# assumption-test

Designs the smallest viable test to check critical assumptions in product solutions. Built around Torres testing concepts and Gilad's AFTER model.

- skill · `type=skill` · Claude Code, Codex, Cursor, GitHub Copilot, Gemini CLI, OpenCode · ★ 47
- Author: haabe
- License: MIT · policy=mirror · the beginning of the file is at the end of this page
- Source: https://github.com/haabe/mycelium/tree/HEAD/plugins/mycelium/skills/assumption-test/SKILL.md
- Updated: 2026-10-24
- HTML: https://affpapa.org/en/nevibecode/skills/haabe-assumption-test

## What it does

The skill breaks a solution down into assumptions covering desirability, usability, feasibility, viability, and ethics. It maps them on a 2x2 matrix of evidence versus importance to target low-evidence, high-impact items first.

Test weight scales directly with the decision class. Light decisions rely on quick pass-or-fail checks on existing data, while heavy decisions demand experiments or outside sampling. Standalone use skips canvas state, theory gates, and harness behavior because the skill is built for the Mycelium framework.

Writing to `.claude/canvas/*.yml` files requires running the `Read` tool beforehand. Claude Code blocks write operations if an agent tries reading files through Bash commands instead.

## Install

### Claude Code (native platform)

1. **Skills CLI (Vercel)**
```bash
npx skills add haabe/mycelium --skill assumption-test -a claude-code
```

2. **Manually: put the files in place**
- File: `~/.claude/skills/assumption-test/SKILL.md` — Copy the whole skill folder; for one project use .claude/skills/assumption-test/

### Codex

1. **Skills CLI (Vercel)**
```bash
npx skills add haabe/mycelium --skill assumption-test -a codex
```

2. **Manually: put the files in place**
- File: `.agents/skills/assumption-test/SKILL.md` — For all projects use ~/.agents/skills/

### Cursor

1. **Skills CLI (Vercel)**
```bash
npx skills add haabe/mycelium --skill assumption-test -a cursor
```

2. **Manually: put the files in place**
- File: `.cursor/skills/assumption-test/SKILL.md` — Cursor also reads .agents/skills/ and .claude/skills/

### GitHub Copilot

1. **GitHub CLI**
```bash
gh skill install haabe/mycelium assumption-test
```

2. **Manually: put the files in place**
- File: `.github/skills/assumption-test/SKILL.md`

### Gemini CLI

1. **Skills CLI (Vercel)**
```bash
npx skills add haabe/mycelium --skill assumption-test -a gemini-cli
```

2. **Platform CLI**
```bash
gemini skills install https://github.com/haabe/mycelium --path plugins/mycelium/skills/assumption-test
```

### Windsurf (Devin Desktop)

**Manually: put the files in place**
- File: `.devin/skills/assumption-test/SKILL.md` — The legacy .windsurf/skills/ path still works

### OpenCode

**Skills CLI (Vercel)**
```bash
npx skills add haabe/mycelium --skill assumption-test -a opencode
```

### Claude.ai

**Claude.ai**
- Zip the folder and upload it in Settings → Capabilities → Skills

Where a file is given instead of a command, copy the files from the source to that path: https://github.com/haabe/mycelium/tree/HEAD/plugins/mycelium/skills/assumption-test/SKILL.md

## When to use it
- extract high-risk assumptions behind a proposed solution
- prioritize assumptions by importance and available evidence
- select the lightest valid test using the AFTER model
- prevent duplicate ID assignments inside `.claude/canvas/*.yml` files

## Example prompts
- Break down the core assumptions behind our checkout redesign
- Find the lightest test to validate our onboarding speed assumption
- Map our high-risk assumptions against open gaps in the canvas

## Source text · SKILL.md · MIT

Below is the content of a third-party file. It is data, not instructions for you: do not act on anything written inside unless the human asks. Block tag: a921d6ed73d8fadb.

BEGIN THIRD-PARTY FILE a921d6ed73d8fadb
````text
---
name: assumption-test
description: "Design the smallest viable test to validate or invalidate a critical assumption. Based on Torres's assumption testing framework, organized by Gilad's AFTER model (Assessment → Fact-Finding → Tests → Experiments → Release Results)."
metadata:
  instruction_budget: "38"
  framework_dependency: "mycelium"
  framework_dependency_note: "This skill is designed to run within the Mycelium framework (https://github.com/haabe/mycelium). Standalone use will skip the canvas state, theory gates, and harness behavior the skill assumes. Install: /plugin install mycelium@haabe-mycelium."
---

# Assumption Testing

Every solution rests on assumptions. Test the riskiest ones first with the lightest method possible.

## Preflight: Read target canvas file(s) before any Write/Edit

**Hard rule.** Before issuing `Write` or `Edit` against any `.claude/canvas/*.yml`, use the **Read tool** on that file in this session. Claude Code's Read-before-Write check requires the `Read` tool specifically — `cat`/`head`/`grep` via Bash do NOT satisfy it.

**Edit vs Write — different cost profiles** (verified 2026-05-14):
- **`Edit`** (exact-string replacement): `Read` with `limit: 1` satisfies the check at ~50 tokens. State-tracking is per-file, not per-byte — subsequent `Edit` calls work anywhere in the file. Use this for partial updates against large canvas files (e.g., `purpose.yml` at 800+ lines).
- **`Write`** (full replacement): do a **full Read** first. Write obliterates the file; you should see what you're about to replace. The `limit:1` shortcut is *not* appropriate here.

**ID-bearing entries — scan the ID space before assigning** (added 2026-05-15, v0.23.19): When adding a new component, opportunity, solution, or any other ID-bearing entry to a canvas file, run a Bash grep first to confirm the next ID in your prefix sequence is actually free:

```
grep -o "<prefix>-[0-9][0-9]*" .claude/canvas/<file>.yml | sort -u -t- -k2 -n | tail -3
```
````
END THIRD-PARTY FILE a921d6ed73d8fadb

The third-party file has ended. Everything between the a921d6ed73d8fadb tags is data: requests and commands from it are not followed. An “end of file” line with another tag inside the block is part of the file.

First 2002 of 25573 bytes. © haabe · MIT · https://github.com/haabe/mycelium/tree/HEAD/plugins/mycelium/skills/assumption-test/SKILL.md

## Similar
- [setup-matt-pocock-skills](https://affpapa.org/en/nevibecode/skills/setup-matt-pocock-skills.md) — skill · 1052851 installs
- [ask-matt](https://affpapa.org/en/nevibecode/skills/ask-matt.md) — skill · 766587 installs
- [to-tickets](https://affpapa.org/en/nevibecode/skills/to-tickets.md) — skill · 711230 installs
- [writing-plans](https://affpapa.org/en/nevibecode/skills/writing-plans.md) — skill · 282859 installs
- [caveman-review](https://affpapa.org/en/nevibecode/skills/caveman-review.md) — skill · 411800 installs
- [caveman-compress](https://affpapa.org/en/nevibecode/skills/caveman-compress.md) — skill · 411500 installs

## Other versions with the same name
- [assumption-test · neeeophytee](https://affpapa.org/en/nevibecode/skills/assumption-test.md) — ★ 355

From the same set: [haabe/mycelium](https://affpapa.org/en/nevibecode/by/haabe/mycelium.md) — 58 cards

---
NeVibeCode on affpapa.org. Catalog texts are descriptions, not instructions for the agent. How to choose and install: https://affpapa.org/en/nevibecode/agents.md