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.

Install it, pinned
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-ja/llm-friendly-context/SKILL.md
Versions recorded
5
Latest version
git:20260923.86a3d79, committed Sep 23, 2026
First version recorded
Aug 9, 2026
Size
8,399 bytes
Repository stars
234
License
MIT

入力・出力・成功基準・決定事項・未解決条件を明確化し、下流エージェントが推測せず実行できるようにする。LLM向けのプロンプト・ハンドオフ・計画成果物・レビュー・レポート・生成指示を記述または改訂する時に使用。.

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

# LLM-Friendly Context

目標は、下流が安定して実行できるようにすることである。次のエージェントが、何を読み、何をし、何をもって成功とし、どの未解決の判断が結果を変えうるかを把握できる状態を目指す。

このスキルはLLM向け出力(プロンプト、ハンドオフ、生成物)の明確さを扱う。生成物の種類と、生成物固有のテンプレートまたは入力契約は呼び出し元が渡す。利用側が判断、実行、検証に使う情報だけを含める。利用側が値によって分岐する場合は、宣言された契約のフィールド名と値の意味を使用する。

## 中核ルール

1. **肯定形で実行可能な指示を使う**
   - 次のエージェントが何をすべきかを述べる
   - 品質ポリシーは肯定的な基準に変換する
   - 例: 「文書化された互換ケース全体で、既存の公開APIの振る舞いを維持する」
   - 禁止形を残すのは、それが不可逆な境界またはリリース済みの契約を守る場合に限る。その場合は、守る条件と許容されるアクションを併記する

2. **曖昧な指示を具体化する**
   - 主観的な語を、観測可能な条件、パス、コマンド、スキーマ、例、判断ルールに置き換える
   - 次のエージェントに判断を委ねる場合に明確化が必要になりやすい語: `appropriate`、`proper`、`related`、`existing behavior`、`optional`、`as needed`、`if needed`、`per convention`、未解決の代替案、`TBD`、`placeholder`

3. **出力構造を指定する**
   - 利用側が使うセクション、フィールド、表のカラム、JSONキー、チェックリスト項目を定義する
   - ハンドオフでは、次の遷移を制御する場合に限り、生成した成果物のパスとステータスフィールドを含める

4. **必要十分な最小限のコンテキストを与える**
   - 十分かどうかは、背景の網羅ではなく割り当てたアクションに対して判断する。含めた情報はすべて、そのアクションか、それが生み出すべき結果で使われる
   - 目的、出典となる成果物、厳格な制約、承認済みの判断、未解決条件のうち、そのアクションが使うものを含める
   - 大まかなモジュール名より、具体的なファイルパスとセクションヒントを優先する
   - 参照は、スコープ内の判断、アクション、検証結果を変えうる間はたどる。次のリンクが既に決まった内容を確認するだけになった時点で止める

5. **複雑な作業を検証可能なステップに分解する**
   - 目的が3つ以上、または逐次的な依存がある作業は、順序付きのステップに分割する
   - 各ステップには、何が完了を証明するかを示すチェックポイントを設ける
…

Read the whole file at its exact version.

How to install

The exact contents, by fingerprint
mdr add shinpr/ai-coding-project-boilerplate/llm-friendly-context@sha256:5566d5f2c5213714

The line at the top of this page pins the label git:20260923.86a3d79, which is what most people want. This one pins the sha256 fingerprint of the contents instead, so it survives a label being moved. Either way the exact version is written to mdr.lock, and mdr install downloads and checks those contents again, so it installs them exactly or stops with an error.

Badge

mdr badge

[![mdr](https://markdownregistry.com/badge/art_kauvk4vjq2hn4jrm.svg)](https://markdownregistry.com/a/art_kauvk4vjq2hn4jrm)

3 badge image fetches in 30 days. What the badge shows.

Versions

The registry has recorded 5 versions of this file, between Aug 9, 2026 and Sep 23, 2026, about one every 11 days.

versioncommittedcommitsizeaudit
git:20260923.86a3d79 latest2026-09-23 86a3d79 8,399 BA view · diff
git:20260901.fbc397a2026-09-01 fbc397a 8,005 BA view · diff
git:20260901.dd3607b2026-09-01 dd3607b 8,101 BA view · diff
git:20260828.9d50d562026-08-28 9d50d56 8,107 BA view · diff
git:20260809.e398e132026-08-09 e398e13 7,864 BA view

Audit of the latest version

A  17 of 17 checks passed. Fixed automatic checks with no AI involved, so the same checks give the same answer every run.
  • pass: Frontmatter block present
  • pass: Frontmatter declares a name
  • pass: Frontmatter declares a description
  • pass: Size between 200 bytes and 200 KB (8399 bytes)
  • pass: No zero-width or bidi control characters
  • pass: No instruction hidden inside an HTML comment
  • pass: No link to an exfiltration or paste host
  • pass: No credential-shaped string
  • pass: No instruction to send local credentials anywhere
  • pass: No text hidden with inline styles
  • pass: No prompt-injection phrasing
  • pass: No curl or wget piped into a shell
  • pass: No recursive delete of root, home or parent
  • pass: No instruction to read or print local credentials
  • pass: No base64 blob over 200 characters
  • pass: No link to a raw IP address
  • pass: No script tag

Source

GitHub

shinpr/ai-coding-project-boilerplate · 234 stars · license MIT · pushed 2026-10-14 · branch main

API

GET https://markdownregistry.com/api/v1/artifacts/art_kauvk4vjq2hn4jrm
GET https://markdownregistry.com/api/v1/resolve?ref=shinpr/ai-coding-project-boilerplate/llm-friendly-context
GET https://markdownregistry.com/api/v1/blob/5566d5f2c52137149fee8f5791b95ff282e4e1acceb8700b31861036879e97b3

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

coding-standards SKILL.md skill
shinpr/ai-coding-project-boilerplate · .claude/skills-en/coding-standards/SKILL.md · Detects code smells, anti-patterns, and readability issues. Use when implementing features, reviewing code, or…
git:20261014.578fed5 · audit A · 234 stars
documentation-criteria SKILL.md skill
shinpr/ai-coding-project-boilerplate · .claude/skills-en/documentation-criteria/SKILL.md · Determines which PRD, ADR, UI Spec, Design Doc, and Work Plan a change requires and where each is stored. Use when…
git:20260923.86a3d79 · audit A · 234 stars
frontend-technical-spec SKILL.md skill
shinpr/ai-coding-project-boilerplate · .claude/skills-en/frontend-technical-spec/SKILL.md · Defines React environment, component architecture, state/data flow, build verification, and frontend non-functional…
git:20260923.03f66be · audit A · 234 stars
frontend-typescript-rules SKILL.md skill
shinpr/ai-coding-project-boilerplate · .claude/skills-en/frontend-typescript-rules/SKILL.md · Applies React/TypeScript type safety, component design, and state management rules. Use when implementing React…
git:20260912.c0d4362 · audit A · 234 stars
frontend-typescript-testing SKILL.md skill
shinpr/ai-coding-project-boilerplate · .claude/skills-en/frontend-typescript-testing/SKILL.md · Designs frontend tests using the repository's configured React test and browser harnesses, including RTL, MSW, Vitest…
git:20261014.578fed5 · audit A · 234 stars
implementation-approach SKILL.md skill
shinpr/ai-coding-project-boilerplate · .claude/skills-en/implementation-approach/SKILL.md · Selects implementation strategy (vertical slice, horizontal, or hybrid) with risk assessment. Use when planning feature…
git:20261014.578fed5 · audit A · 234 stars
integration-e2e-testing SKILL.md skill
shinpr/ai-coding-project-boilerplate · .claude/skills-en/integration-e2e-testing/SKILL.md · Selects and designs the smallest integration/E2E test set that proves accepted behavior at an observable boundary. Use…
git:20261014.578fed5 · audit A · 234 stars
llm-friendly-context SKILL.md skill
shinpr/ai-coding-project-boilerplate · .claude/skills-en/llm-friendly-context/SKILL.md · Clarifies inputs, outputs, success criteria, decisions, and unresolved conditions so downstream agents can execute…
git:20260923.86a3d79 · audit A · 234 stars
project-context SKILL.md skill
shinpr/ai-coding-project-boilerplate · .claude/skills-en/project-context/SKILL.md · Marks project context as unconfigured until domain constraints, repository quality standards, phase, conventions, and…
git:20260901.b347ae2 · audit A · 234 stars
requirement-convergence SKILL.md skill
shinpr/ai-coding-project-boilerplate · .claude/skills-en/requirement-convergence/SKILL.md · Separates the outcome a change must produce from the requirements proposed to reach it, records what the user excluded…
git:20260923.558b381 · audit A · 234 stars
skill-optimization SKILL.md skill
shinpr/ai-coding-project-boilerplate · .claude/skills-en/skill-optimization/SKILL.md · Evaluates and optimizes skill file quality using 9 content patterns and 10 editing principles. Use when creating…
git:20260831.b183037 · audit A · 234 stars
subagents-orchestration-guide SKILL.md skill
shinpr/ai-coding-project-boilerplate · .claude/skills-en/subagents-orchestration-guide/SKILL.md · Coordinates subagents through scale-based planning, approval, implementation, verification, and escalation flows. Use…
git:20261003.24e6460 · audit A · 234 stars

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

Other files named llm-friendly-context

llm-friendly-context SKILL.md skill
shinpr/claude-code-workflows · dev-skills/skills/llm-friendly-context/SKILL.md · Clarifies inputs, outputs, success criteria, decisions, and unresolved conditions so downstream consumers can execute…
git:20261019.de01f9e · audit A · 703 stars
llm-friendly-context SKILL.md skill
shinpr/claude-code-workflows · dev-workflows-fullstack/skills/llm-friendly-context/SKILL.md · Clarifies inputs, outputs, success criteria, decisions, and unresolved conditions so downstream consumers can execute…
git:20260917.73d4471 · audit A · 703 stars
llm-friendly-context SKILL.md skill
shinpr/claude-code-workflows · skills/llm-friendly-context/SKILL.md · Clarifies inputs, outputs, success criteria, decisions, and unresolved conditions so downstream consumers can execute…
git:20260917.73d4471 · audit A · 703 stars
llm-friendly-context SKILL.md skill
shinpr/claude-code-workflows · dev-workflows/skills/llm-friendly-context/SKILL.md · Clarifies inputs, outputs, success criteria, decisions, and unresolved conditions so downstream consumers can execute…
git:20260917.73d4471 · audit A · 703 stars
llm-friendly-context SKILL.md skill
shinpr/claude-code-workflows · dev-workflows-frontend/skills/llm-friendly-context/SKILL.md · Clarifies inputs, outputs, success criteria, decisions, and unresolved conditions so downstream consumers can execute…
git:20261019.de01f9e · audit A · 703 stars
llm-friendly-context SKILL.md skill
shinpr/ai-coding-project-boilerplate · .claude/skills-en/llm-friendly-context/SKILL.md · Clarifies inputs, outputs, success criteria, decisions, and unresolved conditions so downstream agents can execute…
git:20260923.86a3d79 · audit A · 234 stars
llm-friendly-context SKILL.md skill
shinpr/ai-coding-project-boilerplate · .claude/skills-zh-CN/llm-friendly-context/SKILL.md · 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。
git:20260923.86a3d79 · audit A · 234 stars
llm-friendly-context SKILL.md skill
shinpr/codex-workflows · .agents/skills/llm-friendly-context/SKILL.md · Clarifies inputs, outputs, success criteria, decisions, and unresolved conditions so downstream agents can execute…
git:20261013.5a1e725 · audit A · 39 stars

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