cleaning-pm-tasks
Skill0 starsChanged 49 days agoNo licenceView on GitHub
Triages the pm task tracker for cleanup - scans every project (or one), gathers evidence per task (age, last session activity, whether the branch is merged, whether the PR is merged, the parent's status), and presents lettered categories with continuously numbered items - A = finished tasks to archive, B = provably closed in reality but still on an open status, C = junk to delete, D = probably dead with the reason for the doubt, E = tasks whose status lies (doing for a month with no activity) with the status to move them to, F = leave alone. The user picks whole letters or single numbers; only the picks are applied (archive/move via pm mv, delete only through the MCP delete tool). Use when the user says "/cleaning-pm-tasks", "posprzątaj taski", "wyczyść pm", "clean-up tasków", "co zarchiwizować", "śmieci w pm", "stare taski", "triage tasków", "zrób porządek na boardzie", or complains the board is full of stale tasks.
In this repository21 other files it gives its agents.
- batch-finish-autoSkill
- batch-finishSkill
- batch-prepSkill
- claim-checkSkill
- commit-splitSkill
- developing-featuresSkill
- epic-prepSkill
- executor-retroSkill
- figma-ppSkill
- humanizerSkill
- journal-reviewSkill
- parallel-guardSkill
- pass-toSkill
- pmSkill
- simulator-verifySkill
- solo-prepSkill
- solo-retroSkill
- soloSkill
- taking-overSkill
- timeline-bootstrapSkill
- web-verifySkill
The file
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
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.

