Ready to supercharge your AI agents?

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

Get Started Free →

Wasabeef/전용 에이전트로 조사분석 태스크 자율 실행 | DecimalAI

researchby wasabeef

Wasabeef/전용 에이전트로 조사분석 태스크 자율 실행

wasabeef/전용-에이전트로-조사분석-태스크-자율-실행

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

전용 에이전트로 조사·분석 태스크 자율 실행. 「Task로 조사해줘」「조사해줘」「분석해줘」「검색해줘」등으로 기동.

SkillScore91Maintained

Automatic

AI Engineer pack

Last verified 8/16/2026

What it changes

Passed 20 of 22 test cases with the skill, and 11 of 22 without it.

Without skill50%

With skill91%

Checks it passed that the model alone missed

The response routes the request to ultrathink.
The response selects ultrathink instead of Task.
The response identifies ultrathink as the appropriate reasoning mode.

and 8 more in the full report

9 fixed11 passed either way2 still failing0 broke

Pass-rate lift: +41 pp
Tokens: +57%
Agent turns: 0%
Response time: -24%

Model gemini-3.6-flashMeasured 8/16/2026v120 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-489733/SKILL.md https://app.decimal.ai/s/wasabeef-9562e2/SKILL.md

Want it pinned and updatable? pip install "decimalai>=0.15", then decimalai skills add wasabeef-9562e2, 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-489733/ and pins it in .decimal/skills.lock

decimalai skills add wasabeef-9562e2

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

curl -fsSL --create-dirs -o .claude/skills/wasabeef-489733/SKILL.md https://app.decimal.ai/s/wasabeef-9562e2/SKILL.md

Raw file: /s/wasabeef-9562e2/SKILL.md ↗ · machine-readable summary at /s/wasabeef-9562e2.json ↗

Safety checks: 3 of 3 passed

Code scan CleanIntent PassedContent Clean

See it in action

One of 9 test cases the skill fixed. Same model, same prompt, with and without the skill.

1 of 9

Prompt

When evaluating an architectural trade-off between two database indexing strategies using purely existing knowledge without scanning files or external APIs, which execution mode should be used and why?

What was checked, without and with the skill
Checked	Without skill	With skill
The response selects ultrathink instead of Task.	Missed	Passed
The response states that ultrathink relies on internal model knowledge.	Missed	Passed

case-10 · 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.md223 linessingle file

전용 에이전트로 조사·분석 태스크 자율 실행

전용 에이전트를 기동해서 복잡한 검색·조사·분석 작업을 자율적으로 실행합니다. 여러 도구를 조합한 대규모 정보 처리로 컨텍스트 효율성을 중시합니다.

사용법

# Claude 에게 Task 의뢰
"[과제]를 Task 로 조사하세요"

Task 의 특징

자율적 실행

여러 도구를 조합해서 자동 실행
단계적 정보 수집과 분석
결과의 통합과 구조화된 보고

효율적 정보 처리

컨텍스트 소비의 최적화
대규모 파일 검색·해석
외부 정보원에서의 데이터 수집

품질 보증

정보원의 신뢰성 체크
다중 관점으로의 검증
누락 정보의 자동 보완

기본 예시

# 복잡한 코드베이스 조사
"이 기능이 어느 파일에 구현되어 있는지 Task 로 조사하세요"

# 대규모 파일 검색
"설정 파일의 불일치를 Task 로 특정하세요"

Track record

Benchmark

20 / 22

test cases passed, vs 11 / 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/task/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.