agentleFS
Sign inStart free
arsudsandesh97arsudsandesh97/Revoact/skills/roadmap-doc/SKILL.md

roadmap-doc

Skill3 starsChanged 4 months agoMITView on GitHub

Generate a complete ROADMAP.md (or PHASES.md) file for any project. Use whenever the user asks to create, write, generate, or draft a ROADMAP.md or PHASES.md — a timeline document that shows what gets built when, in what order, with what milestones and dependencies.

The file

We split this skill into the rules it gives an agent

5 rules. About 0 are common, 5 are distinctive, and 0 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈5

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 0

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Add 20-30% buffer for unknowns

    line 47
  2. Distinctive:

    Not just "code complete" but "tested, documented, deployed"

    line 58
  3. Distinctive:

    Check risk indicators weekly

    line 64
  4. Distinctive:

    Update every 2 weeks minimum

    line 68
  5. Distinctive:

    When generating a ROADMAP.md:

    line 75

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

ROADMAP.md Author Skill

You are a project planner documenting the timeline and phased delivery of a software project.

Philosophy

A ROADMAP.md answers the question: "What are we building, in what order, and when?"

It shows:

  • Phases/releases and what goes in each
  • Timeline (dates or quarters)
  • Milestones (key deliverables and checkpoints)
  • Dependencies (what must happen before what)
  • Prioritization rationale (why this order)

The audience is everyone on the team — engineers need to know what's next, stakeholders need to track progress, and product managers need to communicate externally. This document changes over time as reality meets plan.

Structure

A ROADMAP.md has 8 core sections:

  1. Overview - Vision and timeline summary
  2. Current Status - Where we are right now
  3. Phased Delivery Plan - What's in each phase/release
  4. Timeline & Milestones - Key dates and checkpoints
  5. Dependencies & Blockers - What depends on what
  6. Success Criteria - How we measure completion
  7. Risks & Contingencies - What could go wrong
  8. Future Vision - Beyond current roadmap

Best Practices

1. Be Realistic, Not Optimistic

  • Add 20-30% buffer for unknowns
  • Account for holidays, sick days, context switching
  • Past velocity is the best predictor

2. Make Dependencies Explicit

  • Show what blocks what
  • Identify critical path
  • Track external dependencies closely

3. Define "Done" Clearly

  • Each phase has concrete completion criteria
  • Not just "code complete" but "tested, documented, deployed"
  • Get stakeholder sign-off

4. Track Risks Proactively

  • Identify risks early
  • Assign owners
  • Check risk indicators weekly

5. Update Regularly

  • Reality diverges from plan
  • Update every 2 weeks minimum
  • Track version history

Output Instructions

When generating a ROADMAP.md:

  1. Interview for timeline (duration, deadlines, constraints)
  2. Understand scope (what needs to be built)
  3. Start with overview (vision, timeline summary)
  4. Show current status (where we are now)
  5. Break into phases (logical chunks of value)
  6. Add milestones (key checkpoints and dates)
  7. Document dependencies (what blocks what)
  8. Define success (completion criteria)
  9. Address risks (what could go wrong + contingencies)
  10. Save as ROADMAP.md in working directory

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

Check your setup, free