agentleFS
darrenCWJdarrenCWJ/agent-skills-scaffold/.claude/skills/roadmap/SKILL.md

roadmap

Skill0 starsChanged 3 months agoMITView on GitHub

Maintain a living project-level roadmap of phases and milestones across many tasks and sessions. Use when a project outgrows a single plan, when the user asks where are we, what is next, show the roadmap, or describes multi-week/multi-milestone ambitions — and update it at EVERY ship phase and plan completion. Plans are per-task; the roadmap is the map they live on.

51 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

  • 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

  • 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

  • anombyte93Skill

    discover

    Phase 1 of the prd-taskmaster pipeline: brainstorm-driven discovery. Delegates to superpowers:brainstorming in Interactive Mode (one adaptive question at a time), or self-brainstorms in Autonomous Mode when no user is present. Intercepts before the brainstorming chain hands off to writing-plans — this skill owns the exit. Extracts constraints, calibrates scale (Solo / Team / Enterprise), and advances the pipeline to GENERATE.

    Also in 4 projects that use this

The file

Files
SKILL.md

Roadmap

A plan answers "how do I do this task"; the roadmap answers "where is this project, and what happens next". One roadmap per project, at docs/ROADMAP.md, created from templates/roadmap.md. It is a living document — a stale roadmap is worse than none because it lies with authority.

Structure (three horizons + status)

  • Milestones/phases — large units of value ("v1 shippable", "research complete", "migrated to X"), each with: status (⬜ not started / 🔄 in progress / ✅ done / ⏸ paused / ❌ dropped), exit criteria (what observable state means done — same falsifiability bar as plans), and links to the plan files that implement it.
  • Now / Next / Later — the honest priority view. NOW: at most 1–2 items actually being worked. NEXT: queued, roughly ordered. LATER: acknowledged, unordered, no false precision (no fake dates on things nobody has scoped).
  • Done log — completed milestones with dates, newest first. This is where progress becomes visible and morale lives.
  • Dropped — abandoned milestones WITH the reason (link the ADR). Silently deleting a milestone erases the learning.

Update triggers (the roadmap is updated, not rewritten)

  • A plan ships (Phase 5) → its milestone progresses or completes; Done log gets a line.
  • A phase completes mid-plan → status note on the milestone.
  • Scope changes / new milestone appears → add it to the right horizon; record an ADR if it displaces something.
  • Something is dropped or paused → move it, with reason.
  • Session start (orient skill) → READ it; the roadmap is context, not decoration.

Rules

  • Roadmap ≠ task list. Task lists churn hourly and live in tools; the roadmap changes on milestone boundaries. If an item would be done within a day, it belongs in a plan, not the roadmap.
  • Exit criteria over dates. For personal/agent-driven projects, sequence and doneness matter more than calendar promises. Add dates only when something external actually depends on them.
  • Keep it under a page. A roadmap nobody can hold in their head has stopped being a map.
  • The differential check (diff-management skill, project level): at every ship, compare roadmap-promised vs actually-delivered. Recurring gaps mean milestones are too big — split them.

Relationship to other artifacts

Roadmap (project, many sessions) → plans in docs/plans/ (one task each) → task list (one session's steps). Handovers point at the roadmap for "where are we"; ADRs record why the roadmap changed shape.

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.