{"skill":{"slug":"first-principles","displayName":"First-Principles-Deconstructor","summary":"Analyzes products by stripping marketing jargon to identify their fundamental physical laws, constraints, and optimal efficient designs from first principles.","description":"# Skill: First-Principles-Audit (Truth-Filter V2.1)\n\n### 1. Core Assertion\nSystem **SHALL** systematically strip all \"Marketing Jargon\" and \"Industry Inertia.\" The mission is to isolate **Atomic Truths**—physical, logical, and economic constraints—to verify the fundamental viability of any subject.\n\n### 2. Operational Phases\n\n#### Phase 0: Technical Ground-Truth Retrieval\n* **Mandate:** Locate patents, technical white papers, cost-structure breakdowns, and raw physical constants.\n* **Filtering:** Explicitly ignore PR announcements, celebrity endorsements, and \"Industry Standard\" claims.\n\n#### Phase 1: Inescapable Constraint Mapping\n* **Assertion:** Identify **3-5 Atomic Constraints** (e.g., Energy Density, Marginal Cost, Bandwidth Limits, Entropy).\n* **Classification:** Categorize every feature as either an \"Immutable Constant\" or \"Marketing Fluff.\"\n\n#### Phase 2: Efficiency-Logic Comparison\n* **Action:** Perform a \"From-Scratch\" reconstruction.\n* **Logic:** Do not compare feature lists. Compare the **Efficiency of Implementation Logic**. \n* **Metric:** If a solution deviates from the most efficient physical path, it **MUST** be flagged as a logical anomaly.\n\n#### Phase 3: Logical Anomaly Detection (The Verdict)\n* **Action:** Generate a \"Hard-Audit Verdict.\"\n* **Detection:** Explicitly point out where the current solution violates physics, economics, or basic common sense.\n\n#### Phase 4: Chaining & Cross-Verification (Critical)\n* **Action:** Consume data from `~/.openclaw/swarm_tmp/expert_output.json` if available.\n* **Serialization:** Map findings into the local `audit_schema.json`.\n* **Persistence:** Write the final report to `~/.openclaw/swarm_tmp/audit_report.json`.\n\n### 3. Hard Constraints\n* **C1 (Zero-Tolerance):** Use of marketing terms (e.g., \"Revolutionary,\" \"Leading-edge\") **SHALL** trigger a mandatory rewrite.\n* **C2 (Evidence-First):** Every audit claim **MUST** be backed by a physical or logical constant.\n* **C3 (Structured Output):** No conversational filler. Output **MUST** be a valid JSON payload following the Phase 4 mandate.","tags":{"latest":"1.0.1","compare":"1.0.0","feasibility":"1.0.0","research":"1.0.0"},"stats":{"comments":0,"downloads":869,"installsAllTime":0,"installsCurrent":0,"stars":0,"versions":2},"createdAt":1773646666632,"updatedAt":1778491943830},"latestVersion":{"version":"1.0.1","createdAt":1774004229584,"changelog":"- Introduced formal phase-driven methodology with stricter language and explicit mandates.\n- Added a new Phase 4: Chaining & Cross-Verification, requiring use of external expert output and serialization of audits into `audit_schema.json`.\n- Defined hard constraints enforcing zero marketing language, evidence-backed claims, and structured JSON output only.\n- Updated skill name from \"First-Principles-Deconstructor\" to \"First-Principles-Audit (Truth-Filter V2.1)\".\n- Added new file: `audit_schema.json` for report structure compliance.","license":"MIT-0"},"metadata":null,"owner":{"handle":"lawliet-ai","userId":"s172j47366kee2r44s4x7w5f5h83v6et","displayName":"Lawliet-ai","image":"https://avatars.githubusercontent.com/u/261297622?v=4"},"moderation":null}