Aznatkoiny

59 mods across 1 repository, 9 stars between them.

zAI-Skills

01

Aznatkoiny/zAI-Skills

Plugin Claude Code

Development marketplace for AI-Toolkit, consulting-toolkit, real-estate-investment, career-coach, and plugin-forge plugins.

9 28d ago A tokens not measured original MIT

ai-toolkit

02

Aznatkoiny/zAI-Skills

Plugin Claude Code

Skills for Deep Learning (Keras 3), Reinforcement Learning (Python & C++), Claude Prompt Optimization, x402 Web3 Payments, and OpenClaw Setup.

9 28d ago A tokens not measured original MIT

prompt-rewriter

03

Aznatkoiny/zAI-Skills

Agent

Use this agent to rewrite a prompt or system prompt for Claude's latest models in an isolated context, applying the prompt-optimizer skill's references end-to-end: diagnosis against the symptom-routing table, core principles, proven reference snippets, and parameter recommendations. Invoke for heavyweight rewrites …

9 28d ago A 334 tokens original MIT

rl-debugger

04

Aznatkoiny/zAI-Skills

Agent

Use this agent to diagnose reinforcement learning training failures: flat or collapsing reward curves, policy entropy collapse, value-function problems, NaN losses, high-variance runs, and suspected environment bugs. It encodes the RL debugging playbook from the reinforcement-learning skill — pre-training sanity…

9 28d ago A 312 tokens original MIT

openclaw-audit

05

Aznatkoiny/zAI-Skills

Command

Audit the local OpenClaw install against the openclaw-setup skill's security checklist — version, binding, auth, channel policy — with a pass/fail table and remediations.

9 28d ago A 38 tokens original MIT

optimize-prompt

06

Aznatkoiny/zAI-Skills

Command

Diagnose and rewrite a prompt using the prompt-optimizer skill — outputs a before/after diff, parameter recommendations, and per-change rationale.

9 28d ago A 27 tokens original MIT

rl-new-project

07

Aznatkoiny/zAI-Skills

Command

Scaffold a Python RL project — custom Gymnasium env, SB3 training script with EvalCallback + VecNormalize, Optuna tuning stub, and validation targets in a Makefile.

9 28d ago A 35 tokens original MIT

x402-scaffold

08

Aznatkoiny/zAI-Skills

Command

Generate an x402 payment starter — seller (paid endpoint with 402 flow) or buyer (paying client) — with safe testnet defaults.

9 28d ago A 29 tokens original MIT

Aznatkoiny/zAI-Skills

Skill Claude CodeCodex

C++ Reinforcement Learning best practices using libtorch (PyTorch C++ frontend) and modern C++17/20. Use when: Implementing RL algorithms in C++ for performance-critical applications Building production RL systems with libtorch Creating replay buffers and experience storage Optimizing RL training with GPU acceleration…

9 28d ago A 83 tokens original MIT

deep-learning

10

Aznatkoiny/zAI-Skills

Skill Claude CodeCodex

Comprehensive guide for Deep Learning with Keras 3 (Multi-Backend: JAX, TensorFlow, PyTorch). Use when building neural networks, CNNs for computer vision, RNNs/Transformers for NLP, time series forecasting, or generative models (VAEs, GANs). Covers model building (Sequential/Functional/Subclassing APIs), custom…

9 28d ago A 91 tokens original MIT

openclaw-setup

11

Aznatkoiny/zAI-Skills

Skill Claude CodeCodex

Set up, install, configure, and deploy OpenClaw (formerly ClawdBot/MoltBot) — a personal AI assistant that runs on your own devices and connects to messaging channels. Use when users ask to "set up OpenClaw," "install ClawdBot," "install MoltBot," "deploy a personal AI assistant," "configure OpenClaw on Mac," "deploy…

9 28d ago E 188 tokens original MIT

prompt-optimizer

12

Aznatkoiny/zAI-Skills

Skill Claude CodeCodex

Optimize prompts for Claude's latest models (Claude 5 family — Opus 5, Sonnet 5, Fable 5 — plus the still-active Opus 4.8, Sonnet 4.6, and Haiku 4.5) using Anthropic's official prompt-engineering guidance. Use when users want to improve, refine, debug, or create prompts or system prompts for Claude. Triggers include…

9 28d ago A 205 tokens original MIT

Aznatkoiny/zAI-Skills

Skill Claude CodeCodex

Reinforcement Learning best practices for Python using modern libraries (Stable-Baselines3, RLlib, Gymnasium). Use when: Implementing RL algorithms (PPO, SAC, DQN, TD3, A2C) Creating custom Gymnasium environments Training, debugging, or evaluating RL agents Setting up hyperparameter tuning for RL Deploying RL models…

9 28d ago A 86 tokens original MIT

x402-payments

14

Aznatkoiny/zAI-Skills

Skill Claude CodeCodex

Build applications using the x402 protocol — Coinbase's open standard for HTTP-native stablecoin payments using the HTTP 402 status code. Use this skill when: Creating APIs that require USDC payments per request (seller/server side) Building clients or AI agents that pay for x402-protected resources (buyer/client…

9 28d ago A 185 tokens original MIT

Aznatkoiny/zAI-Skills

Instructions file

Instructions for Aznatkoiny/zAI-Skills, covering zai-skills — repo conventions, config, mcp servers, commands and agents and docs.

9 28d ago A 650 tokens original MIT

career-coach

16

Aznatkoiny/zAI-Skills

Plugin Claude Code

Career coaching and job search plugin with AI-powered resume building, interview preparation, and multi-platform job discovery. Features a Career Director orchestrator, job search automation via MCP, industry-specific formatting styles, and LaTeX resume compilation.

9 28d ago A tokens not measured original MIT

career-director

17

Aznatkoiny/zAI-Skills

Agent

Use this agent for career planning, job search orchestration, and professional development coaching. Invoke when the user asks about career trajectory, needs multi-step job search coordination, wants gap analysis between current skills and target roles, or requires routing to specialist agents (job search, interview…

9 28d ago A 265 tokens original MIT

interview-prep

18

Aznatkoiny/zAI-Skills

Agent

Use this agent for interview preparation, mock interviews, behavioral question coaching, technical interview practice, and company-specific research. Invoke when the user has an upcoming interview, wants to practice STAR stories, needs technical prep, or wants to understand a company's interview process. Context: User…

9 28d ago A 242 tokens original MIT

job-search

19

Aznatkoiny/zAI-Skills

Agent

Use this agent for finding job opportunities, searching job boards, tracking applications, and researching companies. Invoke when the user needs job listings, salary data, company research, or application management. Handles LinkedIn, Indeed, TrueUp, Glassdoor, and Levels.fyi data through MCP tools. Context: User…

9 28d ago A 220 tokens original MIT

ats-check

20

Aznatkoiny/zAI-Skills

Command

Check a resume against a job description for ATS keyword coverage, with a rewrite suggestion per missing keyword.

9 28d ago A 19 tokens original MIT

compare-offers

21

Aznatkoiny/zAI-Skills

Command

Compare job offers on benchmarked 4-year total compensation with cost-of-living adjustment and negotiation talking points.

9 28d ago A 21 tokens original MIT

cover-letter

22

Aznatkoiny/zAI-Skills

Command

Generate a tailored cover letter for a specific job posting or company.

9 28d ago A 12 tokens original MIT

follow-ups

23

Aznatkoiny/zAI-Skills

Command

Flag stale applications and due next-actions from the tracker and draft follow-up emails.

9 28d ago A 15 tokens original MIT

job-hunt

24

Aznatkoiny/zAI-Skills

Command

Run the full job-search pipeline — search, enrich, score against your profile, and seed the application tracker.

9 28d ago A 21 tokens original MIT