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。

加载中…

高分中文技能

principles

majiayu000's avatarfrom majiayu000★ 5

Provides development principles, guidelines, and VibeCoder guidance. Use when user mentions 原則, principles, ガイドライン, guidelines, VibeCoder, 安全性, safety, 差分編集, diff-aware. Triggers: 原則, principles, ガイドライン, VibeCoder, 安全性, 差分編集. Do not use for actual implementation - use impl skill instead.

tzurot-security

majiayu000's avatarfrom majiayu000★ 5

Security best practices for Tzurot v3 - Secret management, AI-specific security (prompt injection, PII scrubbing), Economic DoS prevention, Discord permission verification, microservices security, and supply chain integrity. Use when handling secrets, user input, or security-critical code.

read-before-edit

majiayu000's avatarfrom majiayu000★ 5

強制執行「先讀後寫」規範,確保 Claude 在修改任何檔案前完整閱讀相關代碼。當需要修改檔案時自動使用。

hook-audit

majiayu000's avatarfrom majiayu000★ 5

Comprehensive audit of Claude Code hooks for correctness, safety, and performance. Use when reviewing, validating, or debugging hooks, checking JSON stdin handling, verifying exit codes (0=allow, 2=block), analyzing error handling, fixing hook failures, ensuring safe degradation, optimizing performance, or validating settings.json registration. Also triggers when user asks about hook best practices, wants to create a new hook, or needs help with hook configuration.

enforcement

ingpoc's avatarfrom ingpoc★ 5

Use when implementing hooks that BLOCK invalid actions, creating quality gates for state transitions, or enforcing tested:true verification. Load when designing enforcement mechanisms. Uses exit code 2 to block, JSON permissionDecision:deny, or updatedInput modification. Rules are instructions; hooks are enforcement.

global-hook-setup

ingpoc's avatarfrom ingpoc★ 5

Use when setting up global hooks for Claude Code enforcement. Load when ~/.claude/hooks/ is missing or incomplete, or when explicitly requested. Installs 7 project-agnostic hooks (state transitions, git hygiene, outcome tracking). Run once per machine.

enumeration-protocol-execution

majiayu000's avatarfrom majiayu000★ 5

Enforce a Divergent-Convergent Scan loop to overcome 'Prevalent Noun Bias' and statistical probability reflexes (System 1).

data-anonymizer

majiayu000's avatarfrom majiayu000★ 5

检测并屏蔽文本和CSV文件中的个人身份信息(姓名、电子邮件、电话、SSN、地址)。支持多种屏蔽策略,可选可逆标记化。

readiness-check

majiayu000's avatarfrom majiayu000★ 5

Pre-run safety gate that evaluates readiness and recommends proceed/modify/skip decisions. Use before scheduled workouts to assess recovery status, injury signals, and training load based on sleep, soreness, and recent activity.

secure-multi-tenancy-isolation

majiayu000's avatarfrom majiayu000★ 5

确保多租户意识实例之间的安全隔离。

defense-implementation

majiayu000's avatarfrom majiayu000★ 5

实施缓解措施,创建输入过滤器,设计输出保护,并构建 LLM 安全的防御性提示。

zf-pipeline-contracts

majiayu000's avatarfrom majiayu000★ 5

Pipeline contract enforcement for ZINC-Fusion-V15 soybean oil forecasting system. Use when working on any ZINC-Fusion-V15 task involving schema definitions, training pipelines, L0 specialists, data ingestion, MLflow/Dagster configuration, or debugging contract drift. Triggers on mentions of fusion.db, specialist models, horizon encoding, quantile outputs, OOF predictions, or any ZINC-Fusion development work.

hti-fallback-guard

majiayu000's avatarfrom majiayu000★ 5

在此存储库中,请避免草率的后备逻辑。比起虚假的成功路径,更喜欢明确的失败、狭窄的错误处理和明确标记的 TODO。

load-anomaly-guard

majiayu000's avatarfrom majiayu000★ 5

检测不安全的训练负荷峰值(>20-30%周环比)并发出安全警报。用于夜间后台作业或审查每周训练量时,提供保守的调整建议。

lint-markdown

CsHeng's avatarfrom CsHeng★ 5

审计 Terraform 代码的反模式、安全问题以及最佳实践违规。当被要求审计、检查或检查 terraform 代码质量时使用。在 reports/YYYY-MM-DD/terraform-audit.md 下生成全面报告。(项目)

output-style-governance

CsHeng's avatarfrom CsHeng★ 5

安全控制和结构化日志实施。当需要安全日志记录指导时使用。

safety-memory

majiayu000's avatarfrom majiayu000★ 5

您处理安全内存的方法。在处理需要安全内存的文件时,请使用此技能。

privacy

SylphxAI's avatarfrom SylphxAI★ 4

Privacy and data protection - GDPR, CCPA, consent. Use when handling user data.

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。