← ClaudeAtlas

groom-backloglisted

Groom a project backlog in an issue tracker. Loads the whole board in bulk, computes a gap inventory instead of eyeballing one, verifies each candidate issue's factual claims against the code and the tracker, ranks the verified candidates by a stated four-tier heuristic, proposes an evidence-backed closure for an issue whose premise evaporated, clusters open issues by outcome, places each cluster under a grouping construct whose description states a verifiable property of the system, finds the dependencies between tickets — the ones the tracker already records and the ones only the prose admits — and proposes each missing link, and fixes triage, priority, label, and state hygiene. The read-and-plan phase writes a plan file, presents the consequential choices with one recommendation each, and waits for the user's approval — nothing on the tracker changes before the user answers. Trigger on "groom the backlog", "groom the board", "clean up the backlog", "shape the backlog", "place these issues under milestones"
bostonaholic/team · ★ 11 · AI & Automation · score 75
Install: claude install-skill bostonaholic/team
# groom-backlog — plan, ask, wait, then execute > Follow `skills/principle-progress-tracking/SKILL.md`: this procedure has more than two steps — > seed one todo item per step below before starting and mark each complete as you go. Grooming mutates shared state that a whole team reads. Placement, dates, and ticket rewrites are judgment calls with no mechanical ground truth. A wrong one stays invisible until someone acts on a board that now lies. So this skill plans, asks the consequential questions, and waits. It acts only on approval. That is the shape `pr-open-comments` takes for an item below its auto-apply bar. That checkpoint is the ethos applied, not a hole in it. The pipeline's autonomous middle earns its autonomy from mechanical gates. A grooming judgment has none, so the user's answer stays this skill's one gate until a loop-driven controller replaces it. The shape is `skills/principle-plan-present-wait/SKILL.md`: plan the mutations to a file, present each consequential choice with one recommendation, and execute only the answered subset. ## Vocabulary The method is tracker-agnostic. Only the nouns change, and GitHub Projects v2 is the worked example throughout. | Concept in the method | GitHub Projects v2 | Linear | Jira | | --- | --- | --- | --- | | Grouping construct | milestone | project milestone | epic / fix version | | Column / state | Status field | workflow state | status | | Priority | Priority field | priority 0–4 | Priority field | | Iteration | iter