Skip to main content
affpapa.org
RU EN
skill CX Codex

derisk-measurement-advisor — Claude Code skill: risk scan for ideas

A skill that scans a product or AI idea across ten risk dimensions, then sorts what it finds into act-now and watch-later. Useful before committing a roadmap slot.

Install into Claude Code · Skills CLI (Vercel) All methods and platforms ↓ 
npx skills add deanpeters/Product-Manager-Skills --skill derisk-measurement-advisor -a claude-code
Open on GitHub

What derisk-measurement-advisor does

Four internal dimensions come from DUFV: Desirability, Usability, Feasibility, Viability. The other six are PESTEL forces outside the organisation. Each risk the scan turns up gets a label, act on immediately or start tracking, and the output is a ranked risk register with next steps attached.

It runs as a conversation. Hand it the idea, its stage (concept, prototype, already in market) and whatever you have validated so far, and it uses that instead of asking again. Call it with nothing and it opens by asking you to describe the idea in a sentence or two.

The skill pushes back on labelling every single item urgent. If everything is act-now, nothing is prioritised, so it suggests a rough 40/60 split between acting and watching. What you get is a register to take to the team or leadership, not a finished experiment plan — designing the individual tests stays with you.

What it helps with

  • split an idea's risks into internal and external before it hits the roadmap
  • separate what needs a response now from what can be monitored
  • produce a prioritised risk register for leadership
  • find cheap tests before team and budget are committed
  • spot outside forces a product-only view would miss

Example prompts for the agent

  • De-risk this: an AI agent that drafts insurance claim responses, prototype stage
  • Run a PESTEL scan on the internal tool idea and tell me what to test first
  • What should we measure before this feature goes on the roadmap?

How to install derisk-measurement-advisor

1Skills CLI (Vercel)

npx skills add deanpeters/Product-Manager-Skills --skill derisk-measurement-advisor -a claude-code

2Manually: put the files in place

~/.claude/skills/derisk-measurement-advisor/SKILL.md

Copy the whole skill folder; for one project use .claude/skills/derisk-measurement-advisor/

Step by step, with commands for each platform: How to install skills in Claude Code: five ways

Questions about derisk-measurement-advisor

How do I install derisk-measurement-advisor in Claude Code?

Run npx skills add deanpeters/Product-Manager-Skills --skill derisk-measurement-advisor -a claude-code. The skill file lands at ~/.claude/skills/derisk-measurement-advisor/SKILL.md.

What does derisk-measurement-advisor do?

It walks a product or AI idea through ten risk dimensions and labels every finding as urgent or watch-only, giving you a ranked risk register.

How is this different from a generic risk checklist?

The scan is driven by your idea, its stage and what you have already validated, so the output reflects your context. The act-or-watch triage also keeps the list from turning into all-urgent noise.

Similar skills

Everything for AI and ML →
skill-creator official anthropics Creates and refines skills, then tests them with prompts, evaluations, and performance checks. 414,180installs writing-for-agents Matt Pocock Guidance for writing skills and agent-facing documents. Use it when editing AGENTS.md, CLAUDE.md, or reference files reached from them. 466,719installs media-use heygen-com Finds or generates media for HyperFrames videos, including voiceovers, music, cutouts, and color grades. Stores files locally in assets. CX Codex +1 1,100,000installs mcp-builder official anthropics This skill walks through building an MCP server in TypeScript or Python, from reading the protocol spec to writing tests and evaluation questions. 130,949installs subagent-driven-development Jesse Vincent This skill runs an implementation plan through fresh subagents for independent tasks and reviews each result. Use it for multi-step work in one session. CX Codex 237,746installs orchestration stablyai Coordinates supervised Orca workers with task DAGs, decision gates, and threaded messages. Fits workflows that split work across multiple agents. CX Codex +1 349,800installs

From the same set69

product-sense-interview-answer Guides practice for spoken product-sense interview answers, from framing assumptions to selecting an MVP. Use it for product design, improvement, or build-next prompts. CX Codex +1 1,700installs organic-growth-advisor A skill that runs a quick triage and points to one organic growth path: new segments, geographies, channels or products. CX Codex +1 1,500installs pm-skill-creator An interactive interview that shapes raw notes, frameworks, and product ideas into a structured SKILL.md draft. CX Codex +1 1,400installs agent-orchestration-advisor Plan parallel AI-agent workflows for complex product-management tasks. Use it to define agent roles, handoffs, and launch-readiness checks. CX Codex +1 1,300installs autonomous-investigation Sets the rules for research skills that run while you are away: question budget, a search plan, and Fact/Inference/Assumption labels on every claim. CX Codex +1 1,200installs competitive-analysis-process Orchestrates competitor research through a structured six-stage workflow tied to strategic choices. It produces battle cards, matrices, and threat assessments. CX Codex +1 1,200installs competitive-research-snapshot Builds a cited competitive snapshot with a comparison matrix and decision implications. Use it when positioning, roadmap, or deal work needs evidence. CX Codex +1 1,200installs incoming-request-advisor Splits an incoming message into the literal ask and the outcome behind it. Useful when a loaded ping, email or escalation needs a reply. CX Codex +1 1,200installs

Project sponsors

Companies that keep this analytics open
Gold sponsor
Nutra.Club

Impressions, clicks and code copies — open statistics. We keep the numbers public for the same reason NeBlask itself is public. Become a sponsor