Stats
Actions
Tags
From sentinel
Product and roadmap decision hygiene. Trigger when the user: is deciding what to build or prioritise ("on doit prioriser le backlog", "help me decide what to build next", "which features do we tackle first", "should we build or buy this"); is reviewing a product roadmap; asks about sprint planning, feature scoring, or backlog grooming; uses phrases like "product roadmap", "feature prioritization", "sprint planning", "backlog grooming", "build vs buy", "RICE", "MoSCoW". Also activates for: product noise audits, roadmap pre-mortem, sprint calibration, and feature scorecard generation.
How this skill is triggered — by the user, by Claude, or both
Slash command
/sentinel:product-managementThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
Product management combines ALL ingredients of systematic poor judgment
Product management combines ALL ingredients of systematic poor judgment (Kahneman, Sibony & Sunstein):
Load: skills/product-management/biases.yaml
Padding RICE/WSJF inputs to justify a pre-made decision. Question: "What would the RICE score be if someone who DISAGREES with building this feature filled in the inputs?"
The highest-paid person's opinion determines the roadmap. Question: "If the CPO/CEO had no opinion on this, what would the data say the priority is?"
Systematic underestimation of time, cost, and complexity. Question: "What's the median delivery time for features of similar scope in the last 12 months? How does this estimate compare?"
User research is done to validate a pre-decided solution, not to discover real problems. Question: "Did your research sessions start with the solution or with the problem? What would have happened if users hated the idea?"
Continuing a feature because it's already partially built. Question: "If this feature didn't exist at all today, would you start building it?"
The initial scope is always "MVP" but always grows before launch. Question: "What's the actual scope after all stakeholder feedback is incorporated? What's the minimum that delivers value if you cut 50%?"
Features are evaluated in isolation, not against what else could be built with the same resources. Question: "What are the 3 best things the engineering team could build instead? How does this feature compare?"
Loud recent feedback (Slack messages, support tickets, sales blockers) dominates prioritization over systematic user research. Question: "Is this priority driven by data or by whoever complained loudest this week? What does the usage data say?"
Load: skills/product-management/frameworks.yaml
6 independent dimensions:
"6 months post-launch. The feature flopped. What happened?" 7 product-specific failure modes.
Each PM/engineer estimates independently (no anchoring). Sentinel measures CV across estimates. CV > 40% = nobody actually knows.
6 techniques: churned user, competitor shipping first, cut 50%, user who never asked for this, rebuild from first principles, kill the roadmap.
Map all competing features by effort vs impact. Force explicit tradeoffs before committing. No free additions.
When /sentinel detects product management context:
STANDARD adds:
FULL adds:
npx claudepluginhub jamon8888/cc-suite --plugin SentinelProvides UI/UX resources: 50+ styles, color palettes, font pairings, guidelines, charts for web/mobile across React, Next.js, Vue, Svelte, Tailwind, React Native, Flutter. Aids planning, building, reviewing interfaces.
Fetches up-to-date documentation from Context7 for libraries and frameworks like React, Next.js, Prisma. Use for setup questions, API references, and code examples.