agentleFS
creoaurea-devlabcreoaurea-devlab/agentic-skills/skills/roadmap/SKILL.md

roadmap

Skill4 starsChanged 8 months agoMITView on GitHub

Planning and roadmap management skill with machine-readable YAML schemas for initiatives, projects, milestones, epics, sprints, and tasks. Use this skill when the user asks to: create a project plan, manage a roadmap, track progress, organize sprints, prioritize a backlog, estimate timelines, define milestones, or says anything like: "plan this", "roadmap", "what should we build next", "prioritize", "sprint planning", "milestone", "backlog", "project status", "what's left to do", or when organizing multi-week work into structured delivery phases.

48 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use sequence, stakeholder-update and 10 more.

Other files people use alongside this one.

Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
  • GTMifySkill

    sequence

    Build a multi-channel outreach cadence (email + LinkedIn + phone) for a target persona or named prospect. Use when the user says 'build a sequence', 'outreach cadence', 'multi-touch sequence', 'multi-channel cadence', 'follow-up sequence', or needs a coordinated multi-channel play. Do NOT use for single cold emails — use cold-email instead.

    Also in 3 projects that use this

  • AnthropicSkill

    stakeholder-update

    Generate a stakeholder update tailored to audience and cadence. Use when writing a weekly or monthly status for leadership, announcing a launch, escalating a risk or blocker, or translating the same progress into exec-brief, engineering-detail, or customer-facing versions.

    Also in 3 projects that use this

  • EpistatesSkill

    strategy

    Plan weekly or monthly X content strategy. Use when the user wants to plan their content calendar, set growth goals, build a content pipeline, or think strategically about their X presence.

    Also in 3 projects that use this

  • ArvorCoSkill

    specify

    Create feature specification from natural language description. Use when starting a new feature or creating a spec. Triggers on: create spec, specify feature, new feature spec.

    Also in 3 projects that use this

  • GitHubSkill

    prd

    Generate high-quality Product Requirements Documents (PRDs) for software systems and AI-powered features. Includes executive summaries, user stories, technical specifications, and risk analysis.

    Also in 7 projects that use this

  • michalattSkill

    challenge

    Pressure-test plans, decisions, and directions by picking and answering the most relevant challenge questions for the current conversation

    Also in 3 projects that use this

The file

We split this skill into the rules it gives an agent

8 rules. 0 are common, 5 are distinctive, and 3 are very specific to this project.

  • 0

    Common

    Most of the 41 edited versions we read keep these.

  • 5

    Distinctive

    This author's own choices. Worth a look.

  • 3

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    No external tools needed — agents and humans read the same file.

    line 16
  2. Very specific:

    Create a .project/roadmap.yaml at the project root:

    line 36
  3. Distinctive:

    Use WSJF (Weighted Shortest Job First) for backlog ordering:

    line 86
  4. Distinctive:

    When asked to update the roadmap:

    line 118
  5. Very specific:

    Update status and updated fields

    line 122
  6. Very specific:

    If a milestone's exit criteria are all met → mark it done

    line 124
  7. Distinctive:

    Write the updated YAML back

    line 125
  8. Distinctive:

    When asked for status:

    line 127

“Common” is measured: kept by at least 6 in 10 of the 41 edited versions of this file we could read. “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

Flat-file, git-versioned roadmap management. One YAML file is the source of truth. No external tools needed — agents and humans read the same file.


Hierarchy

Initiative (strategic theme, e.g., "Platform Launch")
  └── Project (deliverable, e.g., "Auth System")
       └── Milestone (checkpoints with exit criteria)
            └── Epic (feature group)
                 └── Task (atomic work item, ≤1 day)

Each level has an id, title, status, and owner. Tasks also have estimate and priority.


Quick Start

Create a .project/roadmap.yaml at the project root:

roadmap:
  title: "My Project Roadmap"
  updated: 2026-03-18
  initiatives:
    - id: INIT-001
      title: "MVP Launch"
      status: in-progress
      projects:
        - id: PROJ-001
          title: "Core API"
          owner: "@team-backend"
          milestones:
            - id: MS-001
              title: "API v1 Complete"
              target_date: 2026-04-15
              exit_criteria:
                - "All CRUD endpoints passing integration tests"
                - "Auth middleware deployed"
              epics:
                - id: EPIC-001
                  title: "User Management"
                  tasks:
                    - id: T-001
                      title: "User registration endpoint"
                      status: done
                      estimate: 0.5d
                    - id: T-002
                      title: "User profile CRUD"
                      status: in-progress
                      estimate: 1d
                      priority: high

Status Values

planned → in-progress → done
                      → blocked (requires note)
                      → cut (descoped, requires reason)

Prioritization

Use WSJF (Weighted Shortest Job First) for backlog ordering:

WSJF = (business_value + time_criticality + risk_reduction) / job_size
FactorScale
business_value1-5
time_criticality1-5
risk_reduction1-5
job_size1-5 (1 = XS, 5 = XL)

Higher WSJF → do first.


Progress Computation

milestone_progress = done_tasks / total_tasks
project_progress = avg(milestone_progress for each milestone)
initiative_progress = avg(project_progress for each project)

Count only done tasks. blocked and cut tasks are excluded from the denominator if they have exclude_from_progress: true.


Agent Workflow for Updates

When asked to update the roadmap:

  1. Read .project/roadmap.yaml
  2. Identify which tasks/milestones changed
  3. Update status and updated fields
  4. Recompute progress for affected milestones/projects
  5. If a milestone's exit criteria are all met → mark it done
  6. Write the updated YAML back

When asked for status:

  1. Read the roadmap
  2. Compute progress at each level
  3. Report: what's done, what's in progress, what's blocked, what's next

Sprint Planning

For sprint-based teams, add a sprints section:

sprints:
  - id: SPRINT-01
    title: "Sprint 1"
    start: 2026-03-18
    end: 2026-03-29
    goal: "Complete user registration flow"
    tasks: [T-001, T-002, T-003]
    velocity_planned: 8
    velocity_actual: null  # filled at sprint end

Integration Points

  • Issue trackers — export tasks as GitHub Issues / Linear tickets
  • CI/CD — milestone exit criteria map to CI pipeline gates
  • Skills system — the implement skill reads the roadmap to understand what to build next

For the full YAML schema definition with all fields and validation rules, read references/schemas.md.


Anti-Patterns

  • Roadmap without exit criteria — milestones become meaningless checkboxes
  • Tasks larger than 1 day — break them down; large tasks hide complexity
  • No owner on projects — unowned work doesn't get done
  • Updating the tool but not the file — the YAML file is the source of truth, always
  • Planning everything upfront — plan one sprint ahead in detail, the rest in broad strokes

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.