refactor(topics): 멀티 에이전트용 지식 재편 — _Common(공통 기본기) + Domain_* 구조
에이전트 8종(대화형/프로그래머 C·S/디자이너/설계자/기획자/QA/PD/PM)에게 [공통 기본 능력 + 롤별 Specialty] 2층으로 지식을 주입하기 위한 재분류. 문서 내용·포맷은 무수정, 폴더 이동만 (6,372개 문서 수 보존 확인). - Topic_Programming → Domain_Programming (내부 구조 보존) - Topic_Graphic → Domain_Design - Topic_Business → Domain_Product - Topic_General → Domain_General - _Common 신설: Math(구 Topic_Math_Specialty), Reasoning(구 General/From_Thinking & Reasoning), Reasoning_Creativity(구 General/From_창의성), Communication(Poetic_Blog_Writing + From_writing) - 타 도메인의 From_* 폴더는 유지 (출처 표기일 뿐, 이미 도메인에 맞게 분류된 문서) - 빈 폴더 정리 (memory/procedures) - 에이전트→폴더 매핑은 workspace의 .astra/agent-knowledge-map.json (9개 에이전트) Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
This commit is contained in:
@@ -0,0 +1,189 @@
|
||||
---
|
||||
id: wiki-2026-0508-anxiety
|
||||
title: Anxiety
|
||||
category: 10_Wiki/Topics
|
||||
status: verified
|
||||
canonical_id: self
|
||||
aliases: [Anxiety Disorder, Worry]
|
||||
duplicate_of: none
|
||||
source_trust_level: A
|
||||
confidence_score: 0.9
|
||||
verification_status: applied
|
||||
tags: [psychology, mental-health, cognition]
|
||||
raw_sources: []
|
||||
last_reinforced: 2026-05-10
|
||||
github_commit: pending
|
||||
tech_stack:
|
||||
language: python
|
||||
framework: cbt-tools
|
||||
---
|
||||
|
||||
# Anxiety
|
||||
|
||||
## 매 한 줄
|
||||
> **"매 Anxiety는 future-oriented threat에 대한 anticipatory response이다 — fear의 specific object와 달리 diffuse하다"**. Evolutionary perspective에서는 vigilance system의 adaptive output이지만, modern context(2026)에서는 chronic activation이 GAD, panic disorder로 manifest. 매 핵심 distinction: fear = 현재 specific threat, anxiety = future uncertain threat.
|
||||
|
||||
## 매 핵심
|
||||
|
||||
### 매 Fear vs Anxiety
|
||||
- **Fear**: specific, present, immediate — amygdala-driven flight/fight.
|
||||
- **Anxiety**: diffuse, future, anticipatory — BNST(bed nucleus of stria terminalis) involvement.
|
||||
- 매 neural circuitry가 다름 — anxiolytic interventions도 다름.
|
||||
|
||||
### 매 Components
|
||||
- **Cognitive**: catastrophic thinking, worry, attention bias to threat.
|
||||
- **Somatic**: sympathetic activation — tachycardia, hyperventilation, GI distress.
|
||||
- **Behavioral**: avoidance, safety behaviors, reassurance seeking.
|
||||
- **Affective**: dread, apprehension, restlessness.
|
||||
|
||||
### 매 응용
|
||||
1. Clinical: CBT, exposure therapy, SSRIs/SNRIs, recently psilocybin-assisted (FDA 2025 approval).
|
||||
2. Performance: optimal arousal (Yerkes-Dodson) — 매 moderate anxiety가 performance를 enhance.
|
||||
3. Decision making: anxiety로 인한 risk-aversion bias 의 calibration.
|
||||
4. ML: anxiety-like behavior in RL agents (uncertainty aversion penalty).
|
||||
|
||||
## 💻 패턴
|
||||
|
||||
### CBT thought record (digital tool)
|
||||
```python
|
||||
from dataclasses import dataclass
|
||||
from datetime import datetime
|
||||
|
||||
@dataclass
|
||||
class ThoughtRecord:
|
||||
timestamp: datetime
|
||||
situation: str
|
||||
automatic_thought: str
|
||||
emotion: str
|
||||
intensity: int # 0-100
|
||||
cognitive_distortion: str # catastrophizing, mind-reading, etc
|
||||
balanced_thought: str
|
||||
new_intensity: int
|
||||
|
||||
def log_thought(situation, thought, emotion, intensity):
|
||||
return ThoughtRecord(
|
||||
timestamp=datetime.now(),
|
||||
situation=situation,
|
||||
automatic_thought=thought,
|
||||
emotion=emotion,
|
||||
intensity=intensity,
|
||||
cognitive_distortion="",
|
||||
balanced_thought="",
|
||||
new_intensity=0,
|
||||
)
|
||||
```
|
||||
|
||||
### Exposure hierarchy builder
|
||||
```python
|
||||
def build_hierarchy(items: list[tuple[str, int]]) -> list[dict]:
|
||||
"""items: (description, SUDS 0-100). Returns ordered hierarchy."""
|
||||
sorted_items = sorted(items, key=lambda x: x[1])
|
||||
return [
|
||||
{"step": i + 1, "task": desc, "suds": s, "status": "pending"}
|
||||
for i, (desc, s) in enumerate(sorted_items)
|
||||
]
|
||||
|
||||
hierarchy = build_hierarchy([
|
||||
("Look at photo of dog", 20),
|
||||
("Watch dog video", 35),
|
||||
("Be in room with leashed dog", 60),
|
||||
("Pet a calm dog", 80),
|
||||
("Approach unfamiliar dog", 95),
|
||||
])
|
||||
```
|
||||
|
||||
### Physiological monitoring (HRV-based)
|
||||
```python
|
||||
import numpy as np
|
||||
|
||||
def rmssd(rr_intervals_ms: np.ndarray) -> float:
|
||||
"""Root mean square of successive differences — HRV metric.
|
||||
낮은 RMSSD = 매 sympathetic dominance = anxiety state."""
|
||||
diffs = np.diff(rr_intervals_ms)
|
||||
return np.sqrt(np.mean(diffs ** 2))
|
||||
|
||||
def anxiety_proxy(rr: np.ndarray, baseline_rmssd: float) -> float:
|
||||
current = rmssd(rr)
|
||||
return max(0.0, (baseline_rmssd - current) / baseline_rmssd)
|
||||
```
|
||||
|
||||
### Box breathing pacer
|
||||
```python
|
||||
import time
|
||||
|
||||
def box_breathing(cycles: int = 8, beat: float = 4.0):
|
||||
"""4-4-4-4 pattern — vagal tone activation."""
|
||||
for _ in range(cycles):
|
||||
for phase in ["inhale", "hold", "exhale", "hold"]:
|
||||
print(f"{phase} {beat:.0f}s")
|
||||
time.sleep(beat)
|
||||
```
|
||||
|
||||
### GAD-7 scoring
|
||||
```python
|
||||
GAD7_ITEMS = [
|
||||
"Feeling nervous, anxious, on edge",
|
||||
"Not being able to stop or control worrying",
|
||||
"Worrying too much about different things",
|
||||
"Trouble relaxing",
|
||||
"Being so restless it's hard to sit still",
|
||||
"Becoming easily annoyed or irritable",
|
||||
"Feeling afraid as if something awful might happen",
|
||||
]
|
||||
|
||||
def gad7_score(answers: list[int]) -> tuple[int, str]:
|
||||
"""answers: 0-3 each. Returns (score, severity)."""
|
||||
s = sum(answers)
|
||||
sev = "minimal" if s < 5 else "mild" if s < 10 else "moderate" if s < 15 else "severe"
|
||||
return s, sev
|
||||
```
|
||||
|
||||
### LLM-based reframing assistant
|
||||
```python
|
||||
from anthropic import Anthropic
|
||||
|
||||
def reframe(thought: str) -> str:
|
||||
client = Anthropic()
|
||||
msg = client.messages.create(
|
||||
model="claude-opus-4-7",
|
||||
max_tokens=512,
|
||||
system=("You are a CBT-trained assistant. Identify cognitive distortion "
|
||||
"and offer a balanced reframe. Not a substitute for clinical care."),
|
||||
messages=[{"role": "user", "content": thought}],
|
||||
)
|
||||
return msg.content[0].text
|
||||
```
|
||||
|
||||
## 매 결정 기준
|
||||
| 상황 | Approach |
|
||||
|---|---|
|
||||
| Acute panic | Box breathing + grounding (5-4-3-2-1) |
|
||||
| Chronic worry | CBT thought records + worry postponement |
|
||||
| Specific phobia | Graded exposure |
|
||||
| GAD score ≥ 10 | Refer to clinician |
|
||||
| Performance anxiety | Reframe arousal as excitement |
|
||||
|
||||
**기본값**: psychoeducation + behavioral activation — 매 most evidence-based first-line for subclinical anxiety.
|
||||
|
||||
## 🔗 Graph
|
||||
- 응용: [[CBT]]
|
||||
|
||||
## 🤖 LLM 활용
|
||||
**언제**: psychoeducation, journaling prompts, cognitive reframing drafts, GAD-7 scoring assistant.
|
||||
**언제 X**: clinical diagnosis, suicide risk assessment (escalate to human), medication guidance, severe symptoms (Refer).
|
||||
|
||||
## ❌ 안티패턴
|
||||
- **Avoidance reinforcement**: 매 avoiding feared situation 의 short-term relief 의 long-term escalation.
|
||||
- **Reassurance seeking loop**: 매 repeated checking 의 anxiety maintenance.
|
||||
- **Substance self-medication**: alcohol/benzodiazepine dependence risk.
|
||||
- **Catastrophizing without check**: 매 worst-case probability inflation.
|
||||
|
||||
## 🧪 검증 / 중복
|
||||
- Verified (Beck 1979 *Cognitive Therapy*; Barlow 2002 *Anxiety and Its Disorders*; APA 2024 guidelines).
|
||||
- 신뢰도 A.
|
||||
|
||||
## 🕓 Changelog
|
||||
| 날짜 | 변경 |
|
||||
|---|---|
|
||||
| 2026-05-08 | Phase 1 |
|
||||
| 2026-05-10 | Manual cleanup — full content with CBT/exposure tools |
|
||||
Reference in New Issue
Block a user