Agent Plugins Marketplace
← All plugins

research-method

v0.1.0

Method skills that are not about Kotlin: running a time-boxed study, spike or measurement campaign so its verdicts survive review — a pre-registered brief frozen by script, a stand that is pinned, controls that prove every harness can fail, a protocol with a ruler, and a verdict per question with every number traceable to its log.

Claude Code1 Skill

By youndieLicense: MIT1 GitHub starsUpdated 1 hour ago

Directory evidence

Runtimes
Claude Code
Parsed components
1 skill or MCP entry
Source updated
Oct 2, 2026
Manifest status
Canonical path parsed

The directory validates manifest shape and source location. It does not execute the plugin or provide a security endorsement. Review the indexing methodology →

Install research-method for Claude Code

Installs for the current user
claude plugin marketplace add IchenDEV/agent-plugin-mkt
claude plugin marketplace update agent-plugin-marketplace
claude plugin install research-method@agent-plugin-marketplace

Paste and run these commands in a terminal with Claude Code. They add and refresh the PluginsMP catalog, then install this plugin.

The installer fetches third-party code from the source repository shown on this page. This directory validates manifest structure and source location, but does not perform a security audit; review the manifest, components, and source before installing.

Get the source manually
git clone https://github.com/youndie/kotlin-skills

Clone the source repository, then follow its setup instructions to add the plugin to a compatible client. The plugin root is plugins/research-method/.

Plugin files

plugins/research-method/
├── .claude-plugin/plugin.json
└── skills/measurement-study/SKILL.md

Included Skills1

measurement-studyskills/measurement-study/SKILL.md

Run a time-boxed study, spike or measurement campaign so its verdicts survive review: pre-register questions, thresholds, kill criteria and per-step budgets before the first number (frozen by scripts/brief_freeze.py), pin the stand, prove every harness can fail with a positive control, measure by protocol (interleaved arms, a ruler, the generator off the subject's cores, CPU per request rather than rps), keep raw logs as the deliverable, write one verdict per question: green, grey, red or not measured. Also for one measurement inside a product backlog item. Use for 'spike', 'research study', 'benchmark this', 'A/B the build', 'is it faster', 'soak test', 'проведи исследование', 'спайк', 'замерь', 'сравни варианты', 'бенчмарк', 'нагрузочный прогон'. Not for the documentation tree (docs-bootstrap), working a backlog one pull request at a time (backlog-item), or picking a server engine from numbers already measured (kmp-project-structure).

Plugin manifests1

plugins/research-method/.claude-plugin/plugin.json
{
  "name": "research-method",
  "description": "Method skills that are not about Kotlin: running a time-boxed study, spike or measurement campaign so its verdicts survive review — a pre-registered brief frozen by script, a stand that is pinned, controls that prove every harness can fail, a protocol with a ruler, and a verdict per question with every number traceable to its log.",
  "version": "0.1.0",
  "author": {
    "name": "youndie"
  },
  "repository": "https://github.com/youndie/kotlin-skills",
  "license": "MIT"
}

For maintainers

If you maintain this plugin, link to this source-backed listing from your README so users can review its manifest and indexed components.

[research-method on Agent Plugins Marketplace](https://pluginsmp.com/plugins/research-method)