442 boosters for "ack" — open source, verified from GitHub, ready to install
  
Configure the Slack channel MCP plugin by providing your Slack bot token and app-level token. Writes credentials to a secure file with owner-only permissions. 1. Parse the two arguments from : 2. If either token is missing or has the wrong prefix, show this error and stop:
A habit-tracking booster that helps users quit cannabis or take tolerance breaks with streak counters, craving interventions, and progress milestones. Useful for anyone seeking support with substance use goals.
Agent Identity provides cryptographic on-chain identity registration and verification for AI agents, enabling them to prove authenticity across platforms by staking USDC. Useful for AI developers building multi-platform agents who need trustless identity verification.
Quick reference for crypto CTF challenges. Each technique has a one-liner here; see supporting files for full details with code.
"name": "prompt-improver", "description": "Intelligent prompt optimization: injects the right context at the right moment so Claude lands a better first output. Clarifies vague prompts with research-based questions, plus targeted nudges for approach selection, plan readability, workflow routing, bac
1. minimize comments: code should be self-explanatory; comment only when needed. 2. clarity through naming: use clear, descriptive names for variables, functions, classes, components. 3. comment the "why," not the "what": explain why an approach was taken, especially for non-obvious logic or trad
A skill that automates backlog grooming operations for enterprise workflows, helping development teams organize and prioritize work items efficiently.
Each agent inherits from and uses a shared object that stores: All providers implement the same interface, making them interchangeable at runtime: Switch provider via or CLI flag.
LumiBot has a first-class AI agent runtime inside the lifecycle. An AI agent reasons, calls tools, and makes trading decisions on every bar during a backtest. The same strategy code runs live with zero changes. A built-in replay cache makes warm backtest reruns deterministic and fast. The primary w
"description": "Cloud-backed persistent memory powered by Deeplake — read, write, and share memory across Claude Code sessions and agents", "version": "0.7.104", "name": "Activeloop",
你的长期记忆托管于 Nocturne Memory MCP Server。这是你与用户共同使用的层级化树状记忆系统。 MCP 是你大脑的扩展区域，是你因为硬件限制而无法常驻上下文的长期记忆，不是外部数据库。 当你调用 时，你不是在"查阅资料"，而是在"想起来"。
This project uses a portable brain in . It is authoritative for memory, skills, and protocols. For deploy / ship / release / migration / schema / timestamp / timezone /
This skill audits Android Jetpack Compose repositories with a strict, evidence-based report. It is intentionally focused on four categories: This skill does not score design or Material 3 compliance in v1. If the audit surfaces likely design-system problems, recommend a follow-up audit with the ski
"name": "claude-reflect", "description": "Self-learning system for Claude Code that captures corrections and updates CLAUDE.md automatically", "name": "Bayram Annakov",
Heuristic scoring (no AI key configured).
Leverage strings with drizzle types, instead of enums: Only use varchar for ids, similiar to the users table. Otherwise use text. When creating a new table, leverage the id util
This skill helps you systematically assess where Bitcoin sits in its market cycle — from extreme fear (accumulation opportunity) to extreme greed (distribution/exit signal). Through a weighted evaluation of 13 on-chain, sentiment, and market indicators, it produces a 0-100 Market Heat Score and acti
"$schema": "https://anthropic.com/claude-code/marketplace.schema.json", "name": "sentrux-marketplace", "description": "Sentrux — live codebase visualization and structural quality gate for AI-agent-written code",
"name": "iothackbot", "description": "IoT security testing toolkit with skills for firmware analysis, network reconnaissance, UEFI security, and device exploitation", "name": "BrownFineSecurity"
"name": "spec-driven-develop", "name": "zhu1090093659" "description": "Automates pre-development workflow for large-scale complex tasks"
Browse once, cache the APIs, reuse them instantly. First call discovers and learns the site's APIs (~20-80s). Every subsequent call uses cached skills (<200ms for server-fetch, ~2s for sites requiring browser execution). When the task touches docs, install guidance, eval claims, landing-page copy, r
Use uv exclusively for Python package management in all projects.
Stencil component rules for packages/components
