Claude Skills 中文技能市场——为 Claude Code、Codex 与 Cursor 精选 Agent Skills
收录 90,000+ 开源 SKILL.md 工作流,提供中文解读、安全检测与高速下载,一行命令即可装到你的 AI 编程助手里。
高分中文技能
upgrade-integration
Integrate Carnegie Learning's UpGrade A/B testing platform into LMS and EdTech applications. Guides setup of decision points, experiment conditions, LTI/xAPI integration, and outcome logging. Use when asked to add A/B testing, experiments, or feature flags to educational software.
mechinterp-state
管理 SAE 特征分析的研究状态,包括假设、证据跟踪和研究历史
escape-room-balance-engineer
Balance escape room difficulty, timing, and hint systems to achieve 60-70% completion rate. Designs progressive difficulty curves, three-tier hint systems, stuck-point analysis, and playtest metrics. Use when balancing game difficulty, designing hint systems, analyzing playtest data, or optimizing escape room completion rates.
empirical-config-builder
Derive selection thresholds from market data instead of hardcoding. Trigger when: (1) reviewing hardcoded parameters, (2) volume/price thresholds seem arbitrary, (3) selection returns too many/few candidates.
analyzing-backtests
分析来自Jupyter笔记本的算法交易回测结果并生成摘要报告。当用户想要分析或总结回测笔记本时使用。
run-simulation
运行和分析一个或多个偏微分方程(PDE)模拟。
tile-snake-pattern-stitching
KINTSUGI 中的图像拼接的 SNAKE 与 RASTER 瓦片获取模式
backtest-datetime-visualization
将回测可视化从柱状索引/时间步转换为实际日期时间轴,以获得更清晰的时间上下文。
palantir-docs-local
Palantir 本地文档(en/latest)
subgroup-analysis
"进行亚组分析以检查效应调节。在以下情况下使用:(1) 测试预定的调节变量,(2) 探索异质性,(3) 识别差异效应,(4) 元分析综合。"
nixtla-cross-validator
Performs rigorous time series cross-validation using expanding and sliding windows.Use when needing to evaluate the performance of time series models on unseen data.Trigger with "cross validate time series", "evaluate forecasting model", "time series backtesting".
mechinterp-decoder
分析 SAE 解码器权重 - 输出影响、特征重要性和解码器相似度
nixtla-experiment-architect
Generate production-ready forecasting experiments with StatsForecast and TimeGPT. Use when setting up model benchmarking or cross-validation. Trigger with 'scaffold experiment' or 'compare models'.
tsa-integration
Trial Sequential Analysis for meta-analyses with information size calculations
numpy-polynomial
Modern polynomial API for fitting, root finding, and working with orthogonal series like Chebyshev and Legendre. Triggers: polynomial, polyfit, Chebyshev, Legendre, root finding.
optimizationexperiment-brief
准备实验简报,概述假设、设计、成功指标和运营计划。
mechinterp-state
管理SAE功能分析的研究状态,包括假设、证据跟踪和研究历史。
mechinterp-summarizer
将实验结果转换为Markdown研究笔记,并可选择用证据更新研究状态
常见问题
什么是 Claude Skills(Agent Skills)?
Skills 是一种标准化的 SKILL.md 指令包——把「何时触发、如何执行、使用哪些工具」写成结构化工作流,装入 Claude Code、Codex、Cursor 等 AI 编程助手后,Agent 遇到对应任务会自动调用,效果远好于每次手写提示词。
装了 Skill 之后怎么使用?
安装后无需手动调用:直接在 Claude Code / Cursor 里描述你的任务(如「帮我做 PR 代码审查」),Agent 检测到匹配的技能后会自动加载对应 SKILL.md 并按其流程执行。也可以在对话中显式要求「使用 xx skill」。
国内如何高速下载安装?
本站在 Cloudflare R2 托管了全部技能 ZIP 离线包,无需直连 GitHub:在详情页点击「Download ZIP」,或用 `npx skills add <owner/repo>` 一键安装;也可以复制 curl 命令直接解压到 ~/.claude/skills 目录。