Roadmap PlanningSAFE

Product Management skills framework built on battle-tested methods for Claude Code, Cowork, Codex, and AI agents.

The instruction file, verbatim from the audited commit — this is the text the model reads, and the surface the audit's instruction layer examines. Quoted here so you can judge it without cloning anything.

---
name: roadmap-planning
argument-hint: "[product and planning horizon]"
description: Plan a strategic roadmap across prioritization, epic definition, stakeholder alignment, and sequencing. Use when turning strategy into a release plan that teams can execute.
intent: >-
  Guide product managers through strategic roadmap planning by orchestrating prioritization, epic definition, stakeholder alignment, and release sequencing skills into a structured process. Use this to move from disconnected feature requests to a cohesive, outcome-driven roadmap that aligns stakeholders, sequences work logically, and communicates strategic intent—avoiding "feature factory" roadmaps that lack strategic narrative or customer-centric framing.
type: workflow
theme: strategy-positioning
best_for:
  - "Building a strategic roadmap that survives exec review"
  - "Prioritizing competing initiatives across multiple teams"
  - "Planning and sequencing work for the next quarter or half-year"
scenarios:
  - "I have 15 competing initiatives and need to build a Q2 roadmap my exec team will actually approve"
  - "I'm planning our 6-month product roadmap and need to sequence work across 3 teams"
estimated_time: "45-90 min"
---


## Purpose
Guide product managers through strategic roadmap planning by orchestrating prioritization, epic definition, stakeholder alignment, and release sequencing skills into a structured process. Use this to move from disconnected feature requests to a cohesive, outcome-driven roadmap that aligns stakeholders, sequences work logically, and communicates strategic intent—avoiding "feature factory" roadmaps that lack strategic narrative or customer-centric framing.

This is not a Gantt chart—it's a strategic communication tool that shows what you're building, why it matters, and how it ladders up to business outcomes.

## Input

**Works best with:** The product and planning horizon (next quarter, next year).
**Also useful:** Strategy or OKRs to ladder to, the candidate initiative list, team capacity, and known stakeholder pressures.

Anything supplied with the invocation itself — text after the skill name, a pasted context dump, or an appended `ARGUMENTS:` line — counts as answers already given. Use it and skip whatever it covers; don't re-ask.

**Arriving empty-handed? That works too.** The workflow starts by establishing strategic context, then moves through prioritization, epic definition, and sequencing.

**Example invocation:** `Plan a 2-quarter roadmap for our mobile app: here are our 3 OKRs and a list of 12 candidate initiatives.`

## Key Concepts

### What is Strategic Roadmap Planning?

Roadmap planning is the process of:
1. **Gathering inputs** — Customer problems, business goals, technical constraints
2. **Defining initiatives** — Epics with clear hypotheses and success metrics
3. **Prioritizing** — Rank initiatives by impact, effort, strategic fit
4. **Sequencing** — Organize into releases/quarters with logical dependencies
5. **Communicating** — Present roadmap to stakeholders with strategic narrative

### Types of Roadmaps

**Now/Next/Later Roadmap:**
- **Now:** Current quarter (committed)
- **Next:** Following quarter (high confidence)
- **Later:** Future exploration (low confidence)
- **Best for:** Agile teams, uncertainty, continuous discovery

**Theme-Based Roadmap:**
- Organize by strategic themes (e.g., "Retention," "Enterprise Expansion," "Mobile Experience")
- **Best for:** Communicating to execs, showing strategic intent

**Timeline Roadmap (Quarters):**
- Q1: Epics A, B; Q2: Epics C, D; Q3: Epics E, F
- **Best for:** Resource planning, stakeholder communication

**Feature-Based Roadmap (Anti-Pattern):**
- Lists features without context (e.g., "Dark mode," "SSO," "Advanced reporting")
- **Why it fails:** No strategic narrative, no customer problems framed

### Why This Works
- **Outcome-driven:** Ties initiatives to business/customer outcomes
- **Stakeholder alignment:** Transparent process reduces political friction
- **Strategic clarity:** Shows not just "what" but "why"
- **Flexible:** Adapts as you learn from discovery/delivery

### Anti-Patterns (What This Is NOT)
- **Not a commitment:** Roadmaps are strategic plans, not contracts
- **Not a feature list:** Roadmaps frame problems, not just solutions
- **Not waterfall:** Roadmaps evolve quarterly based on learning

### When to Use This
- Annual or quarterly planning cycles
- After product strategy session (translate strategy to roadmap)
- Onboarding new stakeholders (align on direction)
- Reframing existing roadmap (shift from feature-driven to outcome-driven)

### When NOT to Use This
- For tactical sprint planning (use backlog instead)
- When strategy is unclear (run product-strategy-session first)
- When stakeholders expect date commitments (address expectations first)

---

### Facilitation Source of Truth

When running this workflow as a guided conversation, use [`workshop-facilitation`](../workshop-facilitation/SKILL.md) as the interaction protocol.

It defines:
- session heads-up + entry mode (Guided, Context dump, Best guess)
- one-question turns with plain-language prompts
- progress labels (for example, Context Qx/8 and Scoring Qx/5)
- interruption handling and pause/resume behavior
- numbered recommendations at decision points
- quick-select numbered response options for regular questions (include `Other (specify)` when useful)

This file defines the workflow sequence and domain-specific outputs. If there is a conflict, follow this file's workflow logic.

## Application

Use `template.md` for the full fill-in structure.

This workflow orchestrates **5 phases** over **1-2 weeks**, using multiple component and interactive skills.

---

## Phase 1: Gather Inputs (Day 1-2)

**Goal:** Collect business goals, customer problems, technical constraints, stakeholder requests.

### Activities

**1. Review Business Goals (OKRs, Strategic Initiatives)**
- **Source:** Company OKRs, exec strategy memos, board decks
- **Qu

SAFEgrade B · trust 89/100 Nothing in the source contradicts what it says it does. Grade A is reserved for packages that have also passed the behavioural sandbox.

What the source does

Filesystem

none-observed

Network

none-observed

Shell

none-observed

Dependencies

pinned

Secrets in source

none-found

Findings (0)

No findings outside the package's declared scope.

Gates applied: no_behavioural_pass.