feat(scripts): 종료 코드를 손으로 적을 수 없게 만들고 스킬에 버전을 붙인다

capture-evidence.py 는 명령을 subprocess 로 직접 돌리고 그 프로세스의 반환값을
그대로 메타에 적는다. 종료 코드를 인자로 받지 않으므로 손으로 적을 경로가 없다.
raw 원문과 실행 메타가 같은 이름으로 함께 떨어져 「raw 는 있는데 meta 가 없다」가
구조적으로 안 생긴다.

skill-versions.py 는 스킬 9개의 metadata.version 과 검사기 17개의 내용 해시를
한 장으로 낸다. 통과 판정을 검증기 버전에 묶으려면 묶을 값이 있어야 한다.
버전 칸이 없던 스킬 여덟에 1.0.0 을 붙였다. 산문은 한 줄도 안 바꿨다.

Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01Q4vKjQo9KKBBokzxqXLCfk

.agents/skills/analyzing-codebase-for-tech-log/SKILL.md

@@ -1,6 +1,9 @@
 ---
 name: analyzing-codebase-for-tech-log
 description: Use when a project under <분석 대상 저장소> must be deeply analyzed and documented under docs, especially when the repository is too large for one pass and analysis must proceed by bounded module or subsystem.
+metadata:
+  version: "1.0.0"
+  language: "ko-KR"
 ---
 
 # Analyzing Codebase For Tech Log

.agents/skills/deriving-tech-log-root-tree/SKILL.md

@@ -1,6 +1,9 @@
 ---
 name: deriving-tech-log-root-tree
 description: Use when a completed or substantially completed docs project analysis must be decomposed into grounded Tech Log Topics and candidate Case, Concept, Reference, Open Question, and Decision records.
+metadata:
+  version: "1.0.0"
+  language: "ko-KR"
 ---
 
 # Deriving Tech Log Root Tree

.agents/skills/publishing-tech-log-to-studio/SKILL.md

@@ -1,6 +1,9 @@
 ---
 name: publishing-tech-log-to-studio
 description: Use when a finished Tech Log record .md must be put into Tech Log Studio through the browser with Playwright MCP — creating or opening the working copy, uploading assets, filling the per-kind fields, and saving. Save only; this skill never publishes.
+metadata:
+  version: "1.0.0"
+  language: "ko-KR"
 ---
 
 # Studio 반입 — 저장까지만

.agents/skills/refactoring-from-analysis/SKILL.md

@@ -1,6 +1,9 @@
 ---
 name: refactoring-from-analysis
 description: Use when a completed codebase analysis should be turned into one bounded, evidence-backed refactoring WorkItem and implemented in isolation.
+metadata:
+  version: "1.0.0"
+  language: "ko-KR"
 ---
 
 # Refactoring From Analysis

.agents/skills/rewriting-technical-prose-naturally/SKILL.md

@@ -1,6 +1,9 @@
 ---
 name: rewriting-technical-prose-naturally
 description: Use when an existing Korean technical document, section, or heading already contains grounded facts but sounds AI-written, slogan-like, overly polished, abstract, compressed, or mechanically contrasted and must be rewritten without changing its technical meaning.
+metadata:
+  version: "1.0.0"
+  language: "ko-KR"
 ---
 
 # Rewriting Technical Prose Naturally

.agents/skills/running-tech-log-pipeline/SKILL.md

@@ -1,6 +1,9 @@
 ---
 name: running-tech-log-pipeline
 description: Use when a codebase must go all the way to a saved Tech Log Studio draft — running the seven stages (SSOT, tree, record, diagram, prose, voice, Studio save) as separate subagents, one skill per stage, with a run ledger that records which skill each stage actually used and which gate it passed.
+metadata:
+  version: "1.0.0"
+  language: "ko-KR"
 ---
 
 # Tech Log 파이프라인 실행

.agents/skills/technical-visualizer/SKILL.md

@@ -1,6 +1,9 @@
 ---
 name: technical-visualizer
 description: Create source-grounded, diagram-only technical visuals from nearby documentation context. Select a logical composition grammar, compile VizSpec 1.1 into SVG and editable formats, and reject disconnected-card output.
+metadata:
+  version: "1.0.0"
+  language: "ko-KR"
 ---
 
 # Technical Visualizer

.agents/skills/writing-as-the-person-who-did-it/SKILL.md

@@ -1,6 +1,9 @@
 ---
 name: writing-as-the-person-who-did-it
 description: Use when a Korean technical document is accurate, well-ordered and well-evidenced but reads like a report produced by nobody — no one chose anything, nothing surprised anyone, and the limits are an inventory instead of an admission.
+metadata:
+  version: "1.0.0"
+  language: "ko-KR"
 ---
 
 # 일한 사람이 쓴 글로 만들기