By uhstray-io
Uhstray.io skills marketplace — curated Claude Code skills including uhh:memory.
npx claudepluginhub uhstray-io/huhhb --plugin huhhbUltra-compressed communication mode. Cuts token usage ~75% by speaking like Unga Bunga while keeping full technical accuracy. Supports intensity levels: lite, full (default), ultra, wenyan-lite, wenyan-full, wenyan-ultra. Use when user says "unga bunga mode", "talk like unga bunga", "use unga bunga", "less tokens", "be brief", or invokes /unga-bunga. Also auto-triggers when token efficiency is requested.
Use when starting feature work that needs isolation from current workspace or before executing implementation plans - creates isolated git worktrees with smart directory selection and safety verification
Use when starting any conversation - establishes how to find and use skills, requiring Skill tool invocation before ANY response including clarifying questions
Use when about to claim work is complete, fixed, or passing, before committing or creating PRs - requires running verification commands and confirming output before making any success claims; evidence before assertions always
You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.
Use when facing 2+ independent tasks that can be worked on without shared state or sequential dependencies
Ultra-compressed code review comments. Cuts noise from PR feedback while preserving the actionable signal. Each comment is one line: location, problem, fix. Use when user says "review this PR", "code review", "review the diff", "/review", or invokes /unga-bunga-review. Auto-triggers when reviewing pull requests.
Use when you have a written implementation plan to execute in a separate session with review checkpoints
Use when implementation is complete, all tests pass, and you need to decide how to integrate the work - guides completion of development work by presenting structured options for merge, PR, or cleanup
Mine a project directory or raw text into the memory palace for future recall.
Search the memory palace for relevant team knowledge, decisions, or context.
Show memory palace statistics — drawer count, wings, rooms.
Access, search, and manage Uhstray.io team memory nexus. Auto-triggers at session start to load context.
Use when setting up Claude Code for the first time, configuring auto mode, enabling agent teams, or when user says "set up Claude", "configure my assistant", "onboard me", or "enable auto mode"
Use when receiving code review feedback, before implementing suggestions, especially if feedback seems unclear or technically questionable - requires technical rigor and verification, not performative agreement or blind implementation
Use when completing tasks, implementing major features, or before merging to verify work meets requirements
Use when executing implementation plans with independent tasks in the current session
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes
Use when implementing any feature or bugfix, before writing implementation code
Socratic teaching mode — Sensei. Guides users to solutions without ever writing new code. Describes approaches, names relevant APIs/functions, provides documentation links, explains errors in plain language, and asks questions that lead the user to the answer themselves. Use when user says "training mode", "sensei mode", "teach me mode", "guide me through this", "teacher mode", "help me learn", "I want to learn", "no code just explain", or invokes /training. Also triggers when user says "explain without doing" or "don't write it, teach me".
Ultra-compressed commit message generator. Cuts noise from commit messages while preserving intent and reasoning. Conventional Commits format. Subject ≤50 chars, body only when "why" isn't obvious. Use when user says "write a commit", "commit message", "generate commit", "/commit", or invokes /unga-bunga-commit. Auto-triggers when staging changes.
Compress natural language memory files (CLAUDE.md, todos, preferences) into Unga Bunga format to save input tokens. Preserves all technical substance, code, URLs, and structure. Compressed version overwrites the original file. Human-readable backup saved as FILE.original.md. Trigger: /unga-bunga:compress <filepath> or "compress memory file"
Quick-reference card for all Unga Bunga modes, skills, and commands. One-shot display, not a persistent mode. Trigger: /unga-bunga-help, "unga bunga help", "what unga bunga commands", "how do I use unga bunga".
Use when you have a spec or requirements for a multi-step task, before touching code
Use when creating new skills, editing existing skills, or verifying skills work before deployment
huhhb is Uhstray.io's Claude Code skills marketplace — a curated library of skills (slash commands, workflows, AI automation) for teams building with Claude Code.
Name is a play on "hub" (a place for skills) + "uhh" (Uhstray). Say it fast.
# 1. Add the marketplace
claude plugin marketplace add uhstray-io/huhhb
# 2. Install (user scope — available in all projects)
claude plugin install --scope user huhhb
# Or project-scoped — only in this repo
claude plugin install --scope project huhhb
memoryrequiresuvfor its MCP server. The plugin auto-resolves Python deps viauv run— no manualpip installneeded.# macOS / Linux curl -LsSf https://astral.sh/uv/install.sh | sh # Windows (PowerShell) powershell -ExecutionPolicy ByPass -c "irm https://astral.sh/uv/install.ps1 | iex"
# Fetch latest from all marketplaces
claude plugin marketplace update
# Re-install to apply updates
claude plugin install --scope user huhhb
skills/<category>/<skill-name>/skill.md with YAML frontmatter:---
name: skill-name
description: One-line description (shown in skill discovery)
triggers:
- phrase that triggers this skill
---
# Skill content here
marketplace.json:{
"name": "skill-name",
"path": "skills/category/skill-name/skill.md",
"description": "...",
"category": "category",
"tags": ["tag1", "tag2"],
"version": "0.1.0"
}
| Skill | Trigger | Purpose |
|---|---|---|
memory | /memory | Team memory nexus — store and recall project context |
memory-search | /memory-search | Semantic search across the nexus |
memory-mine | /memory-mine | Ingest a project directory into the nexus |
memory-status | /memory-status | Nexus stats — drawer count, wings, rooms |
| Skill | Trigger | Purpose |
|---|---|---|
using-superpowers | /using-superpowers | Session start — how to find and invoke skills correctly |
brainstorming | /brainstorming | Explore intent and design before any implementation |
writing-plans | /writing-plans | Write a structured implementation plan from a spec |
executing-plans | /executing-plans | Execute a written plan with review checkpoints |
test-driven-development | /test-driven-development | Write tests before implementation code |
systematic-debugging | /systematic-debugging | Root-cause bugs before proposing fixes |
verification-before-completion | /verification-before-completion | Verify work passes before claiming done |
subagent-driven-development | /subagent-driven-development | Execute plans via parallel subagents |
dispatching-parallel-agents | /dispatching-parallel-agents | Split independent tasks across agents |
using-git-worktrees | /using-git-worktrees | Isolate feature work in git worktrees |
finishing-a-development-branch | /finishing-a-development-branch | Structured options for merge, PR, or cleanup |
writing-skills | /writing-skills | Create and validate new skills |
| Skill | Trigger | Purpose |
|---|---|---|
requesting-code-review | /requesting-code-review | Verify work before merging |
receiving-code-review | /receiving-code-review | Process review feedback with technical rigor |
| Skill | Trigger | Purpose |
|---|---|---|
unga-bunga | /unga-bunga | Ultra-compressed mode — ~75% fewer tokens, full technical accuracy |
unga-bunga-commit | /unga-bunga-commit | Terse Conventional Commits, subject ≤50 chars |
unga-bunga-review | /unga-bunga-review | One-line PR comments: location, problem, fix |
unga-bunga-compress | /unga-bunga:compress <file> | Compress memory files to save input tokens |
unga-bunga-help | /unga-bunga-help | Quick-reference for all Unga Bunga modes |
Browse the full manifest: marketplace.json
mem)Requires uv installed. Run from the plugin cache directory or any directory with the package:
mem init # Initialize the nexus
mem status # Show drawer count and wings
mem mine <path> --wing work # Ingest a directory
mem search "query" # Semantic search
mem wake-up # Print L0+L1 session context
Built by Uhstray.io — an AI-native team building tools for teams building with AI.
114 battle-tested skills for Claude Code. Session memory, git workflows, database migrations, security scanning, deployments, and more. Auto-trigger commands and project handoffs via markdown-based skills.
Admin access level
Server config contains admin-level keywords
Share bugs, ideas, or general feedback.
Persistent memory across sessions. Learns preferences, conventions, and corrections automatically.
Skill memory layer for Claude Code — auto-capture, learn, and reuse skills from Acontext
Curate auto-memory, promote learnings to CLAUDE.md and rules, extract proven patterns into reusable skills.
Memory system for AI agents — capture, consolidate, and recall knowledge across sessions and machines
Nemp Memory — Cognitive memory layer for AI agents across every platform. Local-first, zero cloud, works with Claude, Codex, Cursor, and Windsurf.