English | 中文 | Codex Branch | Changelog

Awesome Claude Code Configuration

Production-ready configuration for Claude Code. One-command install of global instructions, multi-language coding rules (Python / TypeScript / Go), 21 curated plugins across 10 marketplaces, seven bundled skills, a gradient status bar, and a self-improvement loop that remembers corrections across sessions.

Showcase

• paper-reading skill — Attention Is All You Need
• adversarial-review skill — worked example

Quick Start

macOS / Linux:

bash <(curl -fsSL https://raw.githubusercontent.com/Mizoreww/awesome-claude-code-config/main/install.sh)

Windows (PowerShell):

irm https://raw.githubusercontent.com/Mizoreww/awesome-claude-code-config/main/install.ps1 | iex

Launches a two-level interactive selector. Append --all / -All to skip the menu and install everything non-interactively. Other flags: --dry-run, --uninstall, --version (PowerShell: -DryRun, -Uninstall, -Version).

  > [5/5] Core                   Global instructions, settings, rules...
    [0/3] Language Rules          Python / TypeScript / Go
    [2/3] Review                  code-review + adversarial-review
    [5/6] Workflow                karpathy, mattpocock-skills, neat-freak...
    [2/2] Integrations            context7, playwright
    [4/6] Design & Content        document-skills, frontend-design, humanizer...
    [0/2] Slides                  frontend-slides, ppt-master
    [0/2] Memory & Lifestyle      claude-mem, claude-health
    [0/1] Storage                 storage-analyzer
    [1/11] Academic Research      paper-reading, deepxiv-cli, researchstudio...
    [0/1] MCP Servers             Lark/Feishu

• Main menu: ↑↓ navigate groups, Enter or → open a group's sub-menu, q quit. Arrow to Submit and press Enter to install.
• Sub-menu: ↑↓ navigate items, Space toggle, ← or Esc back to main menu (same as pressing Enter on [ Back ]).
• Shortcuts (any level): a all on, n all off, d defaults; in sub-menus these only affect that group.
• The Review group's adversarial-review and codex are mutually exclusive — selecting one deselects the other.

Core (5) — foundational files, all on by default.

Item	What It Does	Default
CLAUDE.md	Global instructions template	on
settings.json	Smart-merged Claude Code settings	on
Common rules	rules/common/ — coding style, git, security, testing	on
StatusLine	Gradient progress bar & 5h usage (hooks/statusline.sh)	on
Lessons	lessons.md template + SessionStart hook	on

Language Rules (3) — off by default, enable only what your projects use.

Item	What It Does	Default
Python rules	PEP 8, pytest, type hints, bandit	off
TypeScript rules	Zod, Playwright, immutability	off
Go rules	gofmt, table-driven tests, gosec	off

Review (3) — adversarial-review and codex are mutually exclusive.

Item	Source	What It Does	Default
code-review	claude-plugins-official (plugin)	Confidence-based PR code review	on
adversarial-review	bundled skill	Cross-model review (Skeptic / Architect / Minimalist lenses)	on
codex	openai-codex (plugin)	Codex CLI-backed adversarial review	off

Workflow (6) — planning, iteration, code quality, meta-config.

Item	Source	What It Does	Default
andrej-karpathy-skills	karpathy-skills (plugin)	Karpathy coding guidelines: Think-First, Simplicity, Surgical, Goal-Driven	on
superpowers	claude-plugins-official (plugin)	Brainstorming, debugging, code review, git worktrees, plan writing	off
mattpocock-skills	mattpocock (plugin)	22 agent skills (tdd, to-spec, to-tickets, diagnosing-bugs, handoff, teach, grilling…) as a managed plugin bundle	on
neat-freak	bundled skill	Knowledge and governance closeout for project docs, agent rules, authorized memory, and workspace residue	on
code-simplifier	claude-plugins-official	Code simplification and refactoring	on
update-config	bundled skill	/update-config — re-run installer from inside a session	on

Integrations (2) — external tools and services.

Item	Source	What It Does	Default
context7	claude-plugins-official	Up-to-date library documentation lookup	on
playwright	claude-plugins-official	Browser automation, E2E testing, screenshots	on

Design & Content (6) — documents, UI, creative artifacts, text humanization.

Item	Source	What It Does	Default
document-skills	anthropic-agent-skills	PDF, DOCX, PPTX, XLSX creation and manipulation	on
example-skills	anthropic-agent-skills	Frontend design, MCP builder, canvas, algorithmic art	on
frontend-design	claude-plugins-official	Production-grade frontend interfaces	on
humanizer	bundled skill	Remove AI writing patterns (English)	on
humanizer-zh	bundled skill	Remove AI writing patterns (Chinese)	off
lieflat-charts	lieflat-charts (GitHub, PolyForm-NC)	Template-driven HTML charts and full-page reports: Lupi / Basics / Glance / Maps galleries plus 12 bilingual report templates. Fetched from upstream main at install time via sparse checkout (docs/ preview media excluded), not vendored. Noncommercial use only	off

Slides (2) — AI slide / PPTX generation, both off by default.

Item	Source	What It Does	Default
frontend-slides	frontend-slides	Zero-dependency HTML slide generator with PPT conversion and bold template styles	off
ppt-master	ppt-master	Editable PPTX from PDF/DOCX/URL/Markdown — real shapes & animations (run pip install -r requirements.txt post-install)	off

Memory & Lifestyle (2) — session memory and personal productivity, all off by default.

Item	Source	What It Does	Default
claude-mem	thedotmack	Persistent memory with smart search, timeline, AST-aware code search	off
claude-health	claude-health	Health check & wellness dashboard for Claude Code sessions	off

Storage (1) — disk usage analysis, off by default.

Item	Source	What It Does	Default
storage-analyzer	bundled skill (modified)	Read-only disk usage analysis that classifies what is eating space and produces an interactive HTML report with guarded one-click cleanup. Linux support and security hardening were added here on top of the pinned upstream — see UPSTREAM.md; submitted back as khazix-skills#50	off

Academic Research (11) — training / inference plugins + paper-reading, DeepXiv & ResearchStudio skills, off by default except paper-reading.

Item	Source	What It Does	Default
paper-reading	bundled skill	Research paper summarization with figure extraction	on
tokenization	ai-research-skills	HuggingFace Tokenizers, SentencePiece	off
fine-tuning	ai-research-skills	Axolotl, LLaMA-Factory, PEFT, Unsloth	off
post-training	ai-research-skills	GRPO, RLHF, DPO, SimPO	off
inference-serving	ai-research-skills	vLLM, SGLang, TensorRT-LLM, llama.cpp	off
distributed-training	ai-research-skills	DeepSpeed, FSDP, Megatron-Core, Ray Train	off
optimization	ai-research-skills	AWQ, GPTQ, GGUF, Flash Attention, bitsandbytes	off
deepxiv-cli	DeepXiv (GitHub)	arXiv/PMC paper search & reading CLI (hybrid BM25+Vector, 2M+ papers)	off
deepxiv-trending-digest	DeepXiv (GitHub)	Markdown digests of trending papers (last 7 days)	off
deepxiv-baseline-table	DeepXiv (GitHub)	Build baseline comparison tables from research papers	off
researchstudio	ResearchStudio (Microsoft, npx)	Research ideation Idea skills: idea-spark, paper-search, scoop-check	off

MCP Servers (1) — non-plugin MCP integrations, off by default.

Item	Source	What It Does	Default
Lark MCP server	mcp/	Feishu / Lark integration (replace YOUR_APP_ID/YOUR_APP_SECRET after install)	off

Directory Structure

.
├── CLAUDE.md              # Global instructions
├── settings.json          # Permissions, plugins, hooks, model
├── lessons.md             # Self-correction log template (auto-loaded via hook)
├── rules/                 # Coding standards (common + python/typescript/golang)
├── hooks/                 # Statusline with gradient progress bars
├── mcp/                   # MCP server config (Lark-MCP)
├── plugins/               # Plugin catalogue & install guide
├── skills/                # Bundled custom skills
├── docs/                  # Paper summaries, showcases
└── install.sh / install.ps1

Key Mechanisms

• Layered rules — rules/common/ (universal) extended by per-language directories. Each file references a deeper skill for patterns, testing, security.
• Statusline — model, directory, venv, git branch, context window (gradient bar), 5-hour usage countdown. Script at hooks/statusline.sh.
• Self-improvement loop — corrections route to ~/.claude/lessons.md (cross-project) or project MEMORY.md (local). SessionStart hooks re-inject them on startup and after context compaction.
• Plugin catalogue & marketplace URLs — full list with install commands: plugins/README.md.

Settings Defaults

settings.json ships with high-performance defaults. Unknown keys are ignored by older Claude Code; only auto mode is version-gated (installer auto-downgrades to bypassPermissions below 2.1.80).

Key	Value	Effect
permissions.defaultMode	auto	Auto-approve safe actions, block risky ones
effortLevel	max	Pin /effort to highest reasoning tier
betas	extended-cache-ttl-2025-04-11	1-hour prompt cache (vs default 5 min)
env.CLAUDE_CODE_NO_FLICKER	1	Fullscreen rendering
env.CLAUDE_CODE_DISABLE_ADAPTIVE_THINKING	1	Fixed thinking budget (no effect on Opus 4.7)

Smart merge on re-install preserves your overrides for env, permissions.allow, enabledPlugins, hooks.SessionStart, and statusLine. Third-party plugins in your enabledPlugins that are outside this catalogue are left untouched.

Customization

• Add a language: create rules/<lang>/ extending rules/common/
• Add a skill: place in skills/<name>/SKILL.md
• Adapt CLAUDE.md: tune for your shell, package manager, project context

Acknowledgements

• Claude Code in Action — Anthropic Academy's official course
• Working for 10 Claude Codes by Hu Yuanming — multi-instance patterns
• Harness Engineering by OpenAI
• Anthropic Engineering / OpenAI Engineering
• Claude Code Best Practice by shanraisshan
• Claude How To by luongnv89

License

This repository is MIT. Third-party components the installer fetches keep their own licenses — notably lieflat-charts, which is PolyForm Noncommercial 1.0.0 and may be used for noncommercial purposes only. It is off by default and is downloaded from upstream at install time rather than redistributed here.