메뉴
Workflow for running background reasoning, reflective analysis, hidden planning layers, and iterative self-improvement systems to improve Claude’s execution quality across complex tasks.
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
| name | claude-subconscious-workflows |
| description | Workflow for running background reasoning, reflective analysis, hidden planning layers, and iterative self-improvement systems to improve Claude’s execution quality across complex tasks. |
This skill enables Claude to simulate a “subconscious” execution layer that continuously analyzes, reflects, plans, and improves workflows in the background while actively completing tasks.
The workflow focuses on:
The goal is to improve:
Instead of reacting only to immediate prompts, Claude should continuously maintain deeper contextual awareness and improve workflows proactively.
Before starting:
Recommended structure:
memory/
reflection/
optimization/
planning/
Recommended tools:
Optional:
Optional:
Use this skill when:
Do NOT use this skill for:
Build and maintain a large AI tooling repository over several months.
Claude should:
Final result should:
Claude should continuously analyze:
The system should:
Good reflection improves:
Execution and reflection should operate as separate layers.
Example:
The subconscious layer should monitor:
This separation improves:
Subconscious systems rely heavily on:
Claude should maintain:
Long-term context improves:
The system should continuously ask:
Claude should:
Iterative improvement compounds significantly over long projects.
Subconscious reasoning should proactively identify:
Early detection improves:
Start by defining:
Create structured summaries for:
Maintain:
Recommended files:
reflection/
workflow-observations.md
recurring-issues.md
optimization-log.md
The reflection layer should remain:
Continuously analyze:
Claude should identify:
The subconscious layer should suggest:
Prioritize:
Claude should continuously align work with:
Avoid:
Small improvements compound over time.
Claude should:
Avoid:
Regularly review:
Refine:
The system should evolve continuously through iterative refinement.
The final output should include:
The workflow itself should remain:
The agent should:
The workflow should optimize for:
Workflow for building scalable messaging systems on Microsoft Azure using queues, event-driven architecture, pub/sub systems, service buses, and cloud-native communication patterns.
Workflow for implementing observability systems on Microsoft Azure using logging, monitoring, tracing, telemetry, metrics, dashboards, and production-grade cloud diagnostics.
Workflow for creating procedural systems in Blender using Geometry Nodes, procedural materials, node-based modeling, and non-destructive generation techniques.
Workflow for creating precise hard surface models in Blender using clean topology, subdivision workflows, bevel systems, and production-ready modeling techniques.
Workflow for using Claude to generate Blender Python scripts, automate 3D workflows, and create procedural scenes, animations, and assets directly inside Blender.
End-to-end workflow for setting up Blender, rigging a character, and creating a simple animation with a clear output (rendered animation).