本文へ移動
cccskills
無料GitHub で公開

product-roadmap

Prioritize outcome-based product roadmaps, manage capacity and displaced work trade-offs, sequence learning milestones, and maintain portfolio coherence without dual ledgers or fake ROI. (triggers: `product roadmap prioritization`, `product portfolio trade-off`)

インストール方法を見る

含まれるファイル(10)

  • SKILL.md6.3 KB
  • evals/evals.json15.3 KB
  • references/citations-and-sources.md3.2 KB
  • references/evidence-mapping.md8.5 KB
  • references/examples.md15.7 KB
  • references/portfolio-tradeoffs.md4.3 KB
  • references/roadmap-protocol.md5.0 KB
  • references/semantic-rubrics.md7.9 KB
  • references/verification-cases.md23.6 KB
  • references/verification-procedures.md9.0 KB

SKILL.md(原文)

インストールする前に、エージェントに与えられる指示の中身を確認できます。

Product Roadmap & Portfolio Trade-offs

Priority: P0 (CRITICAL)

Sequence outcome-driven roadmaps, manage finite capacity and displaced work, anchor priorities in verified strategic authority, and maintain portfolio coherence without duplicating ledgers or conflating ranking scores with financial ROI.

1. Capability Preflight

Resolve and verify execution prerequisites across installed layouts before prioritizing roadmaps or evaluating portfolio trade-offs:

  1. Installed Location: Locate <agent-skill-root>/product-management/product-evidence/ (standard) or <agent-skill-root>/product-management-product-evidence/ (Kiro flattened). Body lookup via MCP is not local script/runtime proof.
  2. Component Integrity:
    • Package missing or excluded: emit gap Capability gap: product-management/product-evidence not installed or excluded; opt in at a reviewed ref and sync.
    • Script missing: emit gap Capability gap: validate-product-evidence.mjs missing from installed package; repair product-evidence installation.
    • Runtime engine: confirm Node.js $\ge 20.0.0$ (node --version). If $< 20$, emit gap Capability gap: Node.js runtime >= 20.0.0 required for local validator; current environment does not meet minimum engine requirement.
  3. Invocation inputs: confirm an existing absolute canonical authorized narrow authority root (not /, home, or a parent workspace), contained regular ledger file, concrete valid UTC --as-of, and --gate exactly structural|experiment|commit|release. CLI may take a contained relative ledger; library ledgerPath is absolute.
  4. Authority and data: inspect current exact strategy/business/authorization pairs, artifact bindings, source access/privacy/status/freshness, dependencies and cohort/team-capacity overlap. External/protected data are never fetched. Report installation, path/root, authority and evidence gaps separately; do not infer demand, consent or capacity.
  5. Follow Verification Procedures for exact revision, history and read-only portfolio predicates. Never broaden roots, install silently, validate placeholders, or infer permission from a green result.

2. Core Protocol

  1. Strategic Alignment & Opportunity Anchoring:
    • Align every roadmap item with authorized strategic directives (strategy_authority) and framed opportunities (OPP). If strategy is absent or conflicting, set strategy_authority: null and record strategy_gap.
    • Every candidate initiative must link to falsifiable hypotheses (HYP) and explicit non-goals.
  2. Capacity Constraints & Named Displaced Work:
    • Engineering and design capacity is strictly finite and zero-sum. Adding or accelerating an initiative must explicitly record the displaced work, deferred initiatives, or rejected alternatives in decision rationale.
    • Map technical, organizational, and regulatory dependencies explicitly. Never schedule dependent full-builds concurrently with unvalidated upstream bets.
  3. Prioritization Heuristics vs. Financial Reality:
    • Directional ranking scores (RICE, WSJF, Kano) are relative ordering heuristics, NOT validated customer demand or financial ROI.
    • Stakeholder calendar deadlines or executive commitments do NOT erase evidence gaps or validate unproven market assumptions.
  4. Learning Milestones Over Feature Timelines:
    • Structure roadmaps around learning milestones (risk reduction, hypothesis validation, prototype testing), not feature delivery Gantt charts.
    • Front-load high-uncertainty risks before committing capital or engineering capacity to full-scale delivery.
  5. Single Canonical Ledger & Portfolio Coherence:
    • Never duplicate or maintain a secondary mutable evidence ledger for portfolio or cross-product rollups. Each initiative retains one canonical ledger at docs/product/<slug>/evidence.json.
    • Multi-initiative portfolio views are read-only documents referencing canonical initiative ledgers at exact revisions.
    • Maintain strict separation between product discovery evidence and engineering delivery traces (Outcome v1 feature_status: not_started | requirements_ready | design_ready | partially_implemented | implemented | verified | released | blocked). Product discovery IDs stay strictly outside Outcome requirement arrays.

3. Anti-Patterns & Red Flags

  • No Deadlines as Demand: Never treat an executive or marketing deadline as proof of market demand.
  • No Score as Cash Return: Never present a RICE score as expected financial return, NPV, or net ROI.
  • No Invisible Displacement: Never insert a roadmap initiative without explicitly documenting what work was displaced.
  • No Dual Ledgers: Never duplicate initiative evidence into a separate mutable portfolio ledger.
  • No Feature Timelines Without Validation: Never commit fixed long-range delivery dates before validating core value hypotheses.

4. References

レビュー

まだレビューはありません。使ってみた感想をお寄せください。

同じリポジトリのスキル

概要と使いどころ

Upgrade an Android project to Android Gradle Plugin (AGP) 9. Use when migrating to AGP 9, updating Gradle build files, migrating to built-in Kotlin, or adopting the new AGP DSL.

日本語の概要は準備中です。原文の説明を表示しています。

HoangNguyen0403/agent-skills-standard5772026年10月15日 更新

Apply Clean Architecture layering, modularization, and Unidirectional Data Flow in Android projects. Use when setting up project structure, placing code in layers, configuring feature/core modules, or implementing UDF patterns; defer Compose state and ViewModel/StateFlow implementation to their specific skills.

日本語の概要は準備中です。原文の説明を表示しています。

HoangNguyen0403/agent-skills-standard5772026年10月15日 更新

Implement WorkManager and background processing correctly on Android. Use when creating Worker classes, scheduling tasks, choosing between WorkManager and Foreground Services, or setting up Hilt in workers; defer FCM and notification delivery to android-notifications.

日本語の概要は準備中です。原文の説明を表示しています。

HoangNguyen0403/agent-skills-standard5772026年10月15日 更新

Build high-performance declarative UI with Jetpack Compose. Use when writing Composable functions, optimizing recomposition, hoisting state, or working with LazyColumn and side effects; defer deep-link and navigation routing to android-navigation.

日本語の概要は準備中です。原文の説明を表示しています。

HoangNguyen0403/agent-skills-standard5772026年10月15日 更新

Migrate an Android XML View to Jetpack Compose following a structured 10-step workflow. Use when converting XML layouts to Compose, setting up Compose in an existing View-based project, or incrementally adopting Compose.

日本語の概要は準備中です。原文の説明を表示しています。

HoangNguyen0403/agent-skills-standard5772026年10月15日 更新

Write correct coroutine scopes, lifecycle collection, and dispatcher injection in Android production code. Use for suspend functions, coroutine scopes, and dispatcher mechanics; defer ViewModel StateFlow/LiveData architecture, Fragment lifecycle recipes, persistence/notifications, and unit-test recipes to their specific skills.

日本語の概要は準備中です。原文の説明を表示しています。

HoangNguyen0403/agent-skills-standard5772026年10月15日 更新

HoangNguyen0403 のスキルをすべて見る

このスキルの問題を報告する