agentleFS
Sign inStart free
omeirhaegheomeirhaeghe/staffgent/skills/backlog-scrub/SKILL.md

backlog-scrub

Skill1 starsChanged 5 months agoMITView on GitHub

Tidy and reconcile your backlog — dedupe, re-stage, set releases, and spot cross-PM conflicts.

The file

We split this skill into the rules it gives an agent

2 rules. About 0 are common, 0 are distinctive, and 2 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈0

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 2

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Call scrub_backlog first — it returns your open items, likely duplicate pairs, and other PMs' open items.

    line 8
  2. Very specific:

    Every prove/ship item should carry a target release (update_item release=R?).

    line 26

≈ “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

Backlog scrub

Call scrub_backlog first — it returns your open items, likely duplicate pairs, and other PMs' open items. Then work through these passes and apply changes with your ledger tools. Be decisive but conservative: when unsure whether to merge or close, flag it instead of destroying information.

1. Dedupe / merge

  • True duplicates or one item subsumed by another: keep the clearest one, close_item the rest with a note merged into tX.
  • Near-duplicates that are genuinely distinct: don't merge — rename for clarity with update_item so the difference is obvious.

2. Re-stage

  • Move each item to the stage that matches reality (backlog/define/prove/ship): actively scoping → define; validating with data/experiments → prove; building → ship.
  • Stale items nobody will pick up: close_item with a reason.

3. Release alignment

  • Every prove/ship item should carry a target release (update_item release=R?).
  • backlog/define items can stay unscheduled until they firm up.

4. Cross-PM conflicts & overlaps

Compare your items against the other PMs' items in the briefing. Flag (do NOT edit their items — surface to your manager):

  • Overlap / duplication across PMs (two people building the same thing) — name who you think should own it.
  • Dependency — your item needs theirs (or vice versa); note the direction.
  • Conflict — incompatible directions or contention for the same surface; escalate.

5. Report

Summarize tightly: what you merged/closed, what you re-staged, releases you set, and any cross-PM flags with the other PM named. Lead with anything that needs your manager's decision.

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