convez.ai
MCP ServerDevOps & InfraestruturaIntermediário
Mizoreww

Awesome Claude Code Configuration

Mizoreww/awesome-claude-code-config

Config Claude Code pronta para produção com auto-melhoria e 24 plugins

Ver no GitHub
BomPluginScore · de 0 a 100

Configuração pronta para produção do Claude Code com loop de auto-melhoria, regras multi-linguagem (Python/TypeScript/Go), 24 plugins curados e 7 skills bundled. Instalação por comando único com seletor interativo e integração de MCPs como Lark/Feishu.

Instalação

$npx convez-ai Mizoreww/awesome-claude-code-config

1 comando no terminal: detecta o formato do repositório (marketplace ou plugin avulso) e instala via Claude Code. Requer Node 18+ e o Claude Code instalado.

Métricas

Estrelas
262
Forks
37
Acompanhando
1
Saúde
42%
Último commit
há 1 mês
Versão
v4.2.0
Issues abertas
1
Contribuidores
5

Casos de uso

  • Padronizar regras de código entre múltiplas linguagens em projetos
  • Integrar revisão adversarial e paper-reading skills no fluxo de trabalho
  • Automizar instalação e sincronização de configurações globais do Claude Code
  • Melhorar qualidade de código com hooks, memory e integração GitHub

Veredito

Ferramenta sólida e bem-mantida que reduz fricção na configuração do Claude Code para equipes. Instalar tudo de uma vez pode ser verboso; o seletor interativo mitiga isso, mas recomenda-se usar --all para CI/CD.

README

A tradução para o português deste README ainda está na fila.

English | 中文 | Codex Branch | Changelog

Awesome Claude Code Configuration

Statusline

Production-ready configuration for Claude Code. One-command install of global instructions, multi-language coding rules (Python / TypeScript / Go), 24 curated plugins across 9 marketplaces, seven bundled skills, a gradient status bar, and a self-improvement loop that remembers corrections across sessions.

Showcase

Claude Code Demo

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
    [9/10] Workflow                karpathy, superpowers, update-config, handoff...
    [3/3] Integrations            context7, github, playwright
    [4/5] Design & Content        document-skills, frontend-design, humanizer...
    [0/3] Memory & Lifestyle      claude-mem, claude-health, PUA
    [1/10] Academic Research      paper-reading, deepxiv-cli...
    [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.

ItemWhat It DoesDefault
CLAUDE.mdGlobal instructions templateon
settings.jsonSmart-merged Claude Code settingson
Common rulesrules/common/ — coding style, git, security, testingon
StatusLineGradient progress bar & 5h usage (hooks/statusline.sh)on
Lessonslessons.md template + SessionStart hookon

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

ItemWhat It DoesDefault
Python rulesPEP 8, pytest, type hints, banditoff
TypeScript rulesZod, Playwright, immutabilityoff
Go rulesgofmt, table-driven tests, gosecoff

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

ItemSourceWhat It DoesDefault
code-reviewclaude-plugins-official (plugin)Confidence-based PR code reviewon
adversarial-reviewbundled skillCross-model review (Skeptic / Architect / Minimalist lenses)on
codexopenai-codex (plugin)Codex CLI-backed adversarial reviewoff

Workflow (10) — planning, iteration, code quality, meta-config.

ItemSourceWhat It DoesDefault
andrej-karpathy-skillskarpathy-skills (plugin)Karpathy coding guidelines: Think-First, Simplicity, Surgical, Goal-Drivenon
superpowersclaude-plugins-officialBrainstorming, debugging, code review, git worktrees, plan writingon
feature-devclaude-plugins-officialGuided feature developmenton
ralph-loopclaude-plugins-officialAutomated iteration loop (session-aware REPL)on
commit-commandsclaude-plugins-officialGit commit / push / PR workflowon
code-simplifierclaude-plugins-officialCode simplification and refactoringon
everything-claude-codeeverything-claude-codeTDD, security, database, Go/Python/Spring Bootoff
update-configbundled skill/update-config — re-run installer from inside a sessionon
handoffbundled skillCompact the current conversation into a handoff doc for the next agenton
teachbundled skillTeach a topic over multiple sessions (mission, lessons, learning records)on

Integrations (3) — external tools and services.

ItemSourceWhat It DoesDefault
context7claude-plugins-officialUp-to-date library documentation lookupon
githubclaude-plugins-officialGitHub integration (issues, PRs, workflows)on
playwrightclaude-plugins-officialBrowser automation, E2E testing, screenshotson

Design & Content (5) — documents, UI, creative artifacts, text humanization.

ItemSourceWhat It DoesDefault
document-skillsanthropic-agent-skillsPDF, DOCX, PPTX, XLSX creation and manipulationon
example-skillsanthropic-agent-skillsFrontend design, MCP builder, canvas, algorithmic arton
frontend-designclaude-plugins-officialProduction-grade frontend interfaceson
humanizerbundled skillRemove AI writing patterns (English)on
humanizer-zhbundled skillRemove AI writing patterns (Chinese)off

Memory & Lifestyle (3) — session memory and personal productivity, all off by default.

ItemSourceWhat It DoesDefault
claude-memthedotmackPersistent memory with smart search, timeline, AST-aware code searchoff
claude-healthclaude-healthHealth check & wellness dashboard for Claude Code sessionsoff
PUApua-skillsAI agent productivity booster (CN / EN / JA)off

Academic Research (10) — training / inference plugins + paper-reading skills, off by default except paper-reading.

ItemSourceWhat It DoesDefault
paper-readingbundled skillResearch paper summarization with figure extractionon
tokenizationai-research-skillsHuggingFace Tokenizers, SentencePieceoff
fine-tuningai-research-skillsAxolotl, LLaMA-Factory, PEFT, Unslothoff
post-trainingai-research-skillsGRPO, RLHF, DPO, SimPOoff
inference-servingai-research-skillsvLLM, SGLang, TensorRT-LLM, llama.cppoff
distributed-trainingai-research-skillsDeepSpeed, FSDP, Megatron-Core, Ray Trainoff
optimizationai-research-skillsAWQ, GPTQ, GGUF, Flash Attention, bitsandbytesoff
deepxiv-cliDeepXiv (GitHub)arXiv/PMC paper search & reading CLI (hybrid BM25+Vector, 2M+ papers)off
deepxiv-trending-digestDeepXiv (GitHub)Markdown digests of trending papers (last 7 days)off
deepxiv-baseline-tableDeepXiv (GitHub)Build baseline comparison tables from research papersoff

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

ItemSourceWhat It DoesDefault
Lark MCP servermcp/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).

KeyValueEffect
permissions.defaultModeautoAuto-approve safe actions, block risky ones
effortLevelmaxPin /effort to highest reasoning tier
betasextended-cache-ttl-2025-04-111-hour prompt cache (vs default 5 min)
env.CLAUDE_CODE_NO_FLICKER1Fullscreen rendering
env.CLAUDE_CODE_DISABLE_ADAPTIVE_THINKING1Fixed 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

License

MIT

Ver o original no GitHub

Bom para

Relacionados