What problem does it solve? Engineering skills like to-issues, triage, and diagnose need to know where your repo tracks issues, which triage label strings you use, and where your domain documentation lives. Without that per-repo configuration, they guess wrong or create duplicate labels and files. ## Core Features & Use Cases - Guided repo exploration: Inspects git remotes, existing AGENTS.md/CLAUDE.md, CONTEXT.md, ADR directories, and .scratch/ to understand the repo's starting state before writing anything. - Three-decision setup: Walks the user through choosing an issue tracker (GitHub via gh, GitLab via glab, local markdown under .scratch/, or a custom workflow), mapping the five canonical triage label roles, and confirming single-context vs multi-context domain docs. - Scaffolded output: Writes an ## Agent skills block into the existing CLAUDE.md or AGENTS.md plus docs/agents/issue-tracker.md, docs/agents/triage-labels.md, and docs/agents/domain.md from seed templates. - Use Case: After cloning a repo that uses GitLab issues and custom label names, run this skill once so triage applies your real labels and to-issues publishes via glab instead of gh. ## Quick Start Ask the agent to run the setup-matt-pocock-skills skill to configure the issue tracker, triage labels, and domain docs for this repository.
