rfxlamia-skillkit

Skills and agents promoting hybrid human-AI intelligence with mindfulness and intentional design.

112 skills

Development framework for building and orchestrating Claude Code skills and agents.

31 skills · 27 commands · 10 agents · hooks

Collection of Claude subagents, skills, and blueprints for developers covering programming, DevOps, and cloud tools. Accelerates agent-based development.

59 skills

A collection of Claude Code commands, skills, and agents for building startup tools and automations. Useful for developers building multi-agent systems.

35 skills

SPEC-first multi-agent framework for Claude Code enabling human oversight in agent workflows. Balances automation with control.

30 skills

McKinsey's provider-agnostic framework for agentic application operations, codifying patterns from dozens of production deployments to help build scalable AI agents.

27 skills

AI agent skills for CopilotKit — search the current documentation and source, and drive the CopilotKit CLI

9 skills · 2 MCP servers

Graduated assistance framework to prevent skill atrophy when coding with AI

1 agent

Automatically nudges Claude to offer learning exercises after git commits. Requires the learning-opportunities plugin.

hooks

AI Agent Architecture — Governance, design, and security for autonomous AI agent programs. 6 commands. [COMMUNITY]

6 commands

Structured goal-setting exercise using Mental Contrasting with Implementation Intentions

1 skill

Rubber duck tutor that keeps you engaged across the whole AI-coding lifecycle — before you ask AI to build (/duck-prebuild), once code is written and before you ship (/duck-verify, /duck-review), and when orienting to unfamiliar code (/duck-orient), plus /duck for auto-detect. /coach is its teaching sibling, manual-invocation only: /coach <topic> explains and drills a concept, /coach <file> or a bare /coach right after generating code dissects it section by section (what/why-this-way/where-it-breaks), and /coach alone surfaces an unresolved gap from a past duck session and teaches it — resolved only once you pass the exercise, not by saying you understand. Ship-point hooks triage what you just pushed against six risk categories and target the riskiest change you didn't actually discuss, fall back to retrieving an unresolved gap from a past session, or demote to a non-blocking scoreboard after three ignored confrontations in a row. Confrontation telemetry (fired/answered/ignored) is queryable from /duck-orient. Doesn't overlap /code-review or /grilling — duck only checks whether you understand, never whether the code or plan is good, and never teaches — that's coach's job.

6 skills · hooks