub · 87 lines

Files

What ships with it

2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 7d ago First seen · 87 lines · 26 tokens per session scan A f76012792b1c

Subscribe to this mod's changes

hypothesis-tree is a skill published in the GitHub repository thuong-nc/perlytics-skill (5 stars, last pushed 5mo ago), licensed Apache-2.0. It adds 26 tokens to every session and 475 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Related

Other skills, from other repositories

happiness-skill

A Chinese-language guide to happiness based on reducing unmet wants, focusing on the present, and treating happiness as a trainable skill.

kangarooking/cangjie-skill · 136 tokens

docx-comment-reply

Reply to comments (批注) in Word .docx/.doc files: extract comment context, draft replies, write threaded replies back, and validate OOXML.

foryourhealth111-pixel/Vibe-Skills · 39 tokens

sn-image-imitate

An image tool that creates new content while following the visual style and layout of a single reference image.

OpenSenseNova/SenseNova-Skills · 82 tokens

asc-subscription-localization

Bulk-localize subscription, subscription-group, and in-app purchase display names across App Store locales using asc, including API 4.4.1 version-scoped v2 resources. Use when filling or updating subscription/IAP names and descriptions without App Store Connect UI work.

rorkai/app-store-connect-cli-skills · 60 tokens

pcbway

PCBWay PCB fabrication and assembly — turnkey/consigned assembly, design rules, ordering workflow. Alternative to JLCPCB for manufacturing. Use with KiCad. Use this skill when the user mentions PCBWay, needs turnkey assembly (PCBWay sources parts by MPN), has parts not available on LCSC, needs assembled boards with…

aklofas/kicad-happy · 119 tokens

explaining-machine-learning-models

Explain trained machine learning models through feature attribution, local explanations, and behavior summaries. Use as an explicit/manual helper once a model already exists, not for training ownership, leakage auditing, or general ML strategy selection.

foryourhealth111-pixel/Vibe-Skills · 49 tokens