Ready to supercharge your AI agents?

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

Get Started Free →

Wasabeef/역할 선택 가이드 | DecimalAI

agent toolingby wasabeef

Wasabeef/역할 선택 가이드

wasabeef/역할-선택-가이드

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

역할 선택 가이드. 「어떤 역할을 쓰면 좋아?」「역할 목록 보여줘」「역할 사용법은?」등으로 기동.

SkillScore100Maintained

Automatic

Coding pack

Last verified 8/16/2026

What it changes

Passed 22 of 22 test cases with the skill, and 6 of 22 without it.

Without skill27%

With skill100%

Checks it passed that the model alone missed

The response prescribes `/role qa`.
The response prescribes `/role-help`.
The response prescribes `/role mobile`.

and 13 more in the full report

16 fixed6 passed either way0 still failing0 broke

Pass-rate lift: +73 pp
Tokens: +37%
Agent turns: 0%
Response time: -41%

Model gemini-3.6-flashMeasured 8/16/2026v122 of 22 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-8bb0c6/SKILL.md https://app.decimal.ai/s/wasabeef-86d959/SKILL.md

Want it pinned and updatable? pip install "decimalai>=0.15", then decimalai skills add wasabeef-86d959, 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-8bb0c6/ and pins it in .decimal/skills.lock

decimalai skills add wasabeef-86d959

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

curl -fsSL --create-dirs -o .claude/skills/wasabeef-8bb0c6/SKILL.md https://app.decimal.ai/s/wasabeef-86d959/SKILL.md

Raw file: /s/wasabeef-86d959/SKILL.md ↗ · machine-readable summary at /s/wasabeef-86d959.json ↗

Safety checks: 3 of 3 passed

Code scan CleanIntent PassedContent Clean

See it in action

One of 16 test cases the skill fixed. Same model, same prompt, with and without the skill.

1 of 16

Prompt

현재 개발 중인 프로젝트의 상황이 복잡하고 어떤 역할 모드를 적용하는 것이 최적인지 스스로 판단하기 어렵습니다. 자동 제안을 받으려면 어떤 커맨드를 입력해야 하나요?

What was checked, without and with the skill
Checked	Without skill	With skill
The response prescribes `/smart-review`.	Missed	Passed

case-13 · 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.md276 linessingle file

역할 선택 가이드

어떤 역할을 사용해야 할지 고민될 때의 선택 가이드와 도움말 시스템입니다.

사용법

/role-help                      # 전반적인 역할 선택 가이드
/role-help <상황/문제>          # 특정 상황에서의 권장 역할
/role-help compare <역할 1>,<역할 2> # 역할 비교

기본 예제

# 일반적인 가이던스
/role-help
→ 이용 가능한 역할과 특징의 목록 표시

# 상황별 권장
/role-help "API 의 보안이 걱정"
→ security 역할의 권장과 사용 방법

# 역할 비교
/role-help compare frontend,mobile
→ frontend 와 mobile 의 차이와 사용 구분

상황별 역할 선택 가이드

🔒 보안 관련

이런 때는 security 역할:
✅ 로그인·인증 기능의 구현
✅ API 의 보안 취약점 체크
✅ 데이터 암호화·프라이버시 보호
✅ 보안 규정 준수 확인
✅ 침입 테스트·펜테스팅

Track record

Benchmark

22 / 22

test cases passed, vs 6 / 22 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/role-help/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.