Xl AI Language

为新项目设计、已有代码纳管、功能变更、架构重构和一致性校验提供任务架构流程。显式要求使用 Xl-Ai-Language 或任务架构流程，或当前项目存在 architecture.json 或 architecture/ 时，按本次任务范围启用。纯概念问答、只读查看和一次性实验走轻量路径。

5 stars 2 forksAI, LLMs & Agents

Install

skills CLI (Claude Code, Cursor, Codex and more)

npx skills add 40508597/xl-ai-language --skill xl-ai-language

Manual install

git clone --depth 1 https://github.com/40508597/xl-ai-language.git /tmp/xl-ai-language
mkdir -p ~/.claude/skills
cp -r /tmp/xl-ai-language/. ~/.claude/skills/xl-ai-language

Personal skills live in ~/.claude/skills. Use .claude/skills in a project folder to share a skill with your team.

From the SKILL.md

# Xl-Ai-Language

这是全局薄入口，只做定位和路由，不承载完整规则。

本技能指导 AI 组织项目、充分设计、逐层定位、修改实现与真实验证，并提供通用工程规则和外围工具；技能加载、命令调用和自动化集成由具体宿主负责。

## 定位规则

1. 先检测当前工作项目的 `architecture.json` 或 `architecture/`。
2. 根 `architecture.json` 含 `模块路由` 时，它就是项目总架构，沿相关子模块入口逐层读取；有 `指向` 时跟随既有总索引。仅有 `architecture/` 时检查实际索引；只有辅助文件则按创建/分析流程建立入口，既有入口失效则报告未验证并先修复。
3. 按本次需要的具体文件定位：优先读取当前项目根目录 `skills/`、`shared/` 中的对应文件。
4. 对应文件缺失时逐项回退到本技能安装目录；仅有同名目录不代表该能力文件存在。
5. 不得把项目状态、恢复点、变更记录或架构切片写入全局技能目录。

解析器自身从已加载 SKILL.md 所在目录定位：`python "<技能安装目录>/shared/scripts/resolve_tool.py" <工具名>`；保持工作目录为调用方项目。子能力层中的 `../../shared/` 路径按同一规则解析：按所需文件逐项检查当前项目根目录的 `shared/`；对应文件缺失时回退到本技能安装目录的 `shared/`。

## 路由顺序

先读 LAYER.md 判定本次范围；下列完整链路按需进入，轻量任务遵循该层的降级规则。

```text
用户需求
→ skills/xl-ai-language/LAYER.md
→ skills/project-depth-core/CORE.md
→ skills/architecture-json/SCHEMA.md
→ skills/agent-protocol/PROTOCOL.md（仅在需要时）
```

新项目默认把代码按真实模块目录组织，每个受管模块有本目录的 `architecture.json`，根文件保留全局目标、约束和总体路由。模块可递归包含子模块，任何一层可有自己的源码与测试；不把所有文件夹变成模块，不为层数而拆分。创建时先充分理解与设计再落目录，实现修改时从根沿相关分支取得契约、源码、测试与影响依据。详细协议按需读 [递归模块架构](shared/references/recursive-modules.md)。既有集中切片布局继续按已登记入口读取，不为形式迁移源码。

多个项目共用全局能力包时，只共享规则、脚本、模板和参考文档；每个项目的模块架构、任务状态、验证证据和恢复点互相独立。

## 可见回执

每轮实际使用本技能，都按 `skills/xl-ai-language/LAYER.md` 的可见进度规则，在主会话说明当前步骤、实际使用的能力、已确认结果、验证状态与下一步；关键步骤切换、验证结果或阻塞变化时更新，不能只在启动时亮一次名称。轻量任务合并简报，未执行的检查不得标为通过；不以汇报代替实际工作。

## 辅助参考

- 长程项目的查询、结构化变更、验证、协作、交接和操作恢复：按需读 [项目工具链](shared/references/project-toolchain.md)，使用 `taskarch.py`。现有深度设计与质量能力继续适用。

Read the full skill on GitHub

Details

Skill name: xl-ai-language
Repository: 40508597/xl-ai-language
License: MIT
Repo updated: 21 October 2026

FAQ

What does the Xl AI Language skill do?

How do I install the Xl AI Language skill?

skills CLI (Claude Code, Cursor, Codex and more): npx skills add 40508597/xl-ai-language --skill xl-ai-language. Skills go in ~/.claude/skills (personal) or .claude/skills (project), and Claude loads them automatically when a task matches the description.

Is Xl AI Language popular?

It lives in 40508597/xl-ai-language, which has 5 GitHub stars and 2 forks.

Related skills

方源 PPT 单页逻辑梳理

Liuguanyi2125/ppt-copywriting-logic-skill

当用户需要把原始材料、会议纪要、论文/方案资料、领导给的散乱内容或已有 PPT 页面，梳理成 PPT 页面级结论、文案层级、逻辑关系、页面结构和 AI 视觉提示词时使用。 Trigger: "帮我梳理 PPT 文案", "这页 PPT 逻辑怎么排", "把这些内容整理成 PPT", "方源 PPT 单页逻辑梳理", "方源梳理 PPT 文案", "PPT 页面文案和逻辑

AI, LLMs & Agents

Xiaoci

evoworkAI/xiaoci-skill

中文成稿的去 AI 味清理工具（消磁）。识别并清除中文文本里的模型写作痕迹：翻案腔、破折号揭晓、提示语冒号、空转句引列表、段首零回指评论、相邻句结构同款、大纲式编号小标题、理想化拟人喻体、翻译腔、宣传腔、模糊归因、助手元话语残留。当用户说「去 AI 味」「改得说人话」「太像 AI 写的」「像 ChatGPT 写的」「润色得自然点」「过一遍 AI 痕迹」「humanize 中文」「deslop」「这稿子读着假」时使用。也可在 AI 参与写作的稿件定稿发布前主动调用。 Use to remove AI writing tells from Chinese text while preserving facts, register and voice.

AI, LLMs & Agents

Agentic Sprint

vivialiudesign/agentic-sprint

Run a structured multi-agent design sprint to generate, evaluate, and select ideas using specialized AI agents. Use this skill whenever a user wants to explore a product or design problem using multiple perspectives, run a design sprint, brainstorm with different "hats" (user/business/data/system/design), evaluate ideas against principles, or converge on a direction from many options. Trigger this when users say things like "run a sprint on X", "help me think through this from different angles", "I need to explore this problem", "lets do an agentic sprint", or "what would the user/business/dat

AI, LLMs & Agents

Walk Forward Leakage Auditor

mospira/walkforward-audit

Audits time-based machine learning backtests, walk-forward validation, rolling retraining, forecasting evaluations, and temporal train/test pipelines for data leakage, faulty split logic, invalid feature timing, target leakage, calibration/tuning leakage, and misleading experiment comparisons. Use when agent needs to review or change walk-forward code, time-series ML experiments, trading backtests, forecasting notebooks, rolling CV logic, or any model evaluation where past-to-future chronology matters.

AI, LLMs & Agents

AI Native

initxy/ai-native

Turn a repo into an AI-native project — lay down AGENTS.md, standard verbs, gates, a doc-hygiene check, and the spec directory. Use when asked to initialize or set up a repo for coding agents, add or rework AGENTS.md, make a project AI-native, or re-run / upgrade that setup. Works on new and existing repos.

AI, LLMs & Agents

Token Optimizer

samibajwaisking/Token-Optimizer-Skill

Maximize Claude's output quality while minimizing input token usage. Use this skill whenever a user wants to compress prompts, reduce token consumption, extract maximum output from Claude, write high-density instructions, optimize system prompts, or improve AI communication efficiency. Trigger on phrases like "optimize my prompt", "too many tokens", "make this shorter but better", "get more from Claude", "compress this prompt", "write a better system prompt", "token efficient", or any request to improve how someone communicates with Claude or any LLM. Also trigger when building AI-powered tool

AI, LLMs & Agents

Browse the most popular Claude skills, all ai, llms & agents skills, or write your own with the skills generator.