Agent Plugins Marketplace
← All plugins

smartthink

v3.0.2

Context arming engine for Claude Code: routes your task through Cynefin diagnosis, loads only the mental-model references it needs (81 models, 12 engines, TRIZ), synthesizes task-specific research into an armory pack, and primes the session before you start working. Evolves per user via profile + evolution vault.

Claude Code1 Skill

By BkankimLicense: MIT0 GitHub starsUpdated 1 hour ago

Directory evidence

Runtimes
Claude Code
Parsed components
1 skill or MCP entry
Source updated
Sep 26, 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 smartthink 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 smartthink@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/Bkankim/smartthink

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

Plugin files

smartthink/
├── .claude-plugin/plugin.json
└── skills/smartthink/SKILL.md

Included Skills1

smartthinkskills/smartthink/SKILL.md

ALWAYS use this skill before business strategy, competitive analysis, or complex decisions - it arms the session with 81 mental models, 12 thinking engines, and TRIZ frameworks that Claude cannot replicate from general knowledge alone. It does not answer the question: it builds an armory pack (selected reference verbatim + task-fitted application layer + researched domain synthesis), loads it into the session, prints a briefing, and hands the work back to you fully armed. Triggers: "/smartthink", "/st", "무장", "arm", "천재적 사고", "genius thinking", "전략", "strategy", "깊이 분석", "분석해줘", "고민", "해자", "moat", "PMF", "피봇", "스케일링", "네트워크 효과", "제1원리", "first principles", "경쟁사", "비즈니스 모델", "아이디어", "기회", "의사결정", "mental model", "멘탈 모델", "프레임", "framework", "TRIZ", "Cynefin", or any Korean/English request involving strategic thinking, market analysis, business decisions, opportunity evaluation, or competitive positioning. Lifecycle subcommands: "/st init" (profile), "/st retain" (evolution), "/st status" (diagnostics).

Plugin manifests1

.claude-plugin/plugin.json
{
  "name": "smartthink",
  "version": "3.0.2",
  "description": "Context arming engine for Claude Code: routes your task through Cynefin diagnosis, loads only the mental-model references it needs (81 models, 12 engines, TRIZ), synthesizes task-specific research into an armory pack, and primes the session before you start working. Evolves per user via profile + evolution vault.",
  "author": {
    "name": "Bkankim",
    "url": "https://github.com/Bkankim"
  },
  "homepage": "https://github.com/Bkankim/smartthink",
  "repository": "https://github.com/Bkankim/smartthink",
  "license": "MIT",
  "keywords": [
    "mental-models",
    "context-engineering",
    "thinking",
    "cynefin",
    "triz",
    "priming",
    "korean"
  ]
}

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.

[smartthink on Agent Plugins Marketplace](https://pluginsmp.com/plugins/smartthink)