메뉴
Extract generalizable lessons from project work and convert them into reusable skills.
Codex 또는 Claude로 설치 이 Prompt를 복사해 Codex, Claude 또는 다른 어시스턴트에 붙여 넣으면 Skill 페이지를 검토하고 설치를 진행할 수 있습니다.
SOC 직업 분류 기준
Plan, reason, and verify across multiple levels using multi-step reasoning, tree-of-thought, and structured agent workflows.
Detect and repair security vulnerabilities or operational errors in the agent's own code and environment without manual intervention.
Generate and apply complete design systems from text descriptions or visual examples using AI and modern tooling.
Adapt user interfaces automatically based on device, viewport, user preferences, and contextual signals.
Build and query knowledge graphs automatically to capture relationships between entities, concepts, and project artifacts.
Run agent tasks in isolated, sandboxed environments to prevent malicious or untrusted code from affecting the host system.
| name | knowledge-distillation |
| description | Extract generalizable lessons from project work and convert them into reusable skills. |
Category: Meta-Learning Priority: High
Extract generalizable lessons from project work and convert them into reusable skills.
Transform individual project experience into institutional knowledge.
Use this skill when:
memory_manager.py add with the task ID, summary, and key learnings. Example:
python .agents/scripts/memory_manager.py add \
--task-id "task-2026-07-04-001" \
--summary "Resolved SSR issue with React Three Fiber by forcing client-only rendering" \
--key-learning "Always wrap client-only 3D components in a client-only guard" \
--skill-updated react-three-fiber
Project: E-commerce checkout optimization
Lesson: N+1 queries are the #1 cause of slow list endpoints in Laravel.
Pattern: Always eager load relationships in list endpoints.
Action: Created skill "Database Query Optimization"
Linked to: Backend skill, Performance skill, Laravel template
Project done. Nothing special.
memory_manager.py if the lesson is reusable?