llm-friendly-context SKILL.md skillA

llm-friendly-context from shinpr/ai-coding-project-boilerplate is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.

mdr add shinpr/ai-coding-project-boilerplate/llm-friendly-context@git:20260923.86a3d79

Pins git:20260923.86a3d79 in mdr.lock. Pin the fingerprint instead.

Audit grade

A, 17 of 17 checks passed

Kind

SKILL.md skill

Repository

shinpr/ai-coding-project-boilerplate

Path

.claude/skills-zh-CN/llm-friendly-context/SKILL.md

Versions recorded

3

Latest version

git:20260923.86a3d79, committed Sep 23, 2026

First version recorded

Aug 31, 2026

Size

6,428 bytes

Repository stars

234

License

MIT

明确输入、输出、成功标准、决策和未解决的条件，使下游智能体无需猜测即可执行。用于编写或修改面向 LLM 的提示词、交接、规划产物、评审、报告或生成的指令。.

Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file the same grade.

What the file says

# 面向 LLM 的友好上下文

目标是实现稳定的下游执行：下一个智能体应当知道要读什么、要做什么、什么算成功，以及哪些未解决的决策会改变结果。

本技能规范面向 LLM 的输出，使提示词、交接和生成的产物清晰明确。调用方提供产物类型以及任何产物特定的模板或输入契约；只包含其使用方用来决策、行动或验证所需的信息。当使用方根据字段分支处理时，使用已声明契约的字段名和取值含义。

## 核心规则

1. **使用正向、可执行的指令**
   - 说明下一个智能体应当做什么
   - 将质量策略转化为正向标准
   - 示例：“在已记录的兼容性用例中保持现有公共 API 行为不变。”
   - 只有在禁令保护不可逆边界或已发布契约时才保留它；此时要同时说明受保护的条件和允许的行动

2. **将模糊指令具体化**
   - 用可观测的条件、路径、命令、schema、示例或决策规则替代主观用词
   - 以下用词在把决策留给下一个智能体时通常需要澄清：`appropriate`（合适）、`proper`（恰当）、`related`（相关）、`existing behavior`（现有行为）、`optional`（可选）、`as needed`（按需）、`if needed`（如有需要）、`per convention`（按惯例）、未解决的备选方案、`TBD`（待定）、`placeholder`（占位符）

3. **明确输出形态**
   - 定义使用方会用到的章节、字段、表格列、JSON 键或检查清单项
   - 对于交接，仅在会影响下一步转换时才包含生成的产物路径和状态字段

4. **提供最小且充分的上下文**
   - “充分”是指对所分配的行动而言充分，而非提供完整背景：所包含的每一项都会被该行动或其必须产出的结果所使用
   - 包含该行动会用到的目的、来源产物、硬性约束、已接受的决策和未解决的条件
   - 优先使用具体的文件路径和章节提示，而非宽泛的模块名
   - 只要引用还能改变范围内的决策、行动或验证结果，就继续追踪；一旦下一个链接只是确认已经决定的内容，就停止

5. **将复杂工作拆解为可验证的步骤**
   - 将有 3 个及以上目标或存在先后依赖关系的工作拆分为有序步骤
   - 每个步骤都需要一个检查点：什么依据能证明它已完成

6. **明确允许不确定性**
   - 在将某个缺失的操作细节视为未解决之前，先从约束性产物和具有代表性的仓库依据中解决它
   - 记录剩余的不确定性及其对结果或证明的影响。在已确认的边界内做出可逆的、仓库本地的选择，并保留所用的依据
…

Read the whole file at its exact version.

How to install

mdr add shinpr/ai-coding-project-boilerplate/llm-friendly-context@sha256:4735c34a6f46b4da

[![mdr](https://markdownregistry.com/badge/art_tupzplagvuwh7wkm.svg)](https://markdownregistry.com/a/art_tupzplagvuwh7wkm)

Versions

The registry has recorded 3 versions of this file, between Aug 31, 2026 and Sep 23, 2026, about one every 11 days.

Audit of the latest version

Source

API

GET https://markdownregistry.com/api/v1/artifacts/art_tupzplagvuwh7wkm
GET https://markdownregistry.com/api/v1/resolve?ref=shinpr/ai-coding-project-boilerplate/llm-friendly-context
GET https://markdownregistry.com/api/v1/blob/4735c34a6f46b4da35046ed6e4788de570d619133deebd53c35d238e45720bc2

Your AI assistant does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.

Guides: the SKILL.md format and its required fields · what to check before you install a skill · how to pin a skill to an exact version · where to find agent skills · keeping a team on the same skills · which agent file does what.

More from shinpr/ai-coding-project-boilerplate

Every file in shinpr/ai-coding-project-boilerplate

Other files named llm-friendly-context

Browse by kind, by grade A, or by owner.