Ready to supercharge your AI agents?

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

Get Started Free →

Wasabeef/프로젝트 의존성을 분석하고 아키텍처 건전성을 평가한다 | DecimalAI

code reviewby wasabeef

Wasabeef/프로젝트 의존성을 분석하고 아키텍처 건전성을 평가한다

wasabeef/프로젝트-의존성을-분석하고-아키텍처-건전성을-평가한다

Source wasabeef/claude-code-cookbook ↗License Not recorded

프로젝트 의존성을 분석하고 아키텍처 건전성을 평가한다. 「의존성 분석해줘」「순환 의존 검출해줘」「아키텍처 문제는?」「모듈 결합도 확인」「레이어 위반 찾아줘」등으로 기동.

SkillScore84Maintained

Automatic

Coding pack

Last verified 8/16/2026

What it changes

Passed 21 of 25 test cases with the skill, and 9 of 25 without it.

Without skill36%

With skill84%

Checks it passed that the model alone missed

States project root directory execution as a prerequisite.
Applies rule definitions specified in the custom YAML path.
Uses `/dependency-analysis --compare HEAD~10` for revision diffing.

and 12 more in the full report

12 fixed9 passed either way4 still failing0 broke

Pass-rate lift: +48 pp
Tokens: +29%
Agent turns: 0%
Response time: -16%

Model gemini-3.6-flashMeasured 8/16/2026v121 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/wasabeef-e5637b/SKILL.md https://app.decimal.ai/s/wasabeef-60f730/SKILL.md

Want it pinned and updatable? pip install "decimalai>=0.15", then decimalai skills add wasabeef-60f730, 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/wasabeef-e5637b/ and pins it in .decimal/skills.lock

decimalai skills add wasabeef-60f730

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

curl -fsSL --create-dirs -o .claude/skills/wasabeef-e5637b/SKILL.md https://app.decimal.ai/s/wasabeef-60f730/SKILL.md

Raw file: /s/wasabeef-60f730/SKILL.md ↗ · machine-readable summary at /s/wasabeef-60f730.json ↗

Safety checks: 3 of 3 passed

Code scan CleanIntent PassedContent Clean

See it in action

One of 12 test cases the skill fixed. Same model, same prompt, with and without the skill.

1 of 12

Prompt

기본 설정 파일명 대신 커스텀 아키텍처 규칙 파일 `.architecture-rules.yml`을 지정하여 의존성 규칙을 검증하려면 어떤 명령 옵션을 지정해야 하나요?

What was checked, without and with the skill
Checked	Without skill	With skill
Uses `/dependency-analysis --rules .architecture-rules.yml` to specify custom rule files.	Missed	Passed
Applies rule definitions specified in the custom YAML path.	Missed	Passed

case-17 · gemini-3.6-flash · 8/16/2026 · answers are capped and redacted

What's inside

The instructions your model reads when the skill loads.

SKILL.md158 linessingle file

프로젝트 의존성을 분석하고 아키텍처 건전성을 평가한다

프로젝트의 의존관계를 분석하고 아키텍처 건전성을 평가합니다.

사용법

/dependency-analysis [옵션]

옵션

--visual : 의존관계를 시각적으로 표시
--circular : 순환 의존만 감지
--depth <숫자> : 분석 깊이 지정(기본값: 3)
--focus <경로> : 특정 모듈/디렉토리에 집중

기본 예제

# 프로젝트 전체 의존관계 분석
/dependency-analysis

# 순환 의존 감지
/dependency-analysis --circular

# 특정 모듈의 상세 분석
/dependency-analysis --focus src/core --depth 5

분석 항목

1. 의존관계 매트릭스

모듈 간 의존관계를 수치화해서 표시：

직접 의존
간접 의존
의존 깊이
팬인/팬아웃

Track record

Benchmark

21 / 25

test cases passed, vs 9 / 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

wasabeef / claude-code-cookbook

plugins/ko/skills/analyze-dependencies/SKILL.md

View on GitHub ↗

Imported 8/3/2026Version v1

Other skills for the same job

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

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