Ready to supercharge your AI agents?

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

Get Started Free →

Example Skill — measured AI agent skill | DecimalAI

nikkiunitary185/example-skill

SkillScore96Maintained

데모용 예시 스킬입니다. `/autoimprove` 테스트에 사용됩니다.

by nikkiunitary185

Links this skill to your agents and keeps it current with the author’s updates.

Automatic

Coding pack

decimalai skills pull nikkiunitary185-example-skill

Get this skill — curl · raw file

curl -fsSL https://app.decimal.ai/s/nikkiunitary185-example-skill/SKILL.md

Raw file: /s/nikkiunitary185-example-skill/SKILL.md ↗ · machine-readable summary at /s/nikkiunitary185-example-skill.json ↗

In productionGlobal

how this skill behaves on real traffic · last 30 days

No production data for this skill yet — usage numbers appear here once agents start running it.

Anonymized aggregate across every org using this skill — proof from real production use, not a demo.

Does this skill help? · Benchmark: with vs. withoutsign in to run this on your agents

23 test cases from the publisher’s eval.yaml · each run twice on gemini-3.6-flash — with the skill injected, then without · last run 7d ago

Yes — +83% lift-54% tokens0% turns96% of whole cases pass with skill (22/23)

Test case	Without → With	Effect	Δ tokens	Δ turns
case-15	✗→✓	▲ Improved	14%	0%
case-08	✗→✓	▲ Improved	-70%	0%
case-09	✗→✓	▲ Improved	8%	0%
case-01	✗→✓	▲ Improved	-57%	0%
case-07	✗→✓	▲ Improved	-76%	0%

Showing 5 of 23 cases

SkillSafety

✓ 3 of 3 passed

Code scan15 of 15 checks clean

0 critical · 0 warning · 0 info — scanner v4 — 8/1/2026

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

nikkiunitary185 / autoimprove-cc

skills/example-skill/SKILL.md

View on GitHub ↗

License MITImported 8/1/2026Version v1

Skill contents

SKILL.md

Example Skill

데모용 예시 스킬입니다. /autoimprove 테스트에 사용됩니다.

Trigger

/example <message>

$ARGUMENTS의 첫 번째 인자를 message로 사용합니다.

Workflow

사용자 입력(message) 읽기
메시지를 대문자로 변환
결과를 "Echo: <변환된 메시지>" 형식으로 출력

Output Format

Echo: <UPPERCASED MESSAGE>

Rules

Do NOT 빈 메시지를 처리하지 않는다 — 오류 메시지를 반환
Do NOT 500자 이상의 메시지를 허용하지 않는다

Examples

bash
# 기본 사용
/example hello world
# → Echo: HELLO WORLD

# 한국어
/example 안녕하세요
# → Echo: 안녕하세요

주의: 한국어는 대소문자 변환이 적용되지 않으며 원문 그대로 반환됩니다.

Want to see if nikkiunitary185/example-skill would activate on your phrasing? Try it before you install — no LLM call, no signup.

Other measured skills in the registry, with their headline benchmark lift.