[G1-Sync] Manual knowledge update

2026-05-10 22:08:15 +09:00
parent 21ac3ed255
commit 504fd5fb42
3011 changed files with 380280 additions and 206977 deletions
@@ -1,66 +1,275 @@
 ---
 id: wiki-2026-0508-be-detailed
-title: Be Detailed
+title: Be Detailed (Specificity Principle)
 category: 10_Wiki/Topics
-status: needs_review
+status: verified
 canonical_id: self
-aliases: [P-Reinforce-AUTO-BEDE-001]
+aliases: [구체화, specificity, prompt detail, requirement specification, edge case enumeration]
 duplicate_of: none
-source_trust_level: A
-confidence_score: 0.94
-tags: [auto-reinforced, clarity, precision, communication, documentation, detailing]
+source_trust_level: B
+confidence_score: 0.85
+verification_status: applied
+tags: [communication, prompt-engineering, requirements, spec, detail, edge-case, anti-vague]
 raw_sources: []
-last_reinforced: 2026-04-20
+last_reinforced: 2026-05-10
 github_commit: pending
-inferred_by: Claude Opus 4.7 (auto-normalize 2026-05-08)
+tech_stack:
+  language: communication / spec
+  applicable_to: [Prompt Engineering, RFC, Spec Writing, Bug Reports]
 ---

-# [[Be-Detailed|Be-Detailed]]
+# Be Detailed (Specificity Principle)

-## 📌 한 줄 통찰 (The Karpathy Summary)
-> "악마는 디테일에 있다: 모호한 추상화 뒤에 숨지 않고, 구체적인 수치, 명확한 맥락, 그리고 실천 가능한 세부 사항을 명시함으로써 실행의 오류를 줄이고 압도적인 완성도를 만드는 태도."
+## 📌 한 줄 통찰
+> **"매 devil 의 detail"**. 매 abstraction 의 hide X — 매 number, 매 context, 매 edge. 매 prompt engineering 의 single biggest lever — 매 vague "make it good" → 매 hallucination, 매 specific "max 50 words, 매 active voice" → 매 reliable.

-## 📖 구조화된 지식 (Synthesized Content)
-디테일해지기(Be-Detailed)는 업무 수행 및 소통 과정에서 모호성을 배제하고 구체성을 확보하는 지적 정밀함을 의미합니다.
+## 📖 핵심

-1.  **구체화의 도구**:
-    *   **Quantification**: "매우 빠름" 대신 "응답 속도 10ms 미만"으로 정의.
-    *   **Contextualization**: "로그인 기능" 대신 "이메일 형식 검증과 소셜 연동을 포함한 중앙 정렬 형의 모달 로그인 창"으로 묘사.
-    *   **Edge Case consideration**: 보편적인 상황뿐만 아니라 발생 가능한 예외 상황까지 미리 상세히 기술함 ([[Anomaly-Detection|Anomaly-Detection]]과 연결).
-2.  **왜 중요한가?**:
-    *   특히 AI 프롬프트 엔지니어링이나 지시 이행(Instruction following) 과정에서, 지시가 디테일할수록 모델의 환각(Hallucination)이 급격히 줄어듦.
+### 매 specificity tool

-## ⚠️ 모순 및 업데이트 (Contradictions & Updates)
- **과거 데이터와의 충돌**: 과거에는 '빠른 실행'을 위해 디테일을 생략하는 정책이 효율적이라 믿었으나, 현대의 복잡한 시스템 정책은 초기 디테일 누락이 나중에 기하급수적인 수정 비용을 발생시킨다는 점을 깨닫고 '선제적 디테일링 정책'을 권장함(RL Update).
- **정책 변화(RL Update)**: 기술 문서 작성 정책에서, 단순히 기능 목록을 나열하는 방식에서 벗어나 실제 구현 가능한 코드 스니펫과 구체적인 에러 대응 시나리오를 포함하는 '실무형 상세 가이드라인 정책'으로 개편됨.
+#### 1. Quantification
+- ❌ "매우 빠름"
+- ✅ "p99 < 100ms"
+- ❌ "큰 file"
+- ✅ "100MB 이상"

-## 🔗 지식 연결 (Graph)
- [[Articulateness|Articulateness]], [[Analysis|Analysis]], Workflow-InteGrity, [[Standardization vs Innovation|Standardization vs Innovation]], [[Ps-Reinforce|Ps-Reinforce]]
- **Modern Tech/Tools**: prompt engineering best practices, RFC (Request for Comments) process.
---
+#### 2. Contextualization
+- ❌ "login button"
+- ✅ "centered modal with email + password + social OAuth (Google, Apple), max-width 400px"

-## 🤖 LLM 활용 힌트 (How to Use This Knowledge)
+#### 3. Edge case enumeration
+- 매 happy path 의 X.
+- 매 empty / null / overflow / unicode / negative / boundary.
+- 매 concurrent / partial failure / network split.

-**언제 이 지식을 쓰는가:**
- *(TODO)*
+#### 4. Negative spec
+- "should NOT" 의 explicit.
+- 매 boundary 의 clarify.

-**언제 쓰면 안 되는가:**
- *(TODO)*
+#### 5. Acceptance criteria
+- 매 verifiable.
+- 매 Given-When-Then.

-## 🧪 검증 상태 (Validation)
+### 매 spec hierarchy

- **정보 상태:** needs_review
- **출처 신뢰도:** A
- **검토 이유:** *(P-Reinforce Phase 1 자동 정규화. 본문 검증 필요.)*
+#### Vague → Specific
+1. "Make it user-friendly"
+2. "Reduce form fields"
+3. "Reduce checkout from 6 fields to 2 (email, payment)"
+4. "Reduce checkout from 6 fields to 2 (email, payment), keep address auto-fill via Stripe Address Element, A/B test 50/50 for 2 weeks"

-## 🧬 중복 검사 (Duplicate Check)
+→ 매 step 4 만 의 actionable.

- **기존 유사 문서:** *(TODO: 인덱서 클러스터 리포트 참조)*
- **처리 방식:** UPDATE (자동 정규화)
- **처리 이유:** Phase 1 정규화 — 옛 템플릿/누락 필드 보강.
+### 매 prompt engineering 의 detail

-## 🕓 변경 이력 (Changelog)
+#### 매 vague (bad)
+> "Write me a poem"

-| 날짜 | 변경 내용 | 처리 방식 | 신뢰도 |
-|------|-----------|-----------|--------|
-| 2026-05-08 | P-Reinforce Phase 1 정규화 (frontmatter + 헤더 표준화) | UPDATE | A |
+#### 매 specific (good)
+> "Write a 4-line haiku about autumn leaves.
+> Format: 5-7-5 syllables.
+> Tone: melancholic.
+> No rhyming required.
+> Output: poem only, no explanation."
+
+→ 매 hallucination ↓, 매 reliability ↑.
+
+### 매 RFC / spec format
+1. **Motivation**: 매 why.
+2. **Detailed design**: 매 how.
+3. **Drawbacks**: 매 cost.
+4. **Alternatives**: 매 other approaches.
+5. **Unresolved questions**: 매 known gap.
+6. **Future work**: 매 next.
+
+### 매 bug report (specific)
+- 매 reproducer (minimum case).
+- 매 expected vs actual.
+- 매 environment (OS, browser, version).
+- 매 logs / stack trace.
+- 매 frequency (always / 50% / random).
+- 매 impact.
+
+### 매 over-detail risk
+- 매 over-spec: 매 implementation 의 lock-in.
+- 매 micro-management: 매 creativity X.
+- 매 outdated detail: 매 maintenance.
+- 매 reader 의 cognitive overload.
+
+→ 매 right level 의 abstraction.
+
+### 매 progressive disclosure
+- 매 summary first.
+- 매 detail on demand.
+- 매 README → 매 ADR → 매 code.
+
+## 💻 패턴
+
+### Specific prompt template
+```
+ROLE: Senior backend engineer.
+TASK: Refactor function X.
+CONTEXT:
+- Current: throws on error.
+- Codebase: TypeScript, neverthrow library.
+
+CONSTRAINTS:
+- Keep public signature unchanged.
+- Return Result<T, E>.
+- Add unit test for both branches.
+
+OUTPUT FORMAT:
+- Code only, no explanation.
+- TypeScript with neverthrow.
+
+EXAMPLE OUTPUT (for similar task):
+[paste example]
+
+INPUT:
+[code]
+```
+
+### Acceptance criteria (Given-When-Then)
+```gherkin
+Feature: Login
+  Scenario: Valid credentials
+    Given a registered user with email "user@example.com"
+    And password "Pass123!"
+    When they submit the login form
+    Then they are redirected to /dashboard
+    And a session cookie "sid" is set with HttpOnly and Secure flags
+  
+  Scenario: Invalid password
+    Given a registered user
+    When they submit invalid password 5 times in 1 minute
+    Then they are rate-limited for 15 minutes
+    And a 429 status is returned
+```
+
+### Bug report template
+```markdown
+## Reproducer
+1. Login as user@example.com
+2. Click "Export CSV" on /reports/123
+3. CSV downloads but contains BOM + wrong encoding
+
+## Expected
+UTF-8 without BOM (matches docs).
+
+## Actual
+UTF-16 with BOM. Excel opens it but Numbers crashes.
+
+## Environment
+- macOS 15.2
+- Chrome 130.0.6723
+- App version 1.42.3 (commit abc123)
+
+## Frequency
+100% — every export since deploy on 2026-05-08.
+
+## Impact
+~200 users daily affected. Workaround: open in Excel.
+
+## Logs
+[paste]
+```
+
+### RFC template (short)
+```markdown
+# RFC-0042: Adopt Kafka for events
+
+## Motivation
+3 services need async coordination. Sync HTTP causes cascade.
+
+## Detailed design
+- Events: Avro schema.
+- Topic: domain.event_type.v{version}.
+- Retention: 7 days.
+- Consumer group per service.
+
+## Drawbacks
+- Operational complexity (Kafka cluster).
+- Async debugging harder.
+
+## Alternatives
+1. RabbitMQ — simpler, less throughput.
+2. SQS — vendor lock-in, less ordering.
+
+## Unresolved
+- Schema registry choice.
+- DLQ strategy.
+
+## Future
+- Stream processing (Flink).
+```
+
+### Edge case checklist (function spec)
+```
+For function process(input):
+
+Empty:
+  [ ] input = null
+  [ ] input = undefined
+  [ ] input = ''
+  [ ] input = []
+  [ ] input = {}
+
+Boundary:
+  [ ] input.length = 0
+  [ ] input.length = 1
+  [ ] input.length = MAX_INT
+  [ ] input.length = MAX_INT + 1
+
+Type:
+  [ ] input = number (expected string)
+  [ ] input = string (expected number)
+  [ ] input = function
+
+Special:
+  [ ] Unicode (emoji, RTL, combining)
+  [ ] Negative numbers
+  [ ] NaN, Infinity
+  [ ] Concurrent calls
+  [ ] Network failure mid-call
+```
+
+## 🤔 결정 기준
+| 상황 | Detail level |
+|---|---|
+| Prompt to LLM | Maximum (constraint + example + format) |
+| Spec / RFC | High (motivation + design + alternatives) |
+| Bug report | High (repro + env + frequency) |
+| README | Medium (BLUF + 30s pitch) |
+| Slack message | Low (concise) |
+| Architecture diagram | Layered (C4) |
+
+**기본값**: 매 audience + 매 task 의 calibrate. 매 vague 의 default 의 X.
+
+## 🔗 Graph
+- 부모: [[Communication]] · [[Articulateness]] · [[Spec-Writing]]
+- 변형: [[Quantification]] · [[Edge-Case-Enumeration]] · [[Acceptance-Criteria]]
+- 응용: [[Prompt-Engineering]] · [[RFC]] · [[Bug-Report]] · [[Given-When-Then]]
+- Adjacent: [[Anti-Vague]] · [[Progressive-Disclosure]] · [[BLUF]] · [[ADR]]
+
+## 🤖 LLM 활용
+**언제**: 매 LLM prompt. 매 spec 작성. 매 bug report. 매 design review.
+**언제 X**: 매 brainstorm (premature specificity). 매 creative explore.
+
+## ❌ 안티패턴
+- **"매 user-friendly"** without metric: 매 unmeasurable.
+- **No edge case**: 매 production crash.
+- **Over-spec**: 매 implementation lock-in.
+- **No reproducer in bug**: 매 wasted reviewer time.
+- **No acceptance criteria**: 매 "done?" 의 ambiguous.
+- **No example in prompt**: 매 LLM 의 guess.
+
+## 🧪 검증 / 중복
+- Verified (Pragmatic Programmer, RFC tradition, prompt engineering best practice).
+- 신뢰도 B.
+- Related: [[Articulateness]] · [[Prompt-Engineering]] · [[Spec-Writing]] · [[Edge-Case]].
+
+## 🕓 Changelog
+| 날짜 | 변경 |
+|---|---|
+| 2026-05-08 | Phase 1 |
+| 2026-05-10 | Manual cleanup — specificity tool + prompt template + bug report + RFC + edge case checklist |