unbiased-beta-tester SKILL.md skillB

unbiased-beta-tester from wildcard/caro is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.

Install it, pinned
mdr add wildcard/caro/unbiased-beta-tester@v1.0.0

Pins v1.0.0 in mdr.lock. Pin the fingerprint instead.

Audit grade
B, 16 of 17 checks passed
Kind
SKILL.md skill
Repository
wildcard/caro
Path
.claude/skills/unbiased-beta-tester/SKILL.md
Versions recorded
1
Latest version
v1.0.0, committed Jan 6, 2026
Size
15,325 bytes
Repository stars
40
License
AGPL-3.0

Use when users need to simulate unbiased beta testers for CLI tools. Creates tester personas, models their environment, and runs terminal-first exploratory testing based only on documentation and observed terminal output.

Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file the same grade.

What the file says

# Unbiased Beta Tester Skill

## What This Skill Does

This skill creates **unbiased beta tester agents** that simulate real users testing CLI tools. The tester behaves as if they have no internal knowledge of the project, only what they can observe through documentation, websites, and terminal output.

**Key Capabilities:**
- **Profile Builder**: Interactive interview to create detailed tester personas
- **Environment Model**: Configures the tester's simulated environment (OS, shell, tools)
- **Test Runner**: Executes terminal-first exploration following documentation
- **Evidence Collector**: Captures commands, outputs, errors, and logs
- **Issue Composer**: Generates GitHub issue reports following project templates

## The Unbiasedness Principle

The core innovation is **controlled ignorance**. The agent must behave as if:

1. It does NOT know anything beyond:
   - The beta tester profile (prior knowledge, habits, OS, tooling)
   - Public product materials it reads (docs/website/README)
   - Terminal outputs it observes during testing

2. It must NOT use hidden knowledge from being in the same project
…

Read the whole file at its exact version.

How to install

The exact contents, by fingerprint
mdr add wildcard/caro/unbiased-beta-tester@sha256:c46b33a00922fb53

The line at the top of this page pins the label v1.0.0, which is what most people want. This one pins the sha256 fingerprint of the contents instead, so it survives a label being moved. Either way the exact version is written to mdr.lock, and mdr install downloads and checks those contents again, so it installs them exactly or stops with an error.

Badge

mdr badge

[![mdr](https://markdownregistry.com/badge/art_2x4ctzmvan7ay3dy.svg)](https://markdownregistry.com/a/art_2x4ctzmvan7ay3dy)

2 badge image fetches in 30 days. What the badge shows.

Versions

The registry has recorded 1 version of this file, committed on Jan 6, 2026.

versioncommittedcommitsizeaudit
v1.0.0 latest2026-01-06 bbb7c7e 15,325 BB view

Audit of the latest version

B  16 of 17 checks passed. Fixed automatic checks with no AI involved, so the same checks give the same answer every run.
  • fail: No curl or wget piped into a shell (matched: curl -fsSL https://raw.githubusercontent.com/wildcard/caro/main/install.sh | bash)
  • pass: Frontmatter block present
  • pass: Frontmatter declares a name
  • pass: Frontmatter declares a description
  • pass: Size between 200 bytes and 200 KB (15325 bytes)
  • pass: No zero-width or bidi control characters
  • pass: No instruction hidden inside an HTML comment
  • pass: No link to an exfiltration or paste host
  • pass: No credential-shaped string
  • pass: No instruction to send local credentials anywhere
  • pass: No text hidden with inline styles
  • pass: No prompt-injection phrasing
  • pass: No recursive delete of root, home or parent
  • pass: No instruction to read or print local credentials
  • pass: No base64 blob over 200 characters
  • pass: No link to a raw IP address
  • pass: No script tag

Starting a new one? Use a template for SKILL.md on mdpantry, which passes every one of these checks and says what to change in it.

Source

GitHub

wildcard/caro · 40 stars · license AGPL-3.0 · pushed 2026-10-19 · branch main

API

GET https://markdownregistry.com/api/v1/artifacts/art_2x4ctzmvan7ay3dy
GET https://markdownregistry.com/api/v1/resolve?ref=wildcard/caro/unbiased-beta-tester
GET https://markdownregistry.com/api/v1/blob/c46b33a00922fb53385cae73be88ae8bf66c4c4e21cae7f3a858a3336c083e20

Your AI assistant does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.

Guides: the SKILL.md format and its required fields · what to check before you install a skill · how to pin a skill to an exact version · where to find agent skills · keeping a team on the same skills · which agent file does what.

More from wildcard/caro

spec-kitty-git-workflow SKILL.md skill
wildcard/caro · .agents/skills/spec-kitty-git-workflow/SKILL.md · Understand how Spec Kitty manages git: what git operations Python handles automatically, what agents must do manually…
git:20260427.b2f2f5b · audit A · 40 stars
spec-kitty-mission-system SKILL.md skill
wildcard/caro · .agents/skills/spec-kitty-mission-system/SKILL.md · Understand how Spec Kitty missions work: the 4 built-in mission types, how they define workflows via step contracts and…
git:20260427.b2f2f5b · audit A · 40 stars
speckit-git-commit SKILL.md skill
wildcard/caro · .agents/skills/speckit-git-commit/SKILL.md · Auto-commit changes after a Spec Kit command completes
git:20260427.b2f2f5b · audit A · 40 stars
speckit-git-feature SKILL.md skill
wildcard/caro · .agents/skills/speckit-git-feature/SKILL.md · Create a feature branch with sequential or timestamp numbering
git:20260427.b2f2f5b · audit A · 40 stars
speckit-git-initialize SKILL.md skill
wildcard/caro · .agents/skills/speckit-git-initialize/SKILL.md · Initialize a Git repository with an initial commit
git:20260427.b2f2f5b · audit A · 40 stars
speckit-git-remote SKILL.md skill
wildcard/caro · .agents/skills/speckit-git-remote/SKILL.md · Detect Git remote URL for GitHub integration
git:20260427.b2f2f5b · audit A · 40 stars
speckit-git-validate SKILL.md skill
wildcard/caro · .agents/skills/speckit-git-validate/SKILL.md · Validate current branch follows feature branch naming conventions
git:20260427.b2f2f5b · audit A · 40 stars
AGENTS.md@.claude AGENTS.md file
wildcard/caro · .claude/AGENTS.md
git:20260124.5839cb3 · audit A · 40 stars
session-discovery SKILL.md skill
wildcard/caro · .claude/plugins/session-wrangler/skills/session-discovery/SKILL.md
git:20260124.b94838f · audit C · 40 stars
ai-marketing-engineering SKILL.md skill
wildcard/caro · .claude/skills/ai-marketing-engineering/SKILL.md · AI-powered marketing engineering skill based on Alon Huri's framework. Transforms marketing from copywriting to…
v1.0.0 · audit A · 40 stars
ai-prompt-engineer SKILL.md skill
wildcard/caro · .claude/skills/ai-prompt-engineer/SKILL.md · AI engineering skill for prompt optimization, context inference, and intelligent command routing across different…
v1.0.0 · audit A · 40 stars
backend-safety-integrator SKILL.md skill
wildcard/caro · .claude/skills/backend-safety-integrator/SKILL.md · Guide for integrating safety validation into new inference backends
git:20260108.c3a4b5c · audit B · 40 stars

Every file in wildcard/caro

Browse by kind, by grade B, or by owner.