cookoff
Compare Parallel Implementations
Complex features often have several valid implementation paths. This skill runs independent agent implementations, reviews them, and helps select the strongest result.
Install with my Agent
Copy this request to your Agent. It includes the canonical Skill page and manifest.
Review the Skillstore skill "cookoff" from https://skillstore.io/skills/2389-research-cookoff.md and its manifest at https://skillstore.io/api/skills/2389-research-cookoff/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 "cookoff". Use cookoff for the approved authentication design.
Expected outcome:
The skill recommends three implementations because the feature touches authentication, data flow, and tests. It presents options before dispatching agents.
Using "cookoff". Pick the winner from these cookoff results.
Expected outcome:
The skill compares test status, review findings, design adherence, and maintainability. It recommends the strongest implementation with a short rationale.
Using "cookoff". Finish the cookoff and clean up safely.
Expected outcome:
The skill verifies the winning implementation, records the result summary, lists branches for cleanup, and asks before destructive deletion.
Security Audit
Medium RiskMost static findings are false positives caused by Markdown backticks and fenced examples, not Ruby shell execution. No prompt injection, network reconnaissance, or system reconnaissance evidence was found. The main risk is the cleanup workflow, which can delete worktrees and branches without explicit confirmation.
Confirmed security concerns (1)
Capability review items (1)
These are real local capabilities that may be expected for this skill, so they require review but are not counted as confirmed malicious behavior.
Risk Factors
⚙️ External commands (50)
📁 Filesystem 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-cookoff/audits/8?utm_source=security_passport&utm_medium=share&utm_campaign=versioned_reportMarkdown badge
[](https://skillstore.io/skills/2389-research-cookoff?utm_source=security_passport_badge)HTML badge
<a href="https://skillstore.io/skills/2389-research-cookoff?utm_source=security_passport_badge"><img src="https://skillstore.io/badges/skills/2389-research-cookoff/security.svg" alt="Skillstore security assessment" loading="lazy"></a>Embed card
<iframe src="https://skillstore.io/embed/skills/2389-research-cookoff.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). cookoff security audit report (audit version 8) [Author version unspecified]. Skillstore. https://skillstore.io/skills/2389-research-cookoff/audits/8BibTeX citation
@techreport{2389-research-2389-research-cookoff-2026,
author = {2389-research},
title = {cookoff security audit report (audit version 8)},
institution = {Skillstore},
year = {2026},
number = {8},
url = {https://skillstore.io/skills/2389-research-cookoff/audits/8},
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: "cookoff security audit report (audit version 8)"
version: "unspecified"
type: report
authors:
- name: "2389-research"
date-released: "2026-07-09"
url: "https://skillstore.io/skills/2389-research-cookoff/audits/8"
identifiers:
- type: other
value: "skillstore:2389-research-cookoff:audit:8"
description: "Skillstore immutable audit report identifier"
Skillstore Score
Why this score Evidence Confidence: HighWhat You Can Build
Evaluate Competing Feature Builds
Run several independent implementations of a feature and compare quality before choosing one.
Reduce Design Bias
Let agents create separate plans from the same design instead of sharing one implementation plan.
Document Build Decisions
Capture plans, test results, review notes, and winner rationale for later team review.
Try These Prompts
Use cookoff for this approved design. Recommend the number of implementations and show the options before starting.
Run a three-agent cookoff from the design document. Each agent should write its own plan, implement, test, and report results.
Judge the cookoff results using tests, fresh review findings, design adherence, and maintainability. Explain the winner and rejected options.
Run the full cookoff lifecycle. Create worktrees, coordinate agents, compare outputs, request approval before cleanup, and write the result summary.
Best Practices
- Start from a stable design document so every agent has the same target.
- Ask agents to create independent plans before writing implementation code.
- Review tests, design adherence, and maintainability before selecting a winner.
Avoid
- Do not give every agent the same detailed implementation plan.
- Do not dispatch agents one at a time when the goal is parallel comparison.
- Do not delete worktrees or branches before reviewing the cleanup list.
Frequently Asked Questions
When should I use this skill?
Does it write the design document?
How many agents does it use?
Does it require git worktrees?
Can it work without companion skills?
What should I verify before cleanup?
Developer Details
Author
2389-researchLicense
MIT
Skillstore revision
r1
Version notice
The author did not declare a version.
Ref
0519034dad657fb1f7706e0550e962beeda73fdf
Maintenance freshness
7/18/2026
Usage
13 downloads · 275 views
File structure
📄 SKILL.md