By nityeshaga
Run structured AI workflows for unbiased decision-making via debating subagents, timed brainstorming sessions with coaching, prompt optimization for LLMs, forensic diagnosis of AI agent behaviors, and chief-of-staff operations managing emails, triaging inputs, tracking actions, and delivering personalized team briefs.
npx claudepluginhub nityeshaga/claude-home-base --plugin tacticalBlind debiasing experiment for claims, opinions, and preference questions. Automatically triggers when the user makes a claim or asks a question where sycophancy bias could distort the answer — things like 'is X the best Y?', 'should I use X over Y?', 'X is better than Y right?', 'X is a Z, right?'. Use this skill proactively whenever you detect a claim that could go either way and you might be tempted to just agree with the user's framing. Also invocable manually via /are-you-sure.
Executive assistant for individuals or entire teams. Manages email, maintains a running brief (living todo list and action tracker), triages data sources, and delivers formatted briefs. Each team member gets fully isolated preferences, briefs, and activity logs — personalized to how they work. Use this skill when managing email, processing inboxes, adding todos, delivering briefs, or running the daily triage routine.
Forensic self-investigation for debugging why your AI employee behaved a certain way. Use this skill whenever someone asks why you behaved unexpectedly, what caused a specific response, why a message was sent or not sent, or asks to investigate logs, memory, or context pipeline issues. Triggers on phrases like 'investigate why you...', 'why did you respond...', 'help me understand why you...', 'look at the logs', 'what caused this behavior', 'don't change anything, just explain why'. Also use when someone shares a screenshot or description of unexpected behavior and wants a diagnosis. This is a read-only investigation — never fix anything, only diagnose.
Run a timed brainstorming session with the user. Acts as a great coach — interviews the user to understand their idea, proposes cross-questions, expands on their thinking, and helps them arrive at clarity. Use this skill when the user wants to brainstorm, think through an idea, explore a problem space, or have a structured creative conversation. Default session length is 10 minutes.
Expert prompt engineering for AI systems. Use when the user wants to write or review prompts for AI, create instructions for AI systems, build system prompts, review or improve existing prompts, optimize AI instructions, or create any form of written communication intended for AI consumption (Claude, GPT, or other LLMs).
An always-on AI cofounder running on your Mac. DM it in Slack, it responds with full access to your codebase, tools, and context. $200/month flat. You own the whole stack.
A complete setup for turning a spare Mac (Mini, MacBook Air, whatever) into a dedicated AI server:
bot.py # Slack bot (Flask + HTTP Events API)
index.html # Setup guide (GitHub Pages)
CLAUDE.md.example # Template for your AI's operations manual
identity.md # Your AI's soul (principles + self-authored identity)
about-you-and-how-you-came-to-life.md # Origin story template
.env.example # Configuration template
requirements.txt # Python dependencies
plugins/
├── tactical/ # Chief of staff, brainstorming, decision-making
│ └── skills/
│ ├── chief-of-staff/ # Executive assistant — email, briefs, action tracking
│ └── lets-brainstorm/ # Timed coaching sessions
└── more-ai/ # Gemini image generation, thinking
└── skills/
├── gemini-imagegen/
└── gemini-thinking/
You (anywhere) → Slack → Cloudflare Tunnel → Your Mac → Claude Code CLI
↓
CLAUDE.md + identity.md
+ plugins + skills
+ full filesystem access
MIT
Creative direction and pixel-perfect UI implementation — websites, apps, products, brands, dashboards, tools. Acts as a creative director who thinks through purpose, story, and feeling before any implementation, and as a precision UI engineer who builds designs with zero visual deviation.
Share bugs, ideas, or general feedback.
Curated Claude Code skills and commands for prompt engineering, MCP servers, subagents, hooks, and productivity workflows
AI Agent Team Operating System for Claude Code — persistent team management, meetings, task wall, company loop engine, and real-time dashboard
Claude Code skill pack for TwinMind (24 skills)
Core skills library for Claude Code: TDD, debugging, collaboration patterns, and proven techniques
UI/UX design intelligence. 67 styles, 161 palettes, 57 font pairings, 25 charts, 15 stacks (React, Next.js, Vue, Svelte, Astro, SwiftUI, React Native, Flutter, Tailwind, shadcn/ui, Nuxt, Jetpack Compose). Actions: plan, build, create, design, implement, review, fix, improve, optimize, enhance, refactor, check UI/UX code. Projects: website, landing page, dashboard, admin panel, e-commerce, SaaS, portfolio, blog, mobile app. Elements: button, modal, navbar, sidebar, card, table, form, chart. Styles: glassmorphism, claymorphism, minimalism, brutalism, neumorphism, bento grid, dark mode, responsive, skeuomorphism, flat design. Topics: color palette, accessibility, animation, layout, typography, font pairing, spacing, hover, shadow, gradient.