Ready to supercharge your AI agents?

Install any skill in seconds. Free to start, no credit card required.

Get Started Free →

Claude MD · luongnv89 | DecimalAI

agent toolingby luongnv89

Claude MD

luongnv89/claude-md

Source luongnv89/claude-howto ↗License MIT

Create or update CLAUDE.md files following best practices for optimal AI agent onboarding

SkillScore77Maintained

Automatic

AI Engineer pack

Last verified 9/24/2026

What it changes

Passed 15 of 19 test cases with the skill, and 12 of 19 without it.

Without skill64%

With skill77%

Checks it passed that the model alone missed

Advises offloading detailed documentation into an agent_docs directory.
Explains that system prompts consume around 50 instructions from the context budget.
Recommends placing non-obvious traps and environment quirks in a Known Issues section.

and 2 more in the full report

5 fixed12 passed either way3 still failing2 broke

Pass-rate lift: +14 pp
Tokens: +87%
Agent turns: 0%
Response time: -1%

Model gemini-3.6-flashMeasured 9/24/2026v15 · latest is v2017 of 22 cases passed with skill · 19 comparable

Tokens, turns and time describe resource use, not a dollar price.

This benchmark measured an earlier version of the skill.

A newer attempt on gemini-3.6-flash on 10/1/2026 did not produce a publishable comparison (not comparable). The snapshot above is the previously measured run.

Use this skill

Save it into your project's skills folder. Claude Code picks it up in its next session.

curl -fsSL --create-dirs -o .claude/skills/luongnv89-claude-md/SKILL.md https://app.decimal.ai/s/luongnv89-claude-md/SKILL.md

Want it pinned and updatable? pip install "decimalai>=0.15", then decimalai skills add luongnv89-claude-md, and start Claude Code with claude --plugin-dir "$(git rev-parse --show-toplevel)/.agents"

1 · One-time — install the CLI (docs ↗)

pip install "decimalai>=0.15"

2 · Get the skill — writes .agents/skills/luongnv89-claude-md/ and pins it in .decimal/skills.lock

decimalai skills add luongnv89-claude-md

No CLI? Get the same file — curl · raw file

curl -fsSL --create-dirs -o .claude/skills/luongnv89-claude-md/SKILL.md https://app.decimal.ai/s/luongnv89-claude-md/SKILL.md

Raw file: /s/luongnv89-claude-md/SKILL.md ↗ · machine-readable summary at /s/luongnv89-claude-md.json ↗

Safety checks: 3 of 3 passed

Code scan CleanIntent PassedContent Clean

See it in action

One of 5 test cases the skill fixed. Same model, same prompt, with and without the skill.

1 of 5

Prompt

Developers frequently hit an obscure cache bug when running integration tests unless `REDIS_FLUSH=true` is set. Where should this operational detail be placed in CLAUDE.md?

What was checked, without and with the skill
Checked	Without skill	With skill
Recommends placing non-obvious traps and environment quirks in a Known Issues section.	Missed	Passed

case-14 · gemini-3.6-flash · 9/24/2026 · answers are capped and redacted

What's inside

The instructions your model reads when the skill loads.

SKILL.md211 linessingle file

用户输入

$ARGUMENTS

在继续之前，你必须先考虑用户输入（如果不为空）。用户可能会指定：

create - 从零创建新的 CLAUDE.md
update - 改进已有的 CLAUDE.md
audit - 分析并报告当前 CLAUDE.md 的质量
一个具体路径，用于创建或更新（例如 src/api/CLAUDE.md 代表目录级说明）

核心原则

LLM 是无状态的：CLAUDE.md 是每次对话中唯一会自动包含的文件。它是让 AI agent 了解代码库的主要入门文档。

黄金法则

少即是多：前沿 LLM 大约能遵循 150-200 条指令。Claude Code 的系统提示词本身已经占了大约 50 条，因此 CLAUDE.md 必须聚焦且简洁。
只放通用信息：只包含每次会话都适用的内容。任务特定的说明应该放在单独文件里。
不要把 Claude 当成 lint 工具：风格指南会膨胀上下文并降低指令遵循效果。应改用确定性工具（如 prettier、eslint 等）。
绝不自动生成：CLAUDE.md 是 AI harness 中杠杆最高的位置。应该经过认真思考后手工编写。

执行流程

1. 项目分析

首先分析当前项目状态：

检查是否存在已有的 CLAUDE.md 文件：
- 根目录：./CLAUDE.md 或 .claude/CLAUDE.md
- 目录级：**/CLAUDE.md
- 全局用户配置：~/.claude/CLAUDE.md
识别项目结构：
- 技术栈（语言、框架）
- 项目类型（monorepo、单体应用、库）

Track record

Benchmark

15 / 19

test cases passed, vs 12 / 19 without

Adoption

Users: 1
Times used: 13

Safety and source details

SkillSafety

✓ 3 of 3 passed

Code scan15 of 15 checks clean

0 critical · 0 warning · 0 info — scanner v5 — 9/30/2026

View 15 scanner checks

live_secretremote_code_executionreverse_shelldata_exfiltrationssrf_metadataagent_snoopinganti_refusaldestructive_commandsobfuscated_unicodeunicode_homoglyphopaque_blobsuspicious_urltool_overreachtrigger_abuseprompt_injection_phrasing

IntentSafe

LLM judge · does the skill do what it claims

ContentClean

LLM judge · policy & harmful-content review

Source

Imported

luongnv89 / claude-howto

03-skills/claude-md/SKILL.md

View on GitHub ↗

License MITImported 9/30/2026Version v20

More skills from the same source and nearby in the registry, with their headline benchmark lift.