By git-fg
RESEARCH & KNOWLEDGE DOMAIN - Research tools, knowledge retrieval, codebase analysis, gitingest, and experimental analysis
npx claudepluginhub git-fg/thecattoolkitStatistical analysis toolkit for hypothesis testing, regression, correlation, Bayesian statistics, power analysis, and APA reporting. USE when conducting academic research, analyzing experimental data, testing hypotheses with t-tests or ANOVA, performing regression analyses, calculating effect sizes, checking statistical assumptions, or generating publication-ready statistical reports. Do not use for literature reviews, tool selection, or methodology design → see conducting-research skill.
Expertise in narrative structure, academic storytelling, and LaTeX Beamer presentations. Use when designing the flow of research talks and building technical slide decks with a focus on scientific rigor and narrative clarity.
Automatically determines the optimal research tool based on query type and available information. Use when answering technical questions requiring external verification, documentation lookup, or library/repo research. Do not use for statistical calculations, hypothesis testing, or data analysis → see analyzing-data skill.
Transforms repositories into structured plain-text digests optimized for LLM consumption. Use when analyzing GitHub repositories, digesting codebases, or ingesting git repos for AI analysis.
Plugin marketplace for The Cat Toolkit - Vibecoding plugins for autonomous AI development.
For developers, the primary source of truth is CLAUDE.md.
The Cat Toolkit organizes capabilities into domain-specific plugins:
| Plugin | Domain | Focus |
|---|---|---|
| sys-core | Infrastructure | Validation, scaffolding, hooks, MCP, security |
| sys-builder | Engineering | Architecture, planning, execution, testing, TDD |
| sys-cognition | Reasoning | Thinking frameworks, prompt engineering, analysis (directly actionable) |
| sys-agents | Agent Development | Context engineering, memory systems, orchestration (requires implementation) |
| sys-research | Knowledge | Research tools, documentation, codebase analysis |
| sys-multimodal | Media | Vision, audio, video processing |
| sys-edge | Edge/Mobile | Optimization, offline-first, resource-constrained environments |
| sys-nodejs | Node.js | JavaScript/TypeScript development, build tools |
| sys-browser | Browser Automation | Web interaction, crawling, testing |
| llm-application-dev | LLM Applications | RAG systems, vector databases, hybrid search, semantic retrieval |
Key Distinction: sys-cognition provides directly actionable skills (prompt patterns, reasoning frameworks), while sys-agents covers skills requiring external frameworks (Vector DBs, GraphRAG, multi-agent architectures).
Add The Cat Toolkit marketplace and install plugins:
# Add the marketplace
/plugin marketplace add Git-Fg/thecattoolkit
# Install individual plugins
/plugin install sys-core@cattoolkit
/plugin install sys-builder@cattoolkit
/plugin install sys-cognition@cattoolkit
# Or install all plugins
/plugin install sys-core@cattoolkit sys-builder@cattoolkit sys-cognition@cattoolkit sys-edge@cattoolkit sys-multimodal@cattoolkit sys-research@cattoolkit sys-nodejs@cattoolkit llm-application-dev@cattoolkit
For local development, load plugins using the --plugin-dir flag:
# Load individual plugins
claude --plugin-dir ./plugins/sys-builder
claude --plugin-dir ./plugins/sys-cognition
# Load multiple plugins
claude --plugin-dir ./plugins/sys-builder --plugin-dir ./plugins/sys-cognition --plugin-dir ./plugins/sys-core
# Project scope (team-shared)
/plugin install sys-core@cattoolkit --scope project
See Marketplace Configuration Guide for complete installation and configuration details.
The Cat Toolkit - Building the future of autonomous AI development.
Agents used for research across multiple data sources. Other plugins expect this one to be enabled.
External network access
Connects to servers outside your machine
Share bugs, ideas, or general feedback.
Meta-cognitive tools for Claude Code self-improvement. Learn from feedback, optimize configuration, and evolve your AI development workflow.
Domain-specific expert agents for research, documentation, and specialized tasks
Core skills: ecosystem guide, skill creator, research patterns, session reflection, and plugin development. Includes UserPromptSubmit hook for forced skill evaluation.
Upstash Context7 MCP server for up-to-date documentation lookup. Pull version-specific documentation and code examples directly from source repositories into your LLM context.
Reliable automation, in-depth debugging, and performance analysis in Chrome using Chrome DevTools and Puppeteer