deepresearch
深度研究插件（2026架构）- Task-Centric任务驱动型研究系统。DGoT动态优化降低50%成本，Agentic RAG精度99%，支持8种输出格式
By lazygophersLicense: AGPL-3.0-or-later4 GitHub starsUpdated yesterday
Directory evidence
- Runtimes
- Claude Code
- Parsed components
- 6 skill or MCP entries
- Source updated
- Sep 23, 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 deepresearch for Claude Code
claude plugin marketplace add IchenDEV/agent-plugin-mkt
claude plugin marketplace update agent-plugin-marketplace
claude plugin install deepresearch@agent-plugin-marketplacePaste 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/lazygophers/ccpluginClone the source repository, then follow its setup instructions to add the plugin to a compatible client. The plugin root is plugins/tools/deepresearch/.
Plugin files
├── .claude-plugin/plugin.json├── skills/deep-research/SKILL.md├── skills/evidence-synthesizer/SKILL.md├── skills/report-writer/SKILL.md├── skills/research-planner/SKILL.md├── skills/source-retriever/SKILL.md└── skills/source-validator/SKILL.md
Included Skills6
This skill should be used when the user asks to "research X", "deep dive into X", "compare A vs B", "evaluate this project", or requests evidence-backed technical research, architecture review, or technology selection.
This skill should be used when the user needs to synthesize research evidence into conclusions and recommendations. Typical triggers include summarizing evidence, reconciling conflicting sources, or deriving recommendations.
This skill should be used when the user needs a structured research report or formatted output. Typical triggers include writing executive summaries, technical reports, comparison tables, or checklists.
This skill should be used when the user needs to plan a research investigation or clarify research scope and questions. Typical triggers include creating a research plan, defining research questions, or structuring a study. Use when planning or scoping research tasks.
This skill should be used when the user needs to retrieve sources for research or build a source list. Typical triggers include collecting sources, searching for documentation, or assembling references.
This skill should be used when the user needs to validate sources, verify claims, or rate evidence quality. Typical triggers include verifying citations, checking credibility, or rating sources.
Plugin manifests1
{
"name": "deepresearch",
"description": "深度研究插件（2026架构）- Task-Centric任务驱动型研究系统。DGoT动态优化降低50%成本，Agentic RAG精度99%，支持8种输出格式",
"author": {
"name": "lazygophers",
"email": "[email protected]",
"url": "https://github.com/lazygophers"
},
"homepage": "https://github.com/lazygophers/ccplugin/tree/master/plugins/tools/deepresearch",
"repository": "https://github.com/lazygophers/ccplugin/tree/master/plugins/tools/deepresearch",
"license": "AGPL-3.0-or-later",
"keywords": [
"deep-research",
"dgot",
"agentic-rag",
"graphrag",
"task-centric",
"multi-agent",
"fot-framework",
"a2a-protocol",
"2026",
"research",
"analysis",
"synthesis"
],
"agents": [
"./agents/code-analyst.md",
"./agents/research-strategist.md",
"./agents/project-assessor.md",
"./agents/architecture-advisor.md"
],
"skills": "./skills"
}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.
[deepresearch on Agent Plugins Marketplace](https://pluginsmp.com/plugins/deepresearch)