AI Skill Hub 强烈推荐:claude-night-market AI工具 是一款优质的AI工具。AI 综合评分 8.2 分,在同类工具中表现稳健。如果你正在寻找可靠的AI工具解决方案,这是一个值得深入了解的选择。
为Claude Code提供23个强大插件,包含TDD测试驱动开发、Git/PR工作流、规范驱动开发等功能。帮助开发者在Claude中快速实施最佳实践,提升代码质量和开发效率,适合追求工程化的Python开发团队。
claude-night-market AI工具 是一款基于 Python 开发的开源工具,专注于 Claude插件、代码工程化、TDD开发 等核心功能。作为 GitHub 开源项目,它拥有活跃的社区支持和持续的版本迭代,代码完全透明可审计,支持本地部署以保护数据隐私。无论是个人使用还是集成到企业工作流,都能提供稳定可靠的解决方案。
为Claude Code提供23个强大插件,包含TDD测试驱动开发、Git/PR工作流、规范驱动开发等功能。帮助开发者在Claude中快速实施最佳实践,提升代码质量和开发效率,适合追求工程化的Python开发团队。
claude-night-market AI工具 是一款基于 Python 开发的开源工具,专注于 Claude插件、代码工程化、TDD开发 等核心功能。作为 GitHub 开源项目,它拥有活跃的社区支持和持续的版本迭代,代码完全透明可审计,支持本地部署以保护数据隐私。无论是个人使用还是集成到企业工作流,都能提供稳定可靠的解决方案。
# 方式一:pip 安装(推荐)
pip install claude-night-market
# 方式二:虚拟环境安装(推荐生产环境)
python -m venv .venv
source .venv/bin/activate # Windows: .venv\Scripts\activate
pip install claude-night-market
# 方式三:从源码安装(获取最新功能)
git clone https://github.com/athola/claude-night-market
cd claude-night-market
pip install -e .
# 验证安装
python -c "import claude_night_market; print('安装成功')"
# 命令行使用
claude-night-market --help
# 基本用法
claude-night-market input_file -o output_file
# Python 代码中调用
import claude_night_market
# 示例
result = claude_night_market.process("input")
print(result)
# claude-night-market 配置文件示例(config.yml) app: name: "claude-night-market" debug: false log_level: "INFO" # 运行时指定配置文件 claude-night-market --config config.yml # 或通过环境变量配置 export CLAUDE_NIGHT_MARKET_API_KEY="your-key" export CLAUDE_NIGHT_MARKET_OUTPUT_DIR="./output"
A plugin marketplace for Claude Code. Install only the plugins you need to run git workflows, code review, spec-driven development, and autonomous agents from inside your Claude Code session.
<p align="center"> <img src="assets/gifs/skills-showcase.gif" alt="Night Market skills in action" width="720"> </p>
23 plugins in four layers. Each installs independently, and dependencies pull their shared runtime automatically.
Foundation is the base every other layer builds on: leyline (auth, quotas, error patterns, trust verification), sanctum (git, commits, PR prep, sessions), and imbue (TDD enforcement, proof-of-work, scope guarding).
Utility handles cross-cutting concerns: conserve (context and token optimization), conjure (delegation to Gemini and Qwen), hookify (a behavioral rules engine with a security catalog), egregore (autonomous agent orchestration), herald (notifications), and oracle (local ML inference).
Domain is where the day-to-day work happens: pensive (code and architecture review), attune (project lifecycle), spec-kit (spec-driven development), parseltongue (Python), minister (GitHub issues and DORA metrics), memory-palace (knowledge organization), archetypes (architecture paradigms), gauntlet (codebase learning), phantom (computer use), scribe (documentation and slop detection), scry (recordings), tome (research), and cartograph (codebase visualization).
Meta improves the system itself: abstract (skill authoring, hook development, evaluation, and skill-stability tracking).
<picture> <source media="(prefers-color-scheme: dark)" srcset="assets/architecture-dark.svg"> <img alt="Plugin architecture across Foundation, Utility, Domain, and Meta layers" src="assets/architecture-light.svg"> </picture>
The full skill, command, and agent inventory is in the Capabilities Reference.
1.9.14 fixes a silent failure in the skill-observability hooks. PostToolUse and PreToolUse hooks read CLAUDE_TOOL_* environment variables that Claude Code never sets; the payload arrives as JSON on stdin. The affected hooks now read stdin first, with an env-var fallback for the test harness, and a shared hook_io reader centralizes the contract. skill_execution_logger had been exiting 0 without logging, which starved the [Learning] discussion digests of input. The release also adds /speckit-converge, which checks the codebase against spec.md, plan.md, and tasks.md and appends any unbuilt work as new tasks. See the CHANGELOG for the full history.
- Claude Code 2.1.16+ (2.1.32+ for agent teams, 2.1.38+ for security features). - Python 3.9+ for hooks (macOS ships 3.9.6). Hook code must stay 3.9-compatible; plugin packages may target 3.10+ via virtual environments. See the [Plugin Development Guide][dev-guide] for the rules.
Requires Claude Code 2.1.16+ and Python 3.9+ for hooks.
```bash
/plugin marketplace add athola/claude-night-market /plugin install sanctum@claude-night-market # Git workflows /plugin install pensive@claude-night-market # Code review /plugin install spec-kit@claude-night-market # Spec-driven dev ```
Run claude --init once after installing. Prefer one command? npx skills add athola/claude-night-market installs everything; opkg i gh@athola/claude-night-market --plugins sanctum,pensive installs a subset. Full options are in the Installation Guide.
If theSkilltool is unavailable, read skill files directly atplugins/{plugin}/skills/{skill-name}/SKILL.md.
make create-plugin NAME=my-plugin
make validate
make lint && make test
A plugin directory holds .claude-plugin/plugin.json (metadata) plus any of commands/, skills/, hooks/, agents/, and tests/, with a Makefile and pyproject.toml. See the [Plugin Development Guide][dev-guide] for structure and naming conventions.
优质Claude增强方案,融合工程最佳实践。插件设计全面、实用性强,285星关注度证明价值。非常适合追求代码质量的团队使用。
AI Skill Hub 为第三方内容聚合平台,本页面信息基于公开数据整理,不对工具功能和质量作任何法律背书。
建议在沙箱或测试环境中充分验证后,再部署至生产环境,并做好必要的安全评估。
✅ MIT 协议 — 最宽松的开源协议之一,可自由商用、修改、分发,仅需保留版权声明。
总体来看,claude-night-market AI工具 是一款质量优秀的AI工具,在同类工具中具备一定竞争力。AI Skill Hub 将持续追踪其更新动态,建议收藏备用,结合自身场景选择合适时机引入使用。
| 原始名称 | claude-night-market |
| 原始描述 | 开源Claude技能:23 Claude Code plugins: TDD enforcement hooks, git/PR workflows, spec-driven dev。⭐285 · Python |
| Topics | Claude插件代码工程化TDD开发Git工作流Python |
| GitHub | https://github.com/athola/claude-night-market |
| License | MIT |
| 语言 | Python |
收录时间:2026-05-19 · 更新时间:2026-05-19 · License:MIT · AI Skill Hub 不对第三方内容的准确性作法律背书。