Agent skill

Roadmap Generator

by alirezarezvani in alirezarezvani/claude-cto-team

Generate phased implementation roadmaps with Epic/Story/Task breakdown, effort estimates, and validation checkpoints.

MITAuto-check passedAgent Workflows

Install Roadmap Generator

skills CLI
$ npx skills add alirezarezvani/claude-cto-team --skill roadmap-generator -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install alirezarezvani/claude-cto-team roadmap-generator --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/alirezarezvani/claude-cto-team.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/roadmap-generator .claude/skills/roadmap-generator && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
roadmap-generator
GitHub stars
117
Token cost
~1.9k tokens
SKILL.md length
475 words
Files
3
Skills in repo
12
Repo updated
First seen
Licence
MIT

At a glance

Generate phased implementation roadmaps with Epic/Story/Task breakdown, effort estimates, and validation checkpoints.

  • Works in 4 steps: Include buffer: Add 20-30% for unknowns → Account for context switching: Multiply… → New technology penalty: Add 50% for… → …
  • Cto-architect needs to create actionable technical roadmaps from architecture designs
  • SKILL.md covers When to Use, Roadmap Structure, Epic/Story/Task Hierarchy and Effort Estimation Framework, plus 6 more sections
  • Runs Python scripts from its folder

What it does

Roadmap Generator is an agent skill from alirezarezvani/claude-cto-team. Generate phased implementation roadmaps with Epic/Story/Task breakdown, effort estimates, and validation checkpoints. Use when cto-architect needs to create actionable technical roadmaps from architecture designs.

Its SKILL.md is about 1.9k tokens, which your agent loads only when the skill is triggered. The skill folder holds 2 other files (for example `estimation-guide.md` and `generator.py`).

It sits in Agent Workflows, covering Task breakdown. The repository describes itself as: Your personal CTO Team for Claude Code . These Subagents will help you challenging yourself while you plan and execute. The licence is MIT.

When your agent uses it

  • Cto-architect needs to create actionable technical roadmaps from architecture designs
  • Tasks that involve Task breakdown

Example prompts

  • “/roadmap-generator”

Requirements

  • Python 3

Workflow steps

4 steps, taken from the first numbered list in SKILL.md.

  1. Include buffer: Add 20-30% for unknowns
  2. Account for context switching: Multiply by 1.3 for teams juggling priorities
  3. New technology penalty: Add 50% for unfamiliar tech
  4. Integration tax: Add 20% for each external system integration

What it can do on your machine

Read from SKILL.md and the folder at commit a5bbb78. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    Ships script files (Python), which the agent can run.

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Roadmap Generator loads about 1.9k tokens when it runs. Until then it costs about 58 tokens; SKILL.md has 475 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~58
When it runs · the whole SKILL.md, loaded when a task matches
~1.9k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from alirezarezvani/claude-cto-team at commit a5bbb78, republished under its MIT licence (© alirezarezvani). 475 words, ~1,852 tokens.

Download SKILL.mdSave it as .claude/skills/roadmap-generator/SKILL.md (or your agent's skills folder). This skill also uses 2 other files; get the full folder from GitHub.
name
roadmap-generator
description
Generate phased implementation roadmaps with Epic/Story/Task breakdown, effort estimates, and validation checkpoints. Use when cto-architect needs to create actionable technical roadmaps from architecture designs.

Roadmap Generator

Creates structured implementation roadmaps that transform architecture designs into actionable plans with clear phases, milestones, and validation gates.

When to Use

  • After architecture design is complete
  • When translating strategic goals into execution plans
  • Creating project timelines with realistic effort estimates
  • Breaking down large initiatives into manageable phases

Roadmap Structure

Three-Phase Framework

Every roadmap follows MVP → Scale → Advanced phases:

Phase 1: MVP (Foundation)
├── Goal: Prove core value proposition
├── Duration: Typically 6-12 weeks
├── Success Criteria: Core functionality working
└── Exit Gate: User validation / metrics threshold

Phase 2: Scale (Growth)
├── Goal: Handle production load, improve reliability
├── Duration: Typically 8-16 weeks
├── Success Criteria: Performance SLAs met
└── Exit Gate: Load testing passed / uptime targets

Phase 3: Advanced (Optimization)
├── Goal: Competitive features, optimization
├── Duration: Ongoing
├── Success Criteria: Feature parity / differentiation
└── Exit Gate: Business metrics achieved

Epic/Story/Task Hierarchy

Epic

High-level capability that delivers business value.

  • Duration: 2-6 weeks
  • Format: "Enable [user] to [capability]"
  • Example: "Enable customers to receive real-time order notifications"
Story

User-facing functionality within an epic.

  • Duration: 2-5 days
  • Format: "As a [user], I want to [action] so that [benefit]"
  • Example: "As a customer, I want push notifications so I know when my order ships"
Task

Technical work to complete a story.

  • Duration: 2-8 hours
  • Format: "[Verb] [object] [context]"
  • Example: "Implement WebSocket connection handler for notification service"

Effort Estimation Framework

T-Shirt Sizing
SizeStory PointsTypical DurationCharacteristics
XS12-4 hoursTrivial change, no unknowns
S20.5-1 daySimple, well-understood
M31-2 daysSome complexity, minor unknowns
L53-5 daysComplex, some research needed
XL81-2 weeksVery complex, significant unknowns
XXL13+> 2 weeksShould be broken down
Estimation Guidelines
  1. Include buffer: Add 20-30% for unknowns
  2. Account for context switching: Multiply by 1.3 for teams juggling priorities
  3. New technology penalty: Add 50% for unfamiliar tech
  4. Integration tax: Add 20% for each external system integration
Team Velocity Calculation
Effective Capacity = Team Size × Working Days × Focus Factor × Skill Factor

Focus Factor:
- Dedicated team: 0.8
- 50% allocated: 0.4
- Ad-hoc: 0.2

Skill Factor:
- Expert team: 1.0
- Experienced: 0.8
- Learning curve: 0.5

Validation Checkpoints

Phase Gate Reviews

Each phase ends with a validation gate:

markdown
## Phase 1 Exit Gate

### Go Criteria
- [ ] Core features functional in staging
- [ ] Unit test coverage > 70%
- [ ] Integration tests passing
- [ ] Performance baseline established
- [ ] Security review completed

### No-Go Signals
- Critical bugs unresolved
- Core functionality missing
- Team capacity insufficient for Phase 2
- Business requirements changed significantly

### Decision
[ ] GO - Proceed to Phase 2
[ ] CONDITIONAL GO - Proceed with identified risks
[ ] NO-GO - Address blockers first
Mid-Phase Checkpoints
  • Week 2: Architecture validation
  • Week 4: Integration milestone
  • Week 6: Feature complete checkpoint
  • Weekly: Sprint review and course correction

Dependency Management

Show full SKILL.md (198 more words)Show less
Dependency Types
TypeDescriptionMitigation
TechnicalService A needs Service BStart B early, use mocks
TeamNeed DevOps for deploymentReserve capacity early
ExternalThird-party API integrationValidate early, have fallback
DataNeed production data for testingCreate synthetic data
Critical Path Identification
  1. List all dependencies
  2. Identify longest chain
  3. Mark critical path items
  4. Add buffer to critical path (25%)
  5. Parallelize non-critical work

Output Format

Roadmap Document Structure
markdown
# Implementation Roadmap: [Project Name]

**Created**: [Date]
**Owner**: [Team/Person]
**Architecture Reference**: [Link to architecture doc]

## Executive Summary
[2-3 sentences on approach and timeline]

## Timeline Overview
[Visual timeline or Gantt representation]

## Phase 1: MVP (Weeks 1-8)

### Phase Goals
- [Goal 1]
- [Goal 2]

### Epics

#### Epic 1.1: [Name]
**Duration**: [X weeks]
**Dependencies**: [List]

| Story | Points | Owner | Dependencies |
|-------|--------|-------|--------------|
| [Story 1] | M | [Team] | None |
| [Story 2] | L | [Team] | Story 1 |

**Tasks for Story 1**:
- [ ] [Task 1] (S)
- [ ] [Task 2] (M)

### Phase 1 Exit Criteria
- [ ] [Criterion 1]
- [ ] [Criterion 2]

### Phase 1 Risks
| Risk | Probability | Impact | Mitigation |
|------|-------------|--------|------------|
| [Risk] | High/Med/Low | High/Med/Low | [Action] |

---

## Phase 2: Scale (Weeks 9-16)
[Same structure as Phase 1]

---

## Phase 3: Advanced (Weeks 17+)
[Same structure as Phase 1]

---

## Resource Requirements

### Team Composition
| Role | Phase 1 | Phase 2 | Phase 3 |
|------|---------|---------|---------|
| Backend | 2 FTE | 3 FTE | 2 FTE |
| Frontend | 1 FTE | 2 FTE | 1 FTE |
| DevOps | 0.5 FTE | 1 FTE | 0.5 FTE |

### Infrastructure Costs
| Phase | Monthly Cost | Notes |
|-------|-------------|-------|
| Phase 1 | $X | Development environment |
| Phase 2 | $Y | Staging + production |
| Phase 3 | $Z | Full scale |

---

## Success Metrics

| Metric | Phase 1 Target | Phase 2 Target | Phase 3 Target |
|--------|---------------|----------------|----------------|
| [Metric 1] | [Value] | [Value] | [Value] |
| [Metric 2] | [Value] | [Value] | [Value] |

---

## Appendix

### Assumptions
- [Assumption 1]
- [Assumption 2]

### Open Questions
- [Question 1]
- [Question 2]

Anti-Patterns to Avoid

The Big Bang

Planning everything in detail upfront without iteration. Fix: Plan Phase 1 in detail, Phase 2 at epic level, Phase 3 at theme level.

The Feature Factory

Listing features without connecting to business outcomes. Fix: Every epic must connect to a measurable business goal.

The Happy Path

No buffer, no risk mitigation, assumes everything goes perfectly. Fix: Add 25-30% buffer, identify top 5 risks with mitigations.

The Kitchen Sink

Including every possible feature in MVP. Fix: Ruthlessly cut to core value proposition only.


Python Utilities

This skill includes Python utilities for roadmap generation:

  • generator.py - Core roadmap generation logic
  • templates/ - Output templates (markdown, JSON)

See generator.py for programmatic roadmap generation.


References

© alirezarezvani, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 2 other files in skills/roadmap-generator of alirezarezvani/claude-cto-team.

  • SKILL.md
  • estimation-guide.md
  • generator.py

Open the folder on GitHubat commit a5bbb78

Compare with similar skills

Roadmap Generator next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Roadmap Generator compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Roadmap Generator this skillalirezarezvani/claude-cto-team117—~1.9kAutomated safety check: PassMIT
Multi-Role Spec and Task Breakdownmylukin/agent-foreman250—~5.1kAutomated safety check: NotesNone
Scope KnifeMAGA2010/hackathon-run367—~1.3kAutomated safety check: PassMIT
Wayfinder Planning Mapsrengwu/wayfinder-maps134—~3.5kAutomated safety check: PassMIT
Autospec Tasksariel-frischer/autospec144—~2.5kAutomated safety check: PassMIT
Oma Pmfirst-fluke/oh-my-agent1.3k—~1.7kAutomated safety check: PassMIT

Similar skills

  • Runs a requirement through four research-backed specialist agents, a PM, a UX designer, a tech architect and QA, to produce implementable tasks.

    250 GitHub stars~5.1k tokensUpdated 8 mo ago
    Agent WorkflowsAuto-check: notes
  • Scope Knife

    MAGA2010/hackathon-run

    Forces a KEEP, CUT, or DEFER decision on every feature when scope is too large, no MVP consensus exists, or time is running out.

    367 GitHub stars~1.3k tokensUpdated yesterday
    Agent WorkflowsAuto-check passed
  • Wayfinder Planning Maps

    rengwu/wayfinder-maps

    Plans work too big for one agent session as a shared map of investigation tickets, resolved one at a time until the route to the destination is clear.

    134 GitHub stars~3.5k tokensUpdated 2 days ago
    Agent WorkflowsAuto-check passed
  • Autospec Tasks

    ariel-frischer/autospec

    Generate YAML task breakdown from implementation plan. An agent skill from ariel-frischer/autospec.

    144 GitHub stars~2.5k tokensUpdated 10 days ago
    Agent WorkflowsAuto-check passed
  • Oma Pm

    first-fluke/oh-my-agent

    Product manager that decomposes requirements into actionable tasks with priorities and dependencies.

    1.3k GitHub stars~1.7k tokensUpdated today
    Agent WorkflowsAuto-check passed
  • Plan

    softspark/ai-toolkit

    Breaks features/goals into phased plans with task lists, agent assignments, dependencies.

    179 GitHub stars~1.3k tokensUpdated yesterday
    Agent WorkflowsAuto-check passed

More from alirezarezvani/claude-cto-team

All 12 skills in this repo
  • Antipattern Detector

    alirezarezvani/claude-cto-team

    Detect common technical and organizational anti-patterns in proposals, architectures, and plans.

    117 GitHub stars~2.1k tokensUpdated 9 mo ago
    Auto-check passed
  • Architecture Pattern Selector

    alirezarezvani/claude-cto-team

    Recommend architecture patterns (monolith, microservices, serverless, modular monolith) based on scale, team size, and constraints.

    117 GitHub stars~1.6k tokensUpdated 9 mo ago
    Auto-check passed
  • Assumption Challenger

    alirezarezvani/claude-cto-team

    Identify and challenge implicit assumptions in plans, proposals, and technical decisions.

    117 GitHub stars~2.4k tokensUpdated 9 mo ago
    Auto-check passed
  • Cost Estimator

    alirezarezvani/claude-cto-team

    Infrastructure and development cost estimation for technical projects.

    117 GitHub stars~3k tokensUpdated 9 mo ago
    Auto-check passed
  • ML Cv Specialist

    alirezarezvani/claude-cto-team

    Deep expertise in ML/CV model selection, training pipelines, and inference architecture.

    117 GitHub stars~3.1k tokensUpdated 9 mo ago
    Auto-check passed
  • Request Analyzer

    alirezarezvani/claude-cto-team

    Analyze incoming user requests to detect intent, request type (design/validate/debug/document), complexity level, and identify vague requirements or buzzwords that need clarification.

    117 GitHub stars~1.3k tokensUpdated 9 mo ago
    Auto-check passed

Questions about Roadmap Generator

What does Roadmap Generator do?

Generate phased implementation roadmaps with Epic/Story/Task breakdown, effort estimates, and validation checkpoints. Roadmap Generator is an agent skill from alirezarezvani/claude-cto-team. Generate phased implementation roadmaps with Epic/Story/Task breakdown, effort estimates, and validation checkpoints.

When should I use Roadmap Generator?

Roadmap Generator fits situations like: cto-architect needs to create actionable technical roadmaps from architecture designs; tasks that involve Task breakdown.

How do I install Roadmap Generator in Claude Code?

Run `npx skills add alirezarezvani/claude-cto-team --skill roadmap-generator -a claude-code`. Or copy the skill folder (skills/roadmap-generator in alirezarezvani/claude-cto-team) into .claude/skills/roadmap-generator in your project. Claude Code loads it when a task matches its description.

How do I install Roadmap Generator in Codex?

Run `npx skills add alirezarezvani/claude-cto-team --skill roadmap-generator -a codex`. Or copy the skill folder (skills/roadmap-generator in alirezarezvani/claude-cto-team) into .agents/skills/roadmap-generator in your project. Codex loads it when a task matches its description.

Can I use Roadmap Generator in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add alirezarezvani/claude-cto-team --skill roadmap-generator -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/roadmap-generator, .gemini/skills/roadmap-generator, .github/skills/roadmap-generator and .opencode/skills/roadmap-generator in your project.

What does Roadmap Generator need to run?

Going by SKILL.md and its folder, Roadmap Generator needs Python for the scripts in its folder. Our summary lists: Python 3.

Does Roadmap Generator access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Roadmap Generator safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Roadmap Generator use?

Roadmap Generator is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Roadmap Generator use?

About 1.9k tokens (SKILL.md is roughly 7.4k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Roadmap Generator?

Skills that share tags, products or a category with Roadmap Generator: Multi-Role Spec and Task Breakdown (mylukin/agent-foreman, 250 stars), Scope Knife (MAGA2010/hackathon-run, 367 stars), Wayfinder Planning Maps (rengwu/wayfinder-maps, 134 stars) and Autospec Tasks (ariel-frischer/autospec, 144 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Roadmap Generator?

alirezarezvani (a GitHub user) maintains it in alirezarezvani/claude-cto-team, which has 117 GitHub stars. The repository holds 12 skills in this directory. The repository was last updated on December 18, 2025.

Source: alirezarezvani/claude-cto-team on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.