agentleFS
CharleneTStrainCharleneTStrain/product-ops-skills/skills/roadmap-hygiene/SKILL.md

roadmap-hygiene

Skill0 starsChanged 18 days agoMITView on GitHub

Review a product roadmap for stale, undated, ownerless, vague, or contradictory items and produce a short cleanup list, so the roadmap people see is one they can trust. Use when someone shares a roadmap export, planning sheet, Jira or Linear view, or Productboard list and asks for a roadmap review, cleanup, audit, or "is this still accurate?

The file

We split this skill into the rules it gives an agent

1 rule. About 0 are common, 1 is distinctive, and 0 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈1

    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:

    Use dates from the source and today's date.

    line 40

≈ “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 hygiene

A roadmap loses trust one stale item at a time. This check doesn't judge what should be on the roadmap; it judges whether what's on it is clear, current, and owned.

Before you start

If .agents/product-ops-context.md exists (or .claude/product-ops-context.md), read it first. Use the team, owners, tools, meetings, and metric definitions it already has, and only ask for what's missing or specific to this task. If it doesn't exist, go ahead with what you're given, and suggest running product-ops-context once so the next skill doesn't have to ask.

Step 1: Inventory

For each item, capture what the source shows:

ItemStatusOwnerTimeframeLast updatedLinked workCustomer-facing?

Record "None" or "Unknown" where a field is empty. Don't fill gaps.

Step 2: Check each item

Flag every item that has one or more of these problems:

ProblemWhat it looks like
StaleTimeframe has passed and status hasn't changed; or no update in a long time
No ownerOwner blank, or a team instead of a person
No timeframeNo date, quarter, or now / next / later placement
VagueTitle doesn't say what changes for customers ("Platform improvements," "Phase 2")
No linked workMarked in progress, but nothing in engineering is linked
ContradictionSays something different from another item, a release note, or a decision on record
ZombieIn "later" for many cycles with no movement; likely not happening
OverpromiseCustomer-facing roadmap shows a date the internal roadmap doesn't support

Use dates from the source and today's date. Show your evidence for "stale" and "contradiction."

Step 3: Recommend one action per flagged item

  • Update: status or date needs refreshing; name who to ask
  • Assign owner: name who should decide
  • Rewrite: suggest a clearer title in plain words
  • Merge: combine with a duplicate
  • Move to later / archive: for zombies; owner decides
  • Remove from customer-facing view: for overpromises

Recommend only. Never change, move, or delete roadmap items yourself.

Output

# Roadmap hygiene — [Roadmap name] — [Date]

**Summary:** [N] items reviewed · [N] flagged · Biggest issue: [one sentence]

## Fix before the next review
| Item | Problem | Evidence | Action | Ask |

## Lower priority
[Same table]

## Clean
- [N] items with no issues

Customer-facing issues (overpromises, contradictions with public release notes) always go to the top.

Related skills

  • quarterly-planning-prep — clean up before planning starts
  • duplicate-request-merging — tie requests to roadmap items
  • decision-log — record what was cut and why

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.