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

la-bench-parser

dakesan's avatarfrom dakesan

解析LA-Bench格式的JSONL文件以按ID提取实验协议数据。当处理LA-Bench数据集以检索特定实验条目的结构化实验说明、材料、协议步骤、预期结果和参考文献时,应使用此技能。

pop-assessment-ux

jrc1883's avatarfrom jrc1883

使用具体启发式方法评估PopKit的用户体验,包括命令命名、错误消息和交互模式。

edu-demo-evaluator-free

hanialshater's avatarfrom hanialshater

像学习者一样观看教育演示(盲评估)。无测试用例。无基准。无评分标准。诚实地评估:印象、有效与无效之处、学习者影响、建议。输出:agent_X_free_eval.json

mova-wf-cycle-compute-compare-basic-wrapper

Leryk1981's avatarfrom Leryk1981

Deterministically compare two wf_cycle v1.1 runs (IDE vs CLI): compute metrics, compute score, pick winner, and write a compare folder with canonical artifacts.

skillset-smoke-test

outfitter-dev's avatarfrom outfitter-dev

Run and evaluate the Skillset smoke test (aliases, sets, and skill invocation) and interpret its JSON reports. Use this when validating $skill/$set behavior or checking Claude Code/Codex headless runs.

run-benchmark

nimag's avatarfrom nimag

Run and interpret the File API vs Inline benchmark for Gemini performance testing. Use when discussing performance optimization, caching strategies, or comparing document upload approaches.

fpf-skillplanning-initialize-baseline

venikman's avatarfrom venikman

Creates an initial SlotFillingsPlanItem (A.15.3) baseline.

mova-wf-cycle-winner-pack-basic-wrapper

Leryk1981's avatarfrom Leryk1981

Assemble a canonical wf_cycle winner_pack from compare artifacts (deterministic copy, replay check).

fpf-skillmetric-score-usability

venikman's avatarfrom venikman

Calculates the SkillUsabilityScore (U.Metric) for Zero-Shot Enactment.

fpf-skillmetric-evaluate-cslc

venikman's avatarfrom venikman

Evaluates a value against an FPF CSLC (Characteristic/Scale/Level/Coordinate) definition (A.18).

fpf-skillhello-world

venikman's avatarfrom venikman

最小参考技能,用于验证解析和加载。

my-skill

mandersogit's avatarfrom mandersogit

独立测试技能(不属于插件) - 用于通用技能测试。

validation-test

nevir's avatarfrom nevir

A test skill to validate that SessionStart hooks can create symlinks before skill discovery. If you can see this skill, the hook timing works correctly.

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。