Ready to supercharge your AI agents?

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

로드맵 관리 (Roadmap Manager) · modu-ai | DecimalAI

modu-ai/roadmap-manager

SkillScore82Maintained

프로젝트 로드맵·마일스톤 계획과 전략적 제휴(MOU) 초안, ESG 지속가능성 감사·DEI 전략 문서를 만들어 드립니다. 다음과 같은 요청 시 사용하세요: - "로드맵 정리해줘" - "마일스톤 계획 세워줘" - "MOU 초안 작성해줘" - "ESG 지속가능성 감사 해줘" - "DEI 정책 도입 로드맵 설계해줘" - "분기별 마일스톤과 담당자 정리해줘" 일정·리소스·파트너십·지속가능성 계획을 실행 가능한 문서로 정리하고, ai-slop-reviewer·humanize-korean으로 마무리할 수 있습니다. [책임 경계] 운영 케이던스(주간보고·스탠드업·회고·OKR 추적)는 moai-pm, 본 스킬은 제품 발견·로드맵/마일스톤 기획

productivityby modu-ai

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

Automatic

Project Management pack

1 · One-time — install the CLI (docs ↗)

pip install decimalai

2 · Get the skill — writes .claude/skills/modu-ai-roadmap-manager/SKILL.md

decimalai skills pull modu-ai-roadmap-manager --out .claude/skills/

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

curl -fsSL --create-dirs -o .claude/skills/modu-ai-roadmap-manager/SKILL.md https://app.decimal.ai/s/modu-ai-roadmap-manager/SKILL.md

Raw file: /s/modu-ai-roadmap-manager/SKILL.md ↗ · machine-readable summary at /s/modu-ai-roadmap-manager.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

22 test cases from the publisher’s eval.yaml · each run twice on gemini-3.6-flash — with the skill injected, then without · last run 6d ago

Yes — +14% lift · at higher cost+49% tokens0% turns82% of whole cases pass with skill (18/22)

Test case	Without → With	Effect	Δ tokens	Δ turns
case-15	✗→✓	▲ Improved	191%	0%
case-16	✗→✓	▲ Improved	4%	0%
case-17	✗→✓	▲ Improved	-12%	0%
case-13	✓→✓	＝ Same ✓	46%	0%
case-04	✓→✓	＝ Same ✓	52%	0%

Showing 5 of 22 cases

SkillSafety

✓ 3 of 3 passed

Code scan15 of 15 checks clean

0 critical · 0 warning · 0 info — scanner v4 — 8/3/2026

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

modu-ai / cowork-plugins

moai-product/skills/roadmap-manager/SKILL.md

View on GitHub ↗

License NOASSERTIONImported 8/3/2026Version v1Bundled 4 files

Skill contents

references/

SKILL.md

로드맵 관리 (Roadmap Manager)

개요

프로젝트 및 파트너십 전문 스킬입니다. 프로젝트 트래커(일정, 마일스톤, 리소스 관리), 파트너십 개발(전략적 제휴, MOU, 공동사업 기획), 지속가능성 감사(환경 영향 평가, 지속가능성 지표), 다양성 & 포용(DEI 전략, 포용적 조직 문화 설계)을 지원합니다.

트리거 키워드

로드맵, 마일스톤, 프로젝트 관리, 일정, 리소스, 파트너십, MOU, 제휴, 지속가능성, DEI

워크플로우

전략 가이드 로드 및 실행

사용자 요청 수신 → 해당 전략 가이드 판별 → references/{id}.md 로드 → 전략 가이드에 따라 실행 → 결과물 생성 후 사용자 검토 요청

복잡한 전략 판단 시 sequential-thinking MCP가 설치돼 있으면 mcp__sequential-thinking__sequentialthinking을 활용하고, 없으면 ultrathink 키워드 기반 심층 추론으로 대체합니다.

사용 예시

"신규 서비스 출시 6개월 로드맵을 만들어줘"
"분기별 마일스톤과 담당자를 정리해줘"
"스타트업과의 MOU 협력 초안을 작성해줘"
"ESG 공시 대응 지속가능성 감사 체크리스트를 만들어줘"
"조직 내 DEI 정책 도입 로드맵을 설계해줘"

출력 형식

프로젝트 로드맵 (마일스톤, 일정, 리소스 배분)
파트너십 MOU 초안
지속가능성 감사 보고서
DEI 전략 문서

주의사항

| 상황 | 해결 방법 | |------|-----------| | 이해관계자 요구사항 상충 | 우선순위 기준(고객 영향도 vs 기술 난이도 vs 비즈니스 가치)으로 정렬 매트릭스를 만들어 드립니다 | | 우선순위 기준 불명확 | RICE(Reach·Impact·Confidence·Effort) 또는 MoSCoW 방법론으로 기준을 함께 설계합니다 | | 리소스 배분 충돌 | 담당자 역할·책임 매트릭스(RACI)를 작성해 역할을 명확히 합니다 | | ESG 규정 파악 어려움 | KSSB 기준 또는 자산 규모별 공시 의무 범위를 안내해 드립니다 |

2026 한국 PM 로드맵 트렌드

로드맵 관리 도구 트렌드

| 도구 | 특징 | 한국 사용 현황 | |------|------|---------------| | Jira | 애자일 스프린트 중심 | 대기업·스타트업 표준 | | Notion | 유연한 문서 기반 | 스타트업 선호 | | Linear | 개발팀 친화적 | 기술 스타트업 증가 | | Asana | 프로젝트 추적 | 마케팅팀 선호 | | Figma | 디자인 + 로드맵 통합 | 프로덕트팀 활용 증가 |

한국 기업 파트너십 개발 특성

MOU 체결 문화: MOU는 사업 협력 공식화의 첫 단계. 구속력보다 협력 의지 표명 성격 강함
대기업 협력: 대기업 협력사 등록, 벤더 등록 절차가 복잡. 사전 심사 3-6개월 소요
스타트업 생태계: 판교·홍릉·성수 클러스터 중심. 투자사 네트워크 파트너십 전략 중요

ESG 지속가능성 (2026 의무화 대응)

공시 단계적 추진: 자산 2조 원 이상 상장사 대상 ESG 정보 공시 의무화가 추진 중 (시행 시점은 금융위 발표 기준 확인 필요)
KSSB 표준: 한국지속가능성기준위원회(KSSB) 기준 준수 필요
중소기업 선제 대응: 대기업 공급망 ESG 요구로 중소기업도 선제적 대응 필요

후처리 체인

MOU 초안·지속가능성 감사 보고서·DEI 전략 문서 같은 서술형 결과물을 완성한 뒤에는 다음 체인으로 마무리합니다(로드맵 일정표·RACI 매트릭스 같은 표·데이터는 제외, 본문 서술 부분에만 적용):

moai-product:roadmap-manager → moai-core:ai-slop-reviewer → moai-content:humanize-korean

moai-core:ai-slop-reviewer: AI 특유의 상투적 표현·과장·군더더기를 점검하고 다듬습니다.
moai-content:humanize-korean: 자연스러운 한국어 문장으로 최종 정제합니다.

Want to see if modu-ai/roadmap-manager would activate on your phrasing? Try it before you install — no LLM call, no signup.

Latest benchmark · publisher runVerified

8/22/2026, 22:14 UTC · 22 cases

Lift

+14%

82% vs 68%

Agent turns

1.0 vs 1.0

Tokens

+49%

3,103.18 vs 2,080.32

fail → pass · 3pass → pass · 15fail → fail · 4

Per-case results (22)

Case	Status	Duration (ms)			Turns			Tokens			Tool calls
Case	Status	Without	With	Δ	Without	With	Δ	Without	With	Δ	Without	With	Δ
case-13 Our overseas business development manager believes signing a Memorandum of Understanding (MOU) with a Korean strategic partner creates strict, legally binding obligations with immediate penalty clauses. How are MOUs interpreted in Korean business culture?	pass→pass	15,483	14,705	-5%	1	1	0%	2,306	3,367	+46%	0	0	—
case-01 Our product team needs a comprehensive functional PRD with technical edge-case specs, API endpoint definitions, and database schemas for a new user authentication feature. Please write the complete detailed feature PRD.	fail→fail	31,590	26,298	-17%	1	1	0%	6,180	6,182	+0%	0	0	—
case-02 We are finalizing a commercial partnership agreement and need a legal risk analysis of indemnification clauses, governing law, and liquidated damages enforceability under Korean contract law. Please review these legal terms.	fail→fail	14,363	26,033	+81%	1	1	0%	2,318	4,298	+85%	0	0	—
case-03 We are evaluating an acquisition target and need a discounted cash flow (DCF) valuation model, balance sheet audit, and financial statement ratio analysis. Please perform the financial audit.	fail→fail	11,824	23,313	+97%	1	1	0%	1,916	5,279	+176%	0	0	—
case-04 Our engineering leads want to pause feature development to refactor technical debt, while the enterprise sales team demands custom client features immediately. The team is tempted to flip a coin or let executive management decide arbitrarily. How should we objectively evaluate and resolve these conflicting stakeholder demands?	pass→pass	17,009	16,579	-3%	1	1	0%	2,485	3,766	+52%	0	0	—
case-05 We have 50 feature requests from four departments but no agreement on how to rank them. Department heads are pushing to prioritize items based on who shouts loudest. What established methodology should we adopt to define clear priority criteria?	pass→pass	15,090	15,468	+3%	1	1	0%	2,415	3,604	+49%	0	0	—
case-06 During project execution, team members are confused about who gives final sign-off versus who performs the actual work, leading to duplicate work and missed deadlines. How should we structure responsibility boundaries?	pass→pass	12,757	16,974	+33%	1	1	0%	2,084	3,948	+89%	0	0	—
case-07 An investor inquired about mandatory ESG information disclosures in South Korea. We assume ESG reporting is purely voluntary for all domestic listed companies regardless of size. Which compliance standard applies and what corporate asset benchmark triggers mandatory disclosure planning?	pass→pass	9,581	10,299	+7%	1	1	0%	1,619	2,814	+74%	0	0	—
case-08 Our tech startup signed an early intent document with a major Korean conglomerate. Our founders want to start billable project work next week, assuming vendor registration at Korean conglomerates is instant. What is a realistic timeline for enterprise vendor pre-screening in South Korea?	fail→fail	15,995	15,883	-1%	1	1	0%	2,496	3,634	+46%	0	0	—
case-09 A foreign corporate venture capital group visiting South Korea wants to network with local startup founders across major technology hubs outside of central Seoul. Which specific innovation clusters should they visit?	pass→pass	16,390	18,152	+11%	1	1	0%	2,647	3,888	+47%	0	0	—
case-10 Our fast-growing software engineering team wants an issue tracking platform tailored specifically for developer workflows rather than general business task lists. Which issue tracker is currently trending among developer-centric startups in Korea?	pass→pass	13,188	9,544	-28%	1	1	0%	1,928	2,512	+30%	0	0	—
case-11 A Seoul-based corporate IT division is standardizing its project management infrastructure across multi-team Agile sprint cycles. Which tool is considered the mainstream standard across large Korean enterprises and startups for Agile sprint tracking?	pass→pass	11,690	7,189	-39%	1	1	0%	1,689	2,312	+37%	0	0	—
case-12 A 12-person startup team in Seoul prefers managing project roadmaps within a flexible, document-driven workspace rather than rigid ticket boards. Which platform is widely favored by Korean startups for doc-based project tracking?	pass→pass	6,369	6,827	+7%	1	1	0%	900	2,231	+148%	0	0	—
case-14 When generating a multi-year strategic roadmap requiring complex reasoning in an environment where the sequential-thinking MCP server is not installed, what fallback keyword mechanism should be activated?	pass→pass	11,023	2,304	-79%	1	1	0%	1,643	1,544	-6%	0	0	—
case-15 Our product team is categorizing candidate features for a strategic product roadmap into basic expectations, performance satisfiers, and excitement delighters. They plan to order features strictly by submission date. Which classification framework should be used to map features to customer satisfaction levels?	fail→pass	5,289	9,873	+87%	1	1	0%	939	2,728	+191%	0	0	—
case-16 We finished writing a long narrative proposal for a corporate partnership MOU and sustainability audit. What is the initial post-processing reviewer tool in the processing chain for narrative outputs?	fail→pass	10,886	2,663	-76%	1	1	0%	1,554	1,619	+4%	0	0	—
case-17 After running a draft strategic proposal through an initial AI cliché and slop review, what final Korean language post-processing step should be applied to polish the text?	fail→pass	13,664	3,436	-75%	1	1	0%	1,992	1,746	-12%	0	0	—
case-18 We generated a structured 12-month milestone timeline table and a RACI matrix grid. Should narrative text humanization post-processing filters be applied to these structured data tables?	pass→pass	13,230	3,671	-72%	1	1	0%	1,872	1,752	-6%	0	0	—
case-19 A corporate strategy team is structuring goal alignment for a fast-growing venture. The VP insists on setting rigid 12-month fixed target KPIs with top-down mandates, assuming this is optimal for rapidly changing product roadmaps. Which objective-setting framework should be adopted to align cross-functional teams around quarterly ambitious outcomes?	pass→pass	5,757	12,350	+115%	1	1	0%	973	3,101	+219%	0	0	—
case-20 A mid-sized Korean supplier believes ESG sustainability requirements only apply to direct public equity issuers, so they plan to ignore ESG data requests from enterprise buyers. Is this supply chain assumption accurate?	pass→pass	11,769	12,618	+7%	1	1	0%	1,852	3,033	+64%	0	0	—
case-21 A cross-functional corporate marketing department in Seoul needs a task management platform optimized for creative campaign execution. Which tool is widely preferred by marketing teams in Korea?	pass→pass	12,873	11,200	-13%	1	1	0%	1,976	2,912	+47%	0	0	—
case-22 Our product management team wants to embed interactive visual designs and UI specs directly into feature roadmap boards without switching tools. Which design-centric platform is increasingly adopted in Korea for integrated roadmapping?	pass→pass	13,207	5,456	-59%	1	1	0%	1,983	2,000	+1%	0	0	—

These cases were also screened by the skill’s intent / safety pass.See the Trust review ↗Reproduce this benchmark in Colab ↗

How this skill was measured

DecimalAI ran this skill against gemini-3.6-flash twice over the same eval suite — once with the skill loaded and once without — and compared the two runs case by case. 22 cases were attempted. The headline lift of +14 percentage points is the difference between those two pass rates over the 22 comparable cases.

Model measured: gemini-3.6-flash
Graded by: gemini-3.6-flash
Grading method: judged
Verification: verified
Pass rate without the skill: 68.2%
Pass rate with the skill: 81.8%
Cases attempted: 22
Cases counted toward lift: 22
Cases that regressed: 0
Skill version measured: v1
Run completed: 8/22/2026, 22:14 UTC

Measured example — same prompt, with vs. without the skill · from the benchmark run · case case-15

Prompt

Our product team is categorizing candidate features for a strategic product roadmap into basic expectations, performance satisfiers, and excitement delighters. They plan to order features strictly by submission date. Which classification framework should be used to map features to customer satisfaction levels?

Without the skill loaded, the model failed this case. With it loaded, the same prompt on the same model passed. This is one improved case from the latest verified run; every case, including any that regressed, is in the table above.

Show both answers

SkillScore blends 4 signals1 of 4 complete

BenchmarkPass rate WITH skill on a verified run82

Live evalNeeds ≥20 evaluated traces in 30 days

AI ratingNeeds ≥10 rated traces

AdoptionNeeds ≥10 serves across ≥2 orgs in 30 days

Efficiency · separate axis (at equal correctness)+0% turns+51% tokens

Shown for transparency; not credited unless a verified run shows no correctness regression.

Backed by 1 of 4 signals — each added signal makes the score more robust.

Verified on gemini-3.6-flash · re-tested 6 days ago

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