AnastasiyaWCommunity·12 Agent Skills Included

claude-code-config

Battle-tested rules, hooks, and skills for coding agents

Equips coding agents with proven architectural principles, safety hooks, and domain skills for real projects. Stops common agent failures: unfinished tasks, guessed fixes, supply-chain attacks, lost context, and unverified claims. Covers code review, refactoring, testing strategy, frontend and iOS development, ML training, pixel art, and video production. Drop-in rules and verification scripts let agents start from working patterns instead of rediscovering them each session.

140|23

↗

npx skills add AnastasiyaW/claude-code-config --all -g -y

Available:

Tells the agent how to pick and apply the right principles, hooks, and skills for a project, enforce safety and quality rules, and verify its own work before claiming completion.

All Skills in This Repository (12)

Pure Emerald Level Indicators

📦 In Repo

AnastasiyaW

frontend-design

Develop frontend design workflows for accessible web interfaces with responsive layouts and design tokens.

deep-review

Coordinate parallel competency reviews and synthesize code-quality findings into a unified report.

ios-development

Provide iOS development guidance for Swift, SwiftUI, and UIKit apps.

plan-swarm-review

Conduct iterative multi-agent reviews of plans and code for design flaws and security issues.

harness-design

Design multi-agent harnesses with Planner, Generator, and Evaluator roles.

flux2-klein-prompting

Create structured FLUX.2 klein prompts for text-to-image and image-to-image workflows.

flux2-lora-training

Train LoRA adapters for FLUX.2 Klein and Qwen Image Edit 2511.

forensic-prompt-compiler

Convert images into single-line forensic prompts for diffusion models.

diffusion-engineering

Optimize diffusion-model architectures, training pipelines, and inference workflows for deployment.

vlm-segmentation-engineering

Guide vision-language model selection, segmentation pipelines, and GPU deployment.

English Text Humanization

Rewrite AI-generated English to sound natural with varied sentence lengths and tone control.

Russian Text Humanization

Humanize Russian text by removing AI markers and unnatural phrasing.

Community

Intermediate

Frequently Asked Questions

FAQPage Schema

How to install claude-code-config?▼

Run `npx skills add AnastasiyaW/claude-code-config --all -g -y` in your terminal to install all skills globally.

What problems does this configuration solve?▼

It prevents agents from claiming unfinished work as done, guessing fixes without evidence, installing risky fresh packages, and losing context in long sessions. Each rule and hook comes from a real observed failure.

Does it work with Codex and other coding agents?▼

Yes. The AGENTS.md standard is read natively by Codex, and Claude Code loads it through CLAUDE.md, so the same rules apply across harnesses.

How do the safety hooks work?▼

Python hooks run at session events to block destructive commands, detect leaked API keys, and enforce task completion. They install into your global or project config with the included installer script.

Can I use only parts of this configuration?▼

Yes. The README maps project types to minimum sets, so you copy only the principles, hooks, and skills that match your stack instead of everything.