Ready to supercharge your AI agents?

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

Get Started Free →

Wasabeef/복수 역할 병렬 분석으로 통합 보고서 생성 | DecimalAI

agent toolingby wasabeef

Wasabeef/복수 역할 병렬 분석으로 통합 보고서 생성

wasabeef/복수-역할-병렬-분석으로-통합-보고서-생성

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

복수 역할 병렬 분석으로 통합 보고서 생성. 「여러 관점에서 분석해줘」「멀티롤로」「병렬 분석해줘」등으로 기동.

SkillScore95Maintained

Automatic

Coding pack

Last verified 8/16/2026

What it changes

Passed 21 of 22 test cases with the skill, and 6 of 22 without it.

Without skill27%

With skill95%

Checks it passed that the model alone missed

Combines `frontend` and `mobile` roles.
Includes `analyzer` as a role identifier.
Specifies `mobile` as one of the role identifiers.

and 17 more in the full report

15 fixed6 passed either way1 still failing0 broke

Pass-rate lift: +68 pp
Tokens: +82%
Agent turns: 0%
Response time: -36%

Model gemini-3.6-flashMeasured 8/16/2026v121 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-d9c71e/SKILL.md https://app.decimal.ai/s/wasabeef-f1fad2/SKILL.md

Want it pinned and updatable? pip install "decimalai>=0.15", then decimalai skills add wasabeef-f1fad2, 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-d9c71e/ and pins it in .decimal/skills.lock

decimalai skills add wasabeef-f1fad2

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

curl -fsSL --create-dirs -o .claude/skills/wasabeef-d9c71e/SKILL.md https://app.decimal.ai/s/wasabeef-f1fad2/SKILL.md

Raw file: /s/wasabeef-f1fad2/SKILL.md ↗ · machine-readable summary at /s/wasabeef-f1fad2.json ↗

Safety checks: 3 of 3 passed

Code scan CleanIntent PassedContent Clean

See it in action

One of 15 test cases the skill fixed. Same model, same prompt, with and without the skill.

1 of 15

Prompt

We want to run a multi-role subagent analysis on `auth-service.ts` using security and backend roles. Write the command using the short single-letter flag for subagents.

What was checked, without and with the skill
Checked	Without skill	With skill
Uses `-a` placed directly after `security,backend`.	Missed	Passed

case-09 · 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.md314 linessingle file

복수 역할 병렬 분석으로 통합 보고서 생성

여러 역할로 동일한 대상을 병렬 분석하여 통합 보고서를 생성하는 명령어입니다.

사용법

/multi-role <역할 1>,<역할 2> [--agent|-a] [분석 대상]
/multi-role <역할 1>,<역할 2>,<역할 3> [--agent|-a] [분석 대상]

사용 가능한 역할

전문 분석 역할

security : 보안 감사 전문가
performance : 성능 최적화 전문가
analyzer : 근본 원인 분석 전문가
frontend : 프론트엔드·UI/UX 전문가
mobile : 모바일 개발 전문가
backend : 백엔드·서버사이드 전문가

개발 지원 역할

reviewer : 코드 리뷰 전문가
architect : 시스템 아키텍트
qa : 테스트 엔지니어

중요:

--agent 옵션은 역할 지정 직후에 배치하세요
메시지는 --agent 뒤에 작성하세요
올바른 예: /multi-role qa,architect --agent 계획을 평가하세요
잘못된 예: /multi-role qa,architect 계획을 평가하세요 --agent

옵션

--agent 또는 -a : 각 역할을 서브에이전트로 병렬 실행 (대규모 분석 시 권장)
- 이 옵션을 사용하면 각 역할의 description 에 자동 위임 촉진 문구("use PROACTIVELY" 등)가 포함된 경우, 더 적극적인 자동 위임이 활성화됩니다

Track record

Benchmark

21 / 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/multi-role/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.