agentleFS
Sign inStart free
salvo8519salvo8519/fairmark/.agents/skills/roadmap-update/SKILL.md

roadmap-update

Skill1 starsChanged 7 days agoApache-2.0View on GitHub

Propose and apply the roadmap change that a request implies — new task, new epic, a task moved to another milestone, a change of scope, or work dropped — through scripts/roadmap.py, after the maintainer confirms. Use whenever a request adds, changes or drops planned work, or when the maintainer asks to update the roadmap.

3 other projects use a version of this.

Adopted by

Most recently taken up by

The file

Create a free account to mount
Files
SKILL.md

Talk to the maintainer in their preferred language; everything written to the repository or to GitHub is in English, without icons. The roadmap is roadmap/roadmap.yaml; never edit milestones or issues on GitHub by hand.

  1. Classify the request. One of:
    • Already planned: an existing task covers it. Name it (uv run python scripts/roadmap.py list --open), and say whether its scope must change.
    • New task in an existing epic, or new epic when no epic fits.
    • Moved: a task changes milestone (priority).
    • Changed scope: the title or the spec of a task changes.
    • Dropped: planned work will not be done.
    • No impact: a question, or work inside the current issue's scope. Say so in one line and stop.
  2. Propose, in one short block, before doing the work: milestone, epic, title (the outcome, sentence case), labels (area:*, method:*, parallel, needs-methodology), spec (existing id, or "spec needed" for method work), dependencies on other tasks, and the reason for the milestone you chose. Methodology choices that are not settled get needs-methodology. Wait for confirmation, unless the maintainer has already stated the change explicitly.
  3. Apply what was confirmed:
    • new task: uv run python scripts/roadmap.py new --milestone M<n> --epic "<epic>" --title "<title>" --labels <labels> [--spec NNNN] [--body FILE];
    • moved or changed scope: edit the task in roadmap/roadmap.yaml, run uv run python scripts/roadmap.py render, then uv run python scripts/roadmap.py sync --apply-milestones (and update the issue title on GitHub if it changed);
    • dropped: close the issue as not planned with a comment that says why (gh api -X PATCH repos/{owner}/{repo}/issues/<n> -f state=closed -f state_reason=not_planned), then uv run python scripts/roadmap.py sync --write: the task stays in the file with status dropped, so the history remains visible.
  4. Record the change: in the current pull request when it belongs to its issue, otherwise in a chore(project) pull request. uv run python scripts/roadmap.py check must pass.
  5. Report to the maintainer: what changed in the plan, which issue, and what it means for the order of work.

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