Ready to supercharge your AI agents?

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

Get Started Free →

Code Quality Principles · doccker | DecimalAI

codingby doccker

Code Quality Principles

doccker/code-quality-principles

Source doccker/cc-use-exp ↗License NOASSERTION

当编写新模块、设计接口、重构代码或代码审查时触发。提供经典模块化六原则检查清单（大小适中/调用深度/扇入扇出/边界清晰/作用域内聚/可预测性），适用于 PR/Review/新模块设计场景。

SkillScore96Maintained

Automatic

Coding pack

Last verified 8/13/2026

What it changes

Passed 24 of 25 test cases with the skill, and 10 of 25 without it.

Without skill40%

With skill96%

Checks it passed that the model alone missed

Identifies that the Vue component exceeds the threshold of 200 lines
Identifies that the direct fan-out dependencies exceed the limit of 5
Evaluates direct dependencies against the maximum fan-out threshold of 5

and 15 more in the full report

14 fixed10 passed either way1 still failing0 broke

Pass-rate lift: +56 pp
Tokens: +44%
Agent turns: 0%
Response time: -17%

Model gemini-3.6-flashMeasured 8/13/2026v224 of 25 cases passed with skill

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

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/doccker-code-quality-principles/SKILL.md https://app.decimal.ai/s/doccker-code-quality-principles/SKILL.md

Want it pinned and updatable? pip install "decimalai>=0.15", then decimalai skills add doccker-code-quality-principles, 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/doccker-code-quality-principles/ and pins it in .decimal/skills.lock

decimalai skills add doccker-code-quality-principles

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

curl -fsSL --create-dirs -o .claude/skills/doccker-code-quality-principles/SKILL.md https://app.decimal.ai/s/doccker-code-quality-principles/SKILL.md

Raw file: /s/doccker-code-quality-principles/SKILL.md ↗ · machine-readable summary at /s/doccker-code-quality-principles.json ↗

Safety checks: 3 of 3 passed

Code scan CleanIntent PassedContent Clean

See it in action

One of 14 test cases the skill fixed. Same model, same prompt, with and without the skill.

1 of 14

Prompt

A Go microservice package contains a single handler.go file with 550 lines of HTTP handling code. Evaluate whether this file complies with standard Go file size boundaries.

What was checked, without and with the skill
Checked	Without skill	With skill
Identifies that the Go file exceeds the maximum limit of 400 lines for Go files	Missed	Passed
Recommends modularizing the Go handler logic into separate files or components	Passed	Passed

case-08 · gemini-3.6-flash · 8/13/2026 · answers are capped and redacted

What's inside

The instructions your model reads when the skill loads.

SKILL.md134 lines3 files

模块化设计六原则

经典软件工程设计原则在 AI 协作场景下的现代化清单。用作新模块设计、重构、代码审查时的对照表，不替代具体执行 skill。

触发场景

编写新模块、新服务、新接口
用户说"设计"、"拆分模块"、"评审"、"重构"
/review、/new-feature、/optimize、/design 命令在设计阶段
评估技术债时对照原则定位坏味道

六原则速查表

#	原则	一句话	衡量指标	详细案例
1	模块大小适中	单文件控制在职责边界内	行数/职责数	引用 size-check
2	减少调用深度	调用链尽量 ≤ 3 层	栈深度	modularity.md#调用深度
3	多扇入，少扇出	被复用 > 主动依赖	依赖数/被依赖数	modularity.md#扇入扇出
4	接口边界清晰	入参/出参/异常统一	统一响应包装	modularity.md#边界清晰
5	作用域内聚	改 A 不波及 B	跨模块副作用	引用 refactor-safety
6	功能可预测	同输入→同输出	幂等/无副作用/可测	predictability.md

1. 模块大小适中

主要执行交给 size-check skill；本 skill 仅作总纲提示。

核心：单文件超限是设计信号，不是格式问题。提示职责过载，应拆分。

默认阈值：Java ≤ 300 / Go ≤ 400 / Vue ≤ 200 / TS ≤ 300 / Python ≤ 300（项目可覆盖）。

2. 减少调用深度

Track record

Benchmark

24 / 25

test cases passed, vs 10 / 25 without

Adoption

Users: 0
Times used: 0

Safety and source details

SkillSafety

✓ 3 of 3 passed

Code scan15 of 15 checks clean

0 critical · 0 warning · 0 info — scanner v4 — 8/3/2026

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

doccker / cc-use-exp

.antigravity/skills/code-quality-principles/SKILL.md

View on GitHub ↗

License NOASSERTIONImported 8/3/2026Version v2Bundled 2 files

Other skills for the same job

Published skills whose descriptions closely match this one, with their headline benchmark lift.

doccker/cc-code-quality-principles当编写新模块、设计接口、重构代码或代码审查时触发。提供经典模块化六原则检查清单（大小适中/调用深度/扇入扇出/边界清晰/作用域内聚/可预测性），适用于 PR/Review/新模块设计场景。Near-identical description+36 pp pass-rate lift

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