Update to Matt Skills Curated

{
  "description": "Route engineering, AI/ML, cognitive, or productivity tasks to the narrowest effective specialist skill. Use when a task spans planning, implementation, debugging, review, architecture, research, setup, AI modeling, data remediation, or autonomous goals, when the user asks what to do next, or when unsure which workflow fits — even if they don't explicitly name a skill. Do NOT use when the specific specialist skill is already obvious and unambiguous.",
  "included_files": [
    {
      "relative_path": "PHASE-BOUNDARIES.md",
      "size_in_bytes": 4249
    },
    {
      "relative_path": "agents/openai.yaml",
      "size_in_bytes": 109
    },
    {
      "relative_path": "references/catalog.md",
      "size_in_bytes": 9187
    },
    {
      "relative_path": "references/chatgpt-routing-contract.md",
      "size_in_bytes": 3489
    },
    {
      "relative_path": "references/routing-matrix.md",
      "size_in_bytes": 6165
    }
  ],
  "name": "engineering-workflow-guide",
  "skill_md_contents": "---\nname: engineering-workflow-guide\ndescription: \"Route engineering, AI/ML, cognitive, or productivity tasks to the narrowest effective specialist skill. Use when a task spans planning, implementation, debugging, review, architecture, research, setup, AI modeling, data remediation, or autonomous goals, when the user asks what to do next, or when unsure which workflow fits — even if they don't explicitly name a skill. Do NOT use when the specific specialist skill is already obvious and unambiguous.\"\n---\n\n# Engineering Workflow Guide\n\nCentrally analyze tasks, classify developer intent, and route engineering workflows to the narrowest, highest-leverage specialist skill across the curated skill catalog.\n\n---\n\n## Core Invariants\n\n1. **Narrowest Effective Skill**: Select the most specific skill that fully covers the task; avoid invoking broad, ceremonial meta-skills when a focused tool exists.\n2. **One Primary Skill per Phase**: Designate exactly one primary specialist skill for the current turn; chain secondary skills only across distinct lifecycle gates (e.g. Planning $\\rightarrow$ Implementation $\\rightarrow$ Review).\n3. **No Unpackaged Ghost Skills**: Every routed skill must exist verbatim in `references/catalog.md` and have an established `SKILL.md`.\n4. **Fast-Path User Overrides**: If the user explicitly requests a valid skill by name, honor it immediately without redundant routing deliberation.\n5. **Setup Pre-Requisite Check**: If repository issue tracking, triage labels, or domain docs are unconfigured, run `setup-engineering-workflows` prior to planning or triage.\n\n---\n\n## Architecture & Map of Content (MOC)\n\n```\n[ Developer Intent / Request ]\n                │\n                ▼\n┌────────────────────────────────────────────────────────┐\n│ 1. Intent Classification & Catalog Lookup               │\n│    (Match job against `references/catalog.md`)          │\n└──────────────────────────┬─────────────────────────────┘\n                           │\n    ┌──────────────────────┼──────────────────────┐\n    ▼                      ▼                      ▼\n[ Discovery & Plan ]   [ Code & Architecture ]   [ AI, ML & Automation ]\n- `grill-with-docs`    - `implement`             - `ai-engineering`\n- `to-spec`            - `code-review`           - `ai-data-remediation`\n- `to-tickets`         - `diagnosing-bugs`       - `ml-best-practices`\n- `wayfinder`          - `domain-modeling`       - `j-space`\n- `prototype`          - `setup-ts-deep-modules` - `goal`\n                           │\n                           ▼\n┌────────────────────────────────────────────────────────┐\n│ 2. Lifecycle Route Execution                           │\n│    (State route briefly, invoke primary skill)         │\n└────────────────────────────────────────────────────────┘\n```\n\n| Router Reference | Responsibility | File Location |\n|---|---|---|\n| **Skill Catalog** | Exhaustive index of all 42 packaged skills | [references/catalog.md](references/catalog.md) |\n| **ChatGPT Routing Contract** | Runtime consumption & anti-hallucination protocol | [references/chatgpt-routing-contract.md](references/chatgpt-routing-contract.md) |\n| **Routing Matrix** | 100+ intent patterns, triggers, and exclusions | [references/routing-matrix.md](references/routing-matrix.md) |\n| **Phase Boundaries** | Decision tree for `/clear`, `/compact`, `/handoff`, and subagents | [PHASE-BOUNDARIES.md](PHASE-BOUNDARIES.md) |\n\n| Lifecycle Scenario | Canonical Route Pipeline |\n|---|---|\n| **Fuzzy Greenfield Feature** | `grill-with-docs` $\\rightarrow$ `to-spec` $\\rightarrow$ `to-tickets` $\\rightarrow$ `implement` |\n| **Hard Bug or Regression** | `diagnosing-bugs` $\\rightarrow$ `tdd` |\n| **Pull Request Review** | `code-review` (Two-axis: Standards & Spec) |\n| **Deep Module Restructuring** | `improve-codebase-architecture` $\\rightarrow$ `setup-ts-deep-modules` |\n| **Large Multi-Session Map** | `wayfinder` $\\rightarrow$ `to-spec` $\\rightarrow$ `to-tickets` |\n| **Deep Multi-Step Reasoning** | `j-space` (Cognitive registers & seam audits) |\n| **Autonomous Unattended Goal** | `goal` (7-part prompt contract) |\n| **Production ML / LLM System** | `ai-engineering` $\\rightarrow$ `ml-best-practices` |\n| **Self-Healing Data Pipeline** | `ai-data-remediation` |\n| **Long-Form Writing & Essays** | `writing-fragments` $\\rightarrow$ `writing-shape` / `writing-beats` |\n\n---\n\n## Step-by-Step Procedure (TWI)\n\n### Step 1: Ingest Request and Consult Catalog\n- **Action**: Read `references/catalog.md` and classify the user's underlying intent, not just raw keywords.\n- **Key Point**: Check whether repository setup is complete (`docs/agents/issue-tracker.md`).\n- **Why**: Accurate intent classification ensures the agent doesn't jump into code when requirements are undefined.\n\n### Step 2: Formulate the Narrowest Route\n- **Action**: Select the single primary specialist skill and state the multi-phase roadmap in 1–2 lines.\n- **Inline Checklist**:\n  - [ ] Target skill verified in `references/catalog.md`\n  - [ ] Zero overlapping meta-skills invoked\n  - [ ] Distinct lifecycle phases separated cleanly\n\n### Step 3: Execute Primary Phase\n- **Action**: Invoke the selected skill instructions and proceed directly to execution.\n- **Why**: Direct transition eliminates conversational overhead.\n\n---\n\n## Anti-Rationalization Guardrails\n\n| Tempting Rationalization | Binding Rule | Engineering Rationale |\n|---|---|---|\n| *\"Invoke 4 skills at once for a single simple change.\"* | **Enforce 1 primary skill per lifecycle phase.** | Overlapping skill prompts create conflicting instructions and waste context budget. |\n| *\"Invent a new custom workflow name not in catalog.\"* | **Route exclusively to packaged skills in `catalog.md`.** | Routing to non-existent skills causes execution failures. |\n| *\"Overrule the user's explicit skill invocation.\"* | **Honor user-requested skill unless hard conflict exists.** | Respect developer intent and operational autonomy. |\n\n"
}