Update to Matt Skills Curated

{
  "description": "Configure repository issue-tracking, triage-label, domain-doc, and agent-instruction conventions. Use when initializing engineering workflows in a repo, configuring GitHub/GitLab issue labels, or establishing CONTEXT.md conventions — even if the user says \"setup our workflows\". Do NOT use for general project package installs.",
  "included_files": [
    {
      "relative_path": "agents/openai.yaml",
      "size_in_bytes": 116
    },
    {
      "relative_path": "domain.md",
      "size_in_bytes": 2033
    },
    {
      "relative_path": "issue-tracker-github.md",
      "size_in_bytes": 3731
    },
    {
      "relative_path": "issue-tracker-gitlab.md",
      "size_in_bytes": 3809
    },
    {
      "relative_path": "issue-tracker-local.md",
      "size_in_bytes": 1810
    },
    {
      "relative_path": "triage-labels.md",
      "size_in_bytes": 1045
    }
  ],
  "name": "setup-engineering-workflows",
  "skill_md_contents": "---\nname: setup-engineering-workflows\ndescription: \"Configure repository issue-tracking, triage-label, domain-doc, and agent-instruction conventions. Use when initializing engineering workflows in a repo, configuring GitHub/GitLab issue labels, or establishing CONTEXT.md conventions — even if the user says \\\"setup our workflows\\\". Do NOT use for general project package installs.\"\n---\n\n# Setup Engineering Workflows\n\nConfigure and standardize repository issue-tracking, triage-label vocabularies, domain-modeling architecture (`docs/agents/domain.md`), and agent instructions (`AGENTS.md` / `CLAUDE.md`).\n\n---\n\n## Core Invariants\n\n1. **Prompt-Driven Exploration**: Inspect existing remotes, directories, and labels before proposing changes; do not blindly overwrite existing tracker setups.\n2. **Single vs Multi-Context Prudence**: Default to single-context (`CONTEXT.md` at root); only suggest multi-context (`CONTEXT-MAP.md`) when monorepo signals (workspaces, `packages/*`) are detected.\n3. **Preserve Agent Instruction File**: If `CLAUDE.md` or `AGENTS.md` exists, edit it in-place; if neither exists, ask the user before creating one. Never create both.\n4. **Conditional Triage Configuration**: Only configure triage label files (`docs/agents/triage-labels.md`) if the `triage` skill is present in the repository.\n5. **Durable Workspace Documentation**: Persist all configured decisions into `docs/agents/issue-tracker.md`, `docs/agents/domain.md`, and `docs/agents/triage-labels.md`.\n\n---\n\n## Architecture & Map of Content (MOC)\n\n```\n[ Codebase Inspection (Remotes, Monorepos) ] ──► [ Interactive Setup Sections A/B/C ] ──► [ Update AGENTS.md / docs/agents/ ]\n```\n\n| Component | Responsibility | Seed Template |\n|---|---|---|\n| **Issue Tracker Config** | GitHub (`gh`), GitLab (`glab`), or Local Markdown | `skills/setup-engineering-workflows/issue-tracker-github.md` |\n| **Triage Vocabulary** | 5 canonical roles mapping to repo labels | `skills/setup-engineering-workflows/triage-labels.md` |\n| **Domain Docs Layout** | Single-context vs multi-context conventions | `skills/setup-engineering-workflows/domain.md` |\n\n---\n\n## Step-by-Step Procedure (TWI)\n\n### Step 1: Autonomous Repository Exploration\n- **Action**: Check `git remote -v`, root instruction files (`AGENTS.md`, `CLAUDE.md`), `docs/adr/`, and workspace configurations (`pnpm-workspace.yaml`, `packages/`).\n- **Key Point**: Identify whether the repository already has a tracker or triage convention.\n- **Why**: Avoids re-asking the user for facts already evident in git and configuration files.\n\n### Step 2: Configure Issue Tracker & Triage Labels\n- **Action**: Present recommendations section-by-section:\n  - **Section A (Tracker)**: GitHub (`gh`), GitLab (`glab`), or Local Markdown (`.scratch/`).\n  - **Section B (Labels)**: Canonical roles (`needs-triage`, `needs-info`, `ready-for-agent`, `ready-for-human`, `wontfix`).\n  - **Section C (Domain)**: Single-context vs. Multi-context.\n- **Inline Checklist**:\n  - [ ] Tracker confirmed and documented in `docs/agents/issue-tracker.md`\n  - [ ] Triage labels mapped in `docs/agents/triage-labels.md`\n  - [ ] Domain doc rules written to `docs/agents/domain.md`\n\n### Step 3: Wire Instructions into AGENTS.md / CLAUDE.md\n- **Action**: Add or update the `## Agent skills` block inside `AGENTS.md` (or `CLAUDE.md`):\n  ```markdown\n  ## Agent skills\n  \n  ### Issue tracker\n  [Summary of issue tracking]. See `docs/agents/issue-tracker.md`.\n  \n  ### Domain docs\n  [Single or multi-context]. See `docs/agents/domain.md`.\n  ```\n- **Why**: Context pointers ensure newly spawned subagents read repository conventions immediately.\n\n---\n\n## Anti-Rationalization Guardrails\n\n| Tempting Rationalization | Binding Rule | Engineering Rationale |\n|---|---|---|\n| *\"Create both AGENTS.md and CLAUDE.md for maximum coverage.\"* | **Forbidden. Maintain exactly one canonical agent file.** | Multiple instruction files lead to configuration drift and conflicting rules. |\n| *\"Force multi-context on single-package repositories.\"* | **Default to single-context unless monorepo exists.** | Unnecessary multi-context structures create excessive directory nesting. |\n| *\"Overwrite existing custom issue labels without asking.\"* | **Map existing repo labels to canonical roles.** | Overwriting existing team labels breaks active project boards and workflows. |\n\n"
}