{"skill":{"slug":"48h-expert","displayName":"48h-Expert-Methodology","summary":"A meta-learning method compressing deep expertise into 48 hours by extracting core mental models, expert debates, and critical assessment questions for mastery.","description":"# Skill: 48h-Expert-Protocol (Cognitive-Compressor V2.1)\n\n### 1. Core Assertion\nSystem **SHALL NOT** output unstructured prose. All cognitive extractions **MUST** be serialized according to the local `schema.json` to ensure cross-skill interoperability.\n\n### 2. Operational Phases\n\n#### Phase 0: High-Authority Source Retrieval\n* **Mandate:** Execute targeted retrieval of \"Foundational Textbooks,\" \"Peer-Reviewed Research,\" and \"Academic Syllabi.\"\n* **Filtering:** Prioritize `.edu`, `.gov`, and high-impact industry white papers.\n\n#### Phase 1: Primitive Logic Extraction\n* **Assertion:** Deconstruct the domain into **5 Core Mental Models**. \n* **Logic:** Each model **MUST** facilitate the derivation of 80% of secondary field logic.\n\n#### Phase 2: Dialectical Conflict Mapping\n* **Requirement:** Isolate **3 Fundamental Schisms** among top-tier experts. \n* **Format:** Present polarized arguments with zero-bias evidentiary grounding.\n\n#### Phase 3: Diagnostic Socratic Audit\n* **Action:** Generate **10 Deep-Level Probes** to detect knowledge illusions. \n\n#### Phase 4: Data Serialization & Handoff (Critical)\n* **Action:** Map all outputs from Phase 0-3 into the structured `schema.json` format.\n* **Integrity Check:** The resulting JSON **MUST** pass structural validation. \n* **Persistence:** Write the final JSON to `~/.openclaw/swarm_tmp/expert_output.json`.\n\n### 3. Hard Constraints\n* **C1 (Chaining):** Every output node **MUST** be referenceable by subsequent audit skills.\n* **C2 (Schema Compliance):** Any deviation from `schema.json` **SHALL** trigger a mandatory re-formatting cycle.\n* **C3 (Deterministic Output):** No conversational filler before or after the JSON payload.","tags":{"latest":"1.0.1","explore":"1.0.0","learn":"1.0.0","master":"1.0.0","study":"1.0.0"},"stats":{"comments":0,"downloads":614,"installsAllTime":23,"installsCurrent":3,"stars":0,"versions":2},"createdAt":1773646527425,"updatedAt":1778491943830},"latestVersion":{"version":"1.0.1","createdAt":1774004256765,"changelog":"- Introduced a strictly structured output format; all results must be serialized to the new `schema.json`.\n- Added a new phase: Data serialization and validation, with outputs written to `~/.openclaw/swarm_tmp/expert_output.json`.\n- Expanded source requirements to include government and industry white papers.\n- Enforced several hard constraints: referenceability, strict schema validation, and deterministic output with no extraneous text.\n- Replaced unstructured analysis with schema-driven, interoperable data for more robust downstream integration.","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}