mirror of
https://github.com/magnus919/agent-skills.git
synced 2026-09-11 19:47:12 +03:00
Introduce the product-roadmapping-and-portfolio skill for outcome-based sequencing and strategic-bet management. Covers Now/Next/Later views, continue/pause/kill/revisit criteria, capacity allocation, dependency and confidence mapping, scenario planning, stakeholder narratives, and roadmap review cadences. Routes tactical prioritization (RICE, MoSCoW, Kano, OST) to their canonical owners in product-methodology and product-strategy. Includes: - SKILL.md with core methodology, loading guide, and routing table - README.md with human-facing overview and trigger guidance - 5 reference files (outcome roadmapping, strategic bets, dependency and confidence view, scenario comparison, roadmap review cadence) - 1 discovery brief reconciling duplicated framework references - 3 fillable templates (outcome roadmap, bet record, review record) - evals/evals.json with 5 schema-valid cases covering competing bets, dependency invalidation, low-confidence opportunity, capacity shortfall, and stop-bet-with-evidence Closes #189 Co-authored-by: username <username> Co-authored-by: factory-droid[bot] <138933559+factory-droid[bot]@users.noreply.github.com>
641 B
641 B
Dependency and Confidence View
Map cross-bet dependencies and calibrate portfolio confidence.
Dependency Types
- Blocking (A→B), Enabling (A-- >B), Shared-capacity (A||B), External (A→EXT)
Mapping
List all bets → identify dependencies → group into clusters → assess health (Independent/Exposed/Fragile/Blocked) → recalibrate confidence.
Dependency Invalidation
When a dependency is cancelled/delayed: pause dependent bet, reassess, record, communicate.
Confidence Calibration
At each review: new evidence? assumptions invalidated? dependency changes? Three Medium reviews without movement = team not learning.