Update to Matt Skills Curated

{
  "description": "Design and synthesize high-leverage autonomous goal prompts and contracts for unattended execution. Use when crafting a /goal prompt, planning an overnight autonomous coding run, converting rambling specifications into a self-contained agentic mission, or setting up multi-agent autonomous loops — even if they don't explicitly say \"goal prompt\". Do NOT use when the user asks for immediate single-turn execution in the current conversation without an autonomous goal contract.",
  "included_files": [
    {
      "relative_path": "agents/openai.yaml",
      "size_in_bytes": 123
    }
  ],
  "name": "goal",
  "skill_md_contents": "---\nname: goal\ndescription: \"Design and synthesize high-leverage autonomous goal prompts and contracts for unattended execution. Use when crafting a /goal prompt, planning an overnight autonomous coding run, converting rambling specifications into a self-contained agentic mission, or setting up multi-agent autonomous loops — even if they don't explicitly say \\\"goal prompt\\\". Do NOT use when the user asks for immediate single-turn execution in the current conversation without an autonomous goal contract.\"\n---\n\n# Autonomous Goal & Contract Synthesis\n\nTurn user intent, fuzzy requirements, or rambling specifications into an exceptional, self-contained `/goal` prompt ready for unattended, autonomous multi-turn execution.\n\n## Core Principle\n\n> **An autonomous goal prompt specifies the destination, quality bar, and verification loops — never micromanaged step-by-step scripts.**\n\n---\n\n## Core Invariants\n\n1. **Observable Done Condition**: Every deliverable must possess a concrete completion state the autonomous session can verify itself (e.g., test suite passes, CLI runs on fixtures, build outputs exist).\n2. **Upfront Authority & Creative Freedom**: Grant explicit permission to make design decisions, choose internal workflows, and resolve ambiguities without interrupting the user.\n3. **Verified Resource Inventory**: Name only 2–4 tools or paths that were verified against the live environment. Pair with an explicit discovery mandate.\n4. **Mandatory Multi-Pass Verification**: Mandate at least 3 distinct iteration passes matched to the target medium.\n5. **Terminal Goal Line**: End with a single recency-anchored sentence containing the deliverable and autonomy directive (`\"... is your /goal. Work completely autonomously and do not ask me for anything until you are all done.\"`).\n\n---\n\n## The Seven-Part Goal Prompt Anatomy\n\n```\n┌──────────────────────────────────────────────────────────┐\n│ 1. Core Desire & High-Stakes Context                     │\n│ 2. Uncompromising Quality Bar & Principles               │\n│ 3. Verified Resource Inventory & Discovery Mandate       │\n│ 4. Explicit Decision Authority & Creative Freedom        │\n│ 5. Medium-Matched Multi-Pass Verification Loop           │\n│ 6. Concrete Delivery Destination                         │\n│ 7. Terminal Goal Line & Autonomy Directive               │\n└──────────────────────────────────────────────────────────┘\n```\n\n---\n\n## Step-by-Step Procedure (TWI)\n\n### Step 1: Extract Intent & Fill Gaps\n- **Action**: Extract deliverable, scope, real stakes, mentioned tools, quality standards, and target destination.\n- **Key Point**: Synthesize sensible defaults for minor gaps. If an ambiguity is critical, resolve it upfront.\n- **Why**: Multi-round back-and-forth defeats the speed advantage of autonomous delegation.\n\n### Step 2: Verify Resources & Compose Anatomy\n- **Action**: Verify paths and tools before naming them, then weave the 7 components into natural flowing prose (150–350 words).\n- **Key Point**: State the outcome and constraints clearly while explicitly granting the agent freedom to navigate internal implementation steps.\n- **Inline Checklist**:\n  - [ ] Word count is within 150–350 words\n  - [ ] Named resources verified against live repository\n  - [ ] Creative freedom & decision authority explicitly granted\n  - [ ] Medium-specific verification passes defined (3 iterations)\n  - [ ] Destination explicit (link, directory path, file artifact)\n  - [ ] Concludes with terminal goal line and autonomy directive\n\n### Step 3: Mechanical Validation & Delivery\n- **Action**: Verify the drafted prompt against the seven invariants and output in a clean code block.\n- **Key Point**: Deliver the prompt ready to copy-paste with zero clutter.\n- **Why**: Clean delivery prevents formatting and syntax mistakes during execution.\n\n---\n\n## Anti-Rationalization Guardrails\n\n| Tempting Rationalization | Binding Rule | Engineering Rationale |\n|---|---|---|\n| *\"I listed step-by-step instructions so the agent won't get lost.\"* | **Specify destination, not micromanaged steps.** | Micromanagement prevents the agent from adapting to unforeseen obstacles. |\n| *\"I named several tools from memory without checking if they exist.\"* | **Verify all resources before naming.** | Unverified resources cause agents to burn turns searching for phantom paths. |\n| *\"The task is subjective, so verification passes aren't needed.\"* | **Every deliverable requires verification criteria.** | Unverified tasks lead to premature completion and unspotted defects. |\n| *\"I added notes and explanations after the goal line.\"* | **Terminal goal line must be the final sentence.** | Recency bias ensures the terminal directive anchors the model's primary objective. |\n"
}