om-auto-manage-issues

Enriches existing tracker issues with SDLC labels, clarified wording, and implementation-prep analysis.

2.6k|159|Updated Mar 8, 2021
One-click install
npx skills add https://github.com/go-musicfox/go-musicfox --skill om-auto-manage-issues-go-musicfox
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: om-auto-manage-issues
Source: https://github.com/go-musicfox/go-musicfox/tree/main/.agents/skills/om-auto-manage-issues
Command: npx skills add https://github.com/go-musicfox/go-musicfox --skill om-auto-manage-issues-go-musicfox

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve? Backlogs accumulate thin, unlabeled issues — a title and a screenshot, no priority, no risk classification — that no one can triage or implement without re-investigating. This Skill brings existing tracker issues up to standard in bulk or one at a time, without touching repository source code. ## Core Features & Use Cases - SDLC label application: Infers and applies one missing category, priority, and risk label per issue per the repo's SDLC.md, with a rationale comment, never removing human-set labels. - Laconic issue enrichment: Analyzes attached screenshots plus terse text, rewrites the body with a clarified description while preserving the reporter's original verbatim, and posts an understanding comment for confirmation. - Implementation-prep analysis: Posts a read-only root-cause and impact analysis comment so the next agent or human can fix the issue without re-exploring the codebase. - Spec coverage check: Flags feature issues lacking a covering spec and optionally delegates spec authoring via --write-missing-specs. - Use Case: Run "triage the backlog" to process the last 25 open issues worst-described first — labeling, clarifying, and prepping each — or target a single issue with "clean up issue 123". ## Quick Start Ask the agent to triage the backlog by running om-auto-manage-issues with no arguments to enrich the last 25 open issues, or pass an issue number to manage just that one.

Frequently Asked Questions about om-auto-manage-issues

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I triage a backlog of GitHub issues automatically?

Run om-auto-manage-issues with no arguments to process the last 25 open issues, ordered worst-described first. It applies missing SDLC labels, clarifies thin bodies, and reports totals. Use --limit, --label, or --author to narrow the batch.

How do I clean up a single issue that only has a screenshot?

Pass the issue number, for example "clean up issue 123". The skill analyzes the screenshot, rewrites the body with a clarified description while preserving the original text verbatim in a collapsed section, and posts an understanding comment for confirmation.

Does this skill modify repository code or create new issues?

No. It mutates only labels, issue bodies, and comments on existing issues. The implementation-prep analysis and spec-coverage check are strictly read-only; the only exception is --write-missing-specs, which delegates opening a design-only spec PR.

What happens if I run the triage skill twice on the same issue?

Re-runs are no-ops. The skill only adds labels that are missing, detects its own understanding and implementation-notes comments by stable markers, and never duplicates a spec-required comment or spec-PR link.

Will it touch issues someone else is already working on?

No. It runs a three-signal claim check — assignee, in-progress label, and recent robot claim comment — and skips any issue another actor holds, plus issues carrying repo-defined human-hold labels like do-not-close.

How do I preview changes before mutating issues?

Use the --dry-run flag. It computes the planned labels, clarified wording, understanding text, implementation notes, and spec statuses for the report but posts and edits nothing.