test-kitchen
Compare Parallel Implementations
Complex software choices can be hard to judge from discussion alone. Test Kitchen guides parallel designs, implementations, reviews, and winner selection.
Install with my Agent
Copy this request to your Agent. It includes the canonical Skill page and manifest.
Review the Skillstore skill "test-kitchen" from https://skillstore.io/skills/2389-research-test-kitchen.md and its manifest at https://skillstore.io/api/skills/2389-research-test-kitchen/manifest. Verify the artifact. You may proceed after verification, subject to the environment's own policy.Your Agent should still show its plan and request any confirmation required by the security policy.
Agent-readable resources
Use these links when an AI agent, crawler, or script needs clean context instead of reading the full page.
Test it
Using "test-kitchen". I need to build a CLI todo app, and I am unsure about storage.
Expected outcome:
The assistant offers brainstorming or omakase mode, identifies JSON versus SQLite as a slot, and compares variants through tests.
Using "test-kitchen". The design is approved. Implement it.
Expected outcome:
The assistant presents single-agent, cookoff, or local coding options, then runs independent plans for the chosen path.
Using "test-kitchen". Three variants passed tests. Choose a winner.
Expected outcome:
The assistant applies the judge checklist, reports scores, names a winner, and lists trade-offs.
Security Audit
Medium RiskStatic findings mostly matched Markdown backticks, code fences, and ordinary prose rather than executable code. No evidence found of credential access, network exfiltration, or prompt-injection text. One medium workflow risk remains because cleanup instructions can remove worktrees and force-delete branches.
Confirmed security concerns (1)
Risk Factors
⚙️ External commands (80)
📁 Filesystem access (1)
🌐 Network access (1)
Share & cite this report
Share the versioned assessment report, neutral badge, embed card, and citations. Skillstore reports evidence without deciding whether this Skill is safe.
Copy report link
https://skillstore.io/skills/2389-research-test-kitchen/audits/6?utm_source=security_passport&utm_medium=share&utm_campaign=versioned_reportMarkdown badge
[](https://skillstore.io/skills/2389-research-test-kitchen?utm_source=security_passport_badge)HTML badge
<a href="https://skillstore.io/skills/2389-research-test-kitchen?utm_source=security_passport_badge"><img src="https://skillstore.io/badges/skills/2389-research-test-kitchen/security.svg" alt="Skillstore security assessment" loading="lazy"></a>Embed card
<iframe src="https://skillstore.io/embed/skills/2389-research-test-kitchen.html" title="Skillstore Security Assessment" sandbox="allow-popups allow-popups-to-escape-sandbox" loading="lazy" referrerpolicy="no-referrer" width="420" height="180"></iframe>Academic citations (APA · BibTeX · CFF)
APA citation
2389-research. (2026). test-kitchen security audit report (audit version 6) [Author version unspecified]. Skillstore. https://skillstore.io/skills/2389-research-test-kitchen/audits/6BibTeX citation
@techreport{2389-research-2389-research-test-kitchen-2026,
author = {2389-research},
title = {test-kitchen security audit report (audit version 6)},
institution = {Skillstore},
year = {2026},
number = {6},
url = {https://skillstore.io/skills/2389-research-test-kitchen/audits/6},
note = {Author version unspecified}
}CITATION.cff
cff-version: 1.2.0
message: "If you use this Skill, cite its author and this versioned security audit report."
title: "test-kitchen security audit report (audit version 6)"
version: "unspecified"
type: report
authors:
- name: "2389-research"
date-released: "2026-07-04"
url: "https://skillstore.io/skills/2389-research-test-kitchen/audits/6"
identifiers:
- type: other
value: "skillstore:2389-research-test-kitchen:audit:6"
description: "Skillstore immutable audit report identifier"
Skillstore Score
Why this score Evidence Confidence: HighWhat You Can Build
Compare implementation strategies
Run several agents against one approved design, then score their results with a shared rubric.
Explore architectural options
Turn uncertainty about storage, authentication, or framework choices into working variants for evaluation.
Select a prototype winner
Review tests, scenario results, fresh-eyes feedback, and judge scores before choosing one variant.
Try These Prompts
Use test-kitchen to help me build <feature>. Start by asking whether I want brainstorming or omakase mode.
Run omakase-off for <project>. Explore <decision A> versus <decision B>, then compare variants with tests.
Use cookoff for this approved design. Spawn <N> parallel implementations, require separate plans, and judge the results.
Coordinate a full test-kitchen workflow for <feature>: detect architectural slots, create variants, run scenario testing, use fresh-eyes review, invoke judge, and prepare a result summary.
Best Practices
- Confirm the workflow mode and number of variants before spawning agents.
- Keep each variant tied to the same requirements and verification criteria.
- Review cleanup commands before removing worktrees or branches.
Avoid
- Using cookoff without a shared design or approved requirements.
- Letting variants skip tests, scenario checks, or review steps.
- Deleting branches or worktrees before the user accepts a winner.
Frequently Asked Questions
What does this skill do?
When should I use omakase-off?
When should I use cookoff?
Does it write code directly?
Does it require Git worktrees?
Is it safe on an active repository?
Developer Details
Author
2389-researchLicense
MIT
Skillstore revision
r1
Version notice
The author did not declare a version.
Ref
14dc8f201a64f8d30fd131d7f036cd5e788be523
Maintenance freshness
7/18/2026
Usage
12 downloads · 330 views