Skip to content
Agentmart
Submit a tool

bell-design-verdict

How to judge whether a Bell geo-experiment design is sound.

Skill by Korem-consulting

IndexedApache-2.0
Write a review

Install

Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.

npx agentmarket install skill/korem-consulting-bell-design-verdict

Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.

Get the weekly diff

The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.

We use your email only for this newsletter. Privacy

About

How to judge whether a Bell geo-experiment design is sound. Explains the green/yellow/red verdict (historical fit, residual autocorrelation, history length), why the R²-only "strong/moderate/weak" verdict must be ignored, and how to read MDE, budget, R² and treatment proportion. Use after a design analysis or allocation search returns, before telling a client whether to run the test.

Use cases: design, testing, finance

Reviews

Write a review

No reviews yet. Installed it? Reviews come from verified installers only. How reviews work

Permissions

What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.

Tools
No tools found
Secrets
None asked for
Install scripts
None found

Network hosts it talks to 1

  • codeload.github.com · found in install command

Files it touches

  • ~/.claude/skills/bell-design-verdict

What's inside

Skill name
bell-design-verdict
Description
How to judge whether a Bell geo-experiment design is sound. Explains the green/yellow/red verdict (historical fit, residual autocorrelation, history length), why the R²-only "strong/moderate/weak" verdict must be ignored, and how to read MDE, budget, R² and treatment proportion. Use after a design analysis or allocation search returns, before telling a client whether to run the test.
License
Apache-2.0
Metadata
source: Korem-consulting/bell-skills
Instructions
19 lines in SKILL.md · view on GitHub

Files (2)

  • SKILL.md
  • design-verdict.md · references/

Read SKILL.md on GitHub

More from Korem-consulting/bell-skills

Signals

Stars
0
Forks
0
Open issues
0
Last commit (this folder)
Oct 13, 2026 (16 days ago)

From GitHub (fetched Oct 24, 2026).

Details

License
Apache-2.0
Repository
github.com/Korem-consulting/bell-skills
First seen
Oct 24, 2026
Last checked
Oct 24, 2026
Source
GitHubgithub-graphql

More from Korem-consulting

Cite this page

bell-design-verdict skill. Agent Mart. https://agentmart.dev/skills/korem-consulting-bell-design-verdict (last updated 2026-10-24)