@simplysm/sd-claude 13.0.67 → 13.0.68

package/README.md

@@ -1,6 +1,6 @@
 # @simplysm/sd-claude
 
-Simplysm Claude Code CLI — asset installer and cross-platform npx wrapper. Automatically installs Claude Code assets (skills, agents, rules, refs, hooks) via `postinstall` when added as a dev dependency. Provides opinionated development workflows including TDD, systematic debugging, code review, planning, brainstorming, and git worktree management.
+Simplysm Claude Code CLI — asset installer. Automatically installs Claude Code assets (skills, agents, rules, refs, hooks) via `postinstall` when added as a dev dependency. Provides opinionated development workflows including TDD, systematic debugging, code review, planning, brainstorming, and git worktree management.
 
 ## Installation
 
@@ -18,8 +18,7 @@ When installed as a dependency, the `postinstall` script (`scripts/postinstall.m
 
 1. Copies all `sd-*` assets (skills, agents, rules, refs, hooks, statusline) to the project's `.claude/` directory
 2. Configures `statusLine` in `.claude/settings.json` to use `sd-statusline.js`
-3. Configures MCP servers in `.mcp.json` (context7 and playwright) using the cross-platform npx wrapper
-4. Existing `sd-*` entries are replaced with the latest version on each install
+3. Existing `sd-*` entries are replaced with the latest version on each install
 
 The `prepack` script (`scripts/sync-claude-assets.mjs`) runs before `npm pack` / `npm publish` to sync assets from the project root `.claude/` directory into the package's `claude/` directory.
 
@@ -33,7 +32,6 @@ Updates also trigger reinstallation (`pnpm up @simplysm/sd-claude`).
     sd-claude.js               # CLI entry point (bin)
     commands/
       install.js               # Asset installation logic
-      npx.js                   # Cross-platform npx wrapper
   scripts/
     postinstall.mjs            # Thin wrapper — calls `sd-claude install`
     sync-claude-assets.mjs     # Syncs assets from .claude/ before publish
@@ -78,22 +76,19 @@ Updates also trigger reinstallation (`pnpm up @simplysm/sd-claude`).
 
 ## CLI Commands
 
-The package provides an `sd-claude` binary with two subcommands:
+The package provides an `sd-claude` binary:
 
 ```bash
 # Install Claude Code assets to the project's .claude/ directory
 sd-claude install
-
-# Cross-platform npx wrapper (uses npx.cmd on Windows, npx elsewhere)
-sd-claude npx -y @upstash/context7-mcp
 ```
 
-`sd-claude install` is called automatically by the `postinstall` script. `sd-claude npx` is used in `.mcp.json` to launch MCP servers cross-platform.
+`sd-claude install` is called automatically by the `postinstall` script.
 
 ## Programmatic API
 
 ```typescript
-import { runInstall, runNpx } from "@simplysm/sd-claude";
+import { runInstall } from "@simplysm/sd-claude";
 ```
 
 ### runInstall
@@ -107,15 +102,6 @@ Installs Claude Code assets to the project's `.claude/` directory. Performs:
 - Skips if running inside the simplysm monorepo itself
 - Cleans existing `sd-*` entries, then copies fresh versions from the package's `claude/` directory
 - Configures `statusLine` in `.claude/settings.json`
-- Configures MCP servers (context7, playwright) in `.mcp.json`
-
-### runNpx
-
-```typescript
-function runNpx(args: string[]): void
-```
-
-Cross-platform npx wrapper. Spawns `npx.cmd` on Windows, `npx` on other platforms. Passes all arguments through and forwards the exit code.
 
 ## Skills
 

package/claude/refs/sd-code-conventions.md

@@ -38,3 +38,9 @@ async function readFileAsync() { ... } // Async suffix prohibited
 
 - Not enforced — omit when code is self-explanatory
 - When written, use Korean
+
+## index.ts Export Pattern
+
+- Large packages: `#region`/`#endregion` for sections + `//` for sub-groups
+- Small packages (≤10 exports): `//` comments only
+- Always `export *` (wildcard), never explicit `export type { ... } from "..."`

package/claude/refs/sd-migration.md

@@ -0,0 +1,7 @@
+# Migration Rules
+
+When porting/migrating code from another codebase (e.g., v12 Angular → v13 SolidJS):
+
+1. **Analyze every line**: Read the original source and all its dependencies (imports, base classes, etc.) line by line. Understand every feature, prop, and behavior. If a dependency cannot be found, ask the user.
+2. **Ask about every difference**: Any change from the original (API, pattern, design, omission, addition) must be asked to the user. Never decide silently.
+3. **Verify after completion**: Compare the result 1:1 with the original and report any omissions or differences to the user.

package/claude/rules/sd-claude-rules.md

@@ -33,24 +33,6 @@ If a referenced file or document cannot be found, **stop immediately and ask the
 - When in doubt, **ask first** before proceeding.
 - Responses like "I'll create it myself" or "I'll add that as well" are strictly prohibited.
 
-## Bug Workarounds
+## ⚠️ CRITICAL — NEVER SKIP
 
-### AskUserQuestion UI Clipping — CRITICAL
-
-The `AskUserQuestion` widget overlaps and hides the text above it in the UI.
-
-**Mitigation:** Before every `AskUserQuestion` call, output **5 blank lines** at the end of your text so the important content is pushed above the clipping zone.
-
-```
-(your text here)⏎
-⏎
-⏎
-⏎
-⏎
-⏎
-→ AskUserQuestion tool call
-```
-
-- This applies to EVERY `AskUserQuestion` call, no exceptions.
-- The blank lines MUST be in the same message, immediately before the tool call.
-- If you forget the blank lines, the user will not be able to read your preceding text.
+**Before EVERY `AskUserQuestion` call, output `---` as the last line.** The widget clips text above it. No exceptions.

package/claude/rules/sd-refs-linker.md

@@ -18,6 +18,7 @@ Before starting work, **Read** the relevant reference files from `.claude/refs/`
 | Using `@simplysm/*` package APIs                 | `.claude/refs/sd-simplysm-docs.md`    |
 | Debugging, problem-solving, or planning approach | `.claude/refs/sd-workflow.md`         |
 | @simplysm/service-\* 사용 시                     | `.claude/refs/sd-service.md`          |
+| Migrating/porting code from another codebase     | `.claude/refs/sd-migration.md`        |
 
 ## v12 only (< 13)
 

package/claude/skills/sd-api-name-review/SKILL.md

@@ -1,6 +1,7 @@
 ---
 name: sd-api-name-review
-description: Use when reviewing a library or module's public API naming for consistency and industry standard alignment - function names, parameter names, option keys, enum values, type names
+description: Public API naming consistency and industry standard alignment review
+disable-model-invocation: true
 model: sonnet
 ---
 

package/claude/skills/sd-brainstorm/SKILL.md

@@ -1,6 +1,7 @@
 ---
 name: sd-brainstorm
-description: "You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation."
+description: Collaborative design exploration through Q&A before implementation
+disable-model-invocation: true
 model: opus
 ---
 

package/claude/skills/sd-check/SKILL.md

@@ -1,6 +1,7 @@
 ---
 name: sd-check
-description: Use when verifying code quality via typecheck, lint, and tests - before deployment, PR creation, after code changes, or when type errors, lint violations, or test failures are suspected. Applies to whole project or specific paths.
+description: Code quality verification via typecheck, lint, and tests
+disable-model-invocation: true
 allowed-tools: Bash(npm run check), Bash(npm run typecheck), Bash(npm run lint --fix), Bash(npm run vitest)
 ---
 

package/claude/skills/sd-commit/SKILL.md

@@ -1,6 +1,7 @@
 ---
 name: sd-commit
-description: Use when creating git commits — for staging and committing changed files with conventional commit messages, either for context-relevant files only (default) or all uncommitted changes at once (all mode).
+description: Git commit with conventional commit messages
+disable-model-invocation: true
 argument-hint: "[all]"
 allowed-tools: Bash(git status:*), Bash(git add:*), Bash(git commit:*)
 model: haiku

package/claude/skills/sd-debug/SKILL.md

@@ -1,6 +1,7 @@
 ---
 name: sd-debug
-description: Use when encountering any bug, test failure, or unexpected behavior. Enforces root-cause investigation before proposing fixes.
+description: Systematic root-cause debugging methodology
+disable-model-invocation: true
 ---
 
 # Systematic Debugging

package/claude/skills/sd-discuss/SKILL.md

@@ -1,6 +1,7 @@
 ---
 name: sd-discuss
-description: "Use when evaluating code design decisions against industry standards and project conventions - class vs functional, pattern choices, architecture trade-offs, technology selection"
+description: Evidence-based technical discussion with industry research
+disable-model-invocation: true
 model: opus
 ---
 

package/claude/skills/sd-email-analyze/SKILL.md

@@ -0,0 +1,52 @@
+---
+name: sd-email-analyze
+description: Email file (.eml/.msg) parsing and attachment extraction
+disable-model-invocation: true
+---
+
+# Email Analyzer
+
+## Overview
+
+Python script that parses `.eml` and `.msg` (Outlook) email files. Extracts mail headers, body text, inline images, and attachments to disk. Content analysis of extracted files is delegated to Claude's Read tool and document-skills plugin.
+
+## When to Use
+
+- User provides a `.eml` or `.msg` file to analyze or summarize
+- Korean email content needs proper decoding
+
+## Usage
+
+```bash
+python .claude/skills/sd-email-analyze/email-analyzer.py <email_file_path>
+```
+
+First run auto-installs: `extract-msg`.
+
+### After Running
+
+1. Read the markdown output (mail info, body text, file paths)
+2. **Inline images**: Use **Read** tool on each saved path to view
+3. **Attachments**: Use **Read** tool (PDF, images) or let **document-skills** plugin handle (XLSX, PPTX, DOCX)
+
+## Output
+
+- `<email_stem>_files/` directory with all extracted files
+- Markdown report to stdout:
+  1. **Mail info table**: Subject, From, To, Cc, Date, counts
+  2. **Body text**: Plain text (HTML stripped if no plain text)
+  3. **Inline images**: Table with saved file paths
+  4. **Attachments**: Table with saved file paths
+
+## Inline Image Handling
+
+Two sources extracted:
+
+1. **CID images**: MIME parts with Content-ID (`cid:` references in HTML)
+2. **Data URI images**: Base64-encoded images in HTML (`data:image/...;base64,...`)
+
+## Common Mistakes
+
+- **Wrong Python**: Ensure `python` points to Python 3.8+
+- **Firewall blocking pip**: First run needs internet for `extract-msg` install
+- **Forgetting inline images**: Always check "본문 삽입 이미지" section and Read each path

package/claude/skills/sd-email-analyze/email-analyzer.py

@@ -0,0 +1,393 @@
+#!/usr/bin/env python3
+"""Email Analyzer - Parses EML/MSG files, extracts body/attachments/inline images to disk."""
+
+import sys
+import os
+import io
+import subprocess
+import email
+import html
+import re
+import base64
+from email.policy import default as default_policy
+from pathlib import Path
+
+# stdout UTF-8 강제 (Windows 호환)
+sys.stdout = io.TextIOWrapper(sys.stdout.buffer, encoding="utf-8", errors="replace")
+sys.stderr = io.TextIOWrapper(sys.stderr.buffer, encoding="utf-8", errors="replace")
+
+
+def ensure_packages():
+    """필요한 패키지 자동 설치."""
+    packages = {"extract-msg": "extract_msg"}
+    missing = []
+    for pip_name, import_name in packages.items():
+        try:
+            __import__(import_name)
+        except ImportError:
+            missing.append(pip_name)
+    if missing:
+        print(f"패키지 설치 중: {', '.join(missing)}...", file=sys.stderr)
+        subprocess.check_call(
+            [sys.executable, "-m", "pip", "install", "-q", *missing],
+            stdout=subprocess.DEVNULL,
+            stderr=subprocess.DEVNULL,
+        )
+
+
+ensure_packages()
+
+import extract_msg  # noqa: E402
+
+
+# ── Korean charset helpers ──────────────────────────────────────────
+
+KOREAN_CHARSET_MAP = {
+    "ks_c_5601-1987": "cp949",
+    "ks_c_5601": "cp949",
+    "euc_kr": "cp949",
+    "euc-kr": "cp949",
+}
+
+
+def fix_charset(charset):
+    if charset is None:
+        return "utf-8"
+    return KOREAN_CHARSET_MAP.get(charset.lower(), charset)
+
+
+# ── Email parsing ──────────────────────────────────────────────────
+
+
+def parse_email(filepath):
+    """Parse email file (.eml or .msg) and return structured data."""
+    ext = Path(filepath).suffix.lower()
+    if ext == ".msg":
+        return _parse_msg(filepath)
+    return _parse_eml(filepath)
+
+
+def _parse_eml(filepath):
+    with open(filepath, "rb") as f:
+        msg = email.message_from_binary_file(f, policy=default_policy)
+
+    headers = {
+        "subject": str(msg["Subject"] or ""),
+        "from": str(msg["From"] or ""),
+        "to": str(msg["To"] or ""),
+        "cc": str(msg["Cc"] or ""),
+        "date": str(msg["Date"] or ""),
+    }
+
+    body_plain = ""
+    body_html = ""
+
+    if msg.is_multipart():
+        for part in msg.walk():
+            ctype = part.get_content_type()
+            cdisp = part.get_content_disposition()
+            if cdisp == "attachment":
+                continue
+            if ctype == "text/plain" and not body_plain:
+                body_plain = _get_text_eml(part)
+            elif ctype == "text/html" and not body_html:
+                body_html = _get_text_eml(part)
+    else:
+        ctype = msg.get_content_type()
+        if ctype == "text/html":
+            body_html = _get_text_eml(msg)
+        else:
+            body_plain = _get_text_eml(msg)
+
+    attachments = []
+    inline_images = []
+    seen_cids = set()
+
+    for part in msg.walk():
+        payload = part.get_payload(decode=True)
+        if payload is None:
+            continue
+
+        content_id = (part.get("Content-ID") or "").strip("<> ")
+        ctype = part.get_content_type()
+        filename = part.get_filename()
+
+        # Inline image: Content-ID + image type
+        if content_id and ctype.startswith("image/"):
+            if content_id not in seen_cids:
+                seen_cids.add(content_id)
+                ext = _guess_image_ext(ctype, filename)
+                inline_images.append({
+                    "content_id": content_id,
+                    "filename": filename or f"inline_{len(inline_images) + 1}{ext}",
+                    "content_type": ctype,
+                    "size": len(payload),
+                    "data": payload,
+                })
+            continue
+
+        # Regular attachment: has filename
+        if not filename:
+            continue
+        cdisp = part.get_content_disposition()
+        if cdisp not in ("attachment", "inline", None):
+            continue
+        attachments.append({
+            "filename": filename,
+            "content_type": ctype,
+            "size": len(payload),
+            "data": payload,
+        })
+
+    return headers, body_plain, body_html, attachments, inline_images
+
+
+def _parse_msg(filepath):
+    msg = extract_msg.openMsg(filepath)
+    try:
+        headers = {
+            "subject": msg.subject or "",
+            "from": msg.sender or "",
+            "to": msg.to or "",
+            "cc": msg.cc or "",
+            "date": str(msg.date or ""),
+        }
+
+        body_plain = msg.body or ""
+        raw_html = getattr(msg, "htmlBody", None)
+        if isinstance(raw_html, bytes):
+            body_html = raw_html.decode("utf-8", errors="replace")
+        else:
+            body_html = raw_html or ""
+
+        attachments = []
+        inline_images = []
+
+        for att in (msg.attachments or []):
+            data = getattr(att, "data", None)
+            if data is None:
+                continue
+            if isinstance(data, str):
+                data = data.encode("utf-8")
+
+            filename = (
+                getattr(att, "longFilename", None)
+                or getattr(att, "shortFilename", None)
+                or getattr(att, "name", None)
+                or "unnamed"
+            )
+            mimetype = getattr(att, "mimetype", None) or "application/octet-stream"
+            cid = getattr(att, "contentId", None) or ""
+
+            entry = {
+                "filename": filename,
+                "content_type": mimetype,
+                "size": len(data),
+                "data": data,
+            }
+
+            if cid and mimetype.startswith("image/"):
+                entry["content_id"] = cid.strip("<> ")
+                inline_images.append(entry)
+            else:
+                attachments.append(entry)
+
+        return headers, body_plain, body_html, attachments, inline_images
+    finally:
+        msg.close()
+
+
+def _get_text_eml(part):
+    try:
+        return part.get_content()
+    except Exception:
+        payload = part.get_payload(decode=True)
+        if not payload:
+            return ""
+        charset = fix_charset(part.get_content_charset())
+        return payload.decode(charset, errors="replace")
+
+
+def _guess_image_ext(content_type, filename=None):
+    if filename:
+        ext = Path(filename).suffix
+        if ext:
+            return ext
+    mapping = {
+        "image/png": ".png",
+        "image/jpeg": ".jpg",
+        "image/gif": ".gif",
+        "image/bmp": ".bmp",
+        "image/webp": ".webp",
+        "image/svg+xml": ".svg",
+    }
+    return mapping.get(content_type, ".bin")
+
+
+# ── File saving ────────────────────────────────────────────────────
+
+
+def save_files(files, output_dir):
+    """Save files to output directory, handling name collisions. Returns list with saved_path."""
+    os.makedirs(output_dir, exist_ok=True)
+    result = []
+    for f in files:
+        filepath = os.path.join(output_dir, f["filename"])
+        if os.path.exists(filepath):
+            stem = Path(filepath).stem
+            ext = Path(filepath).suffix
+            n = 1
+            while os.path.exists(filepath):
+                filepath = os.path.join(output_dir, f"{stem}_{n}{ext}")
+                n += 1
+        with open(filepath, "wb") as fh:
+            fh.write(f["data"])
+        result.append({**f, "saved_path": filepath})
+    return result
+
+
+def extract_data_uri_images(html_body, output_dir):
+    """Extract base64 data URI images embedded in HTML body."""
+    pattern = r'<img[^>]+src=["\']data:image/([^;]+);base64,([^"\']+)["\']'
+    matches = re.findall(pattern, html_body, re.IGNORECASE)
+    if not matches:
+        return []
+
+    os.makedirs(output_dir, exist_ok=True)
+    images = []
+    for i, (img_type, b64data) in enumerate(matches, 1):
+        try:
+            data = base64.b64decode(b64data)
+            ext_map = {"jpeg": ".jpg", "svg+xml": ".svg"}
+            ext = ext_map.get(img_type, f".{img_type}")
+            filename = f"datauri_{i}{ext}"
+            filepath = os.path.join(output_dir, filename)
+            with open(filepath, "wb") as f:
+                f.write(data)
+            images.append({
+                "filename": filename,
+                "content_type": f"image/{img_type}",
+                "size": len(data),
+                "saved_path": filepath,
+            })
+        except Exception:
+            continue
+    return images
+
+
+# ── HTML stripping ──────────────────────────────────────────────────
+
+
+def strip_html(text):
+    text = re.sub(r"<style[^>]*>.*?</style>", "", text, flags=re.DOTALL | re.I)
+    text = re.sub(r"<script[^>]*>.*?</script>", "", text, flags=re.DOTALL | re.I)
+    text = re.sub(r"<br\s*/?>", "\n", text, flags=re.I)
+    text = re.sub(r"</(?:p|div|tr|li)>", "\n", text, flags=re.I)
+    text = re.sub(r"<[^>]+>", "", text)
+    text = html.unescape(text)
+    text = re.sub(r"\n{3,}", "\n\n", text)
+    return text.strip()
+
+
+# ── Size formatting ─────────────────────────────────────────────────
+
+
+def fmt_size(n):
+    if n < 1024:
+        return f"{n} B"
+    if n < 1024 * 1024:
+        return f"{n / 1024:.1f} KB"
+    return f"{n / (1024 * 1024):.1f} MB"
+
+
+# ── Markdown report ─────────────────────────────────────────────────
+
+
+def build_report(filepath):
+    headers, body_plain, body_html, attachments, inline_images = parse_email(filepath)
+
+    out_dir = str(Path(filepath).parent / f"{Path(filepath).stem}_files")
+
+    # Save inline images
+    saved_inline = []
+    if inline_images:
+        saved_inline = save_files(inline_images, out_dir)
+
+    # Extract data URI images from HTML body
+    saved_datauri = []
+    if body_html:
+        saved_datauri = extract_data_uri_images(body_html, out_dir)
+
+    all_inline = saved_inline + saved_datauri
+
+    # Save attachments
+    saved_attachments = []
+    if attachments:
+        saved_attachments = save_files(attachments, out_dir)
+
+    out = []
+    out.append("# 이메일 분석서\n")
+    out.append(f"**원본 파일**: `{os.path.basename(filepath)}`\n")
+
+    # ── 메일 정보
+    out.append("## 메일 정보\n")
+    out.append("| 항목 | 내용 |")
+    out.append("|------|------|")
+    out.append(f"| **제목** | {headers['subject']} |")
+    out.append(f"| **보낸 사람** | {headers['from']} |")
+    out.append(f"| **받는 사람** | {headers['to']} |")
+    if headers["cc"]:
+        out.append(f"| **참조** | {headers['cc']} |")
+    out.append(f"| **날짜** | {headers['date']} |")
+    out.append(f"| **첨부파일** | {len(saved_attachments)}개 |")
+    if all_inline:
+        out.append(f"| **본문 이미지** | {len(all_inline)}개 |")
+    out.append("")
+
+    # ── 본문
+    out.append("## 본문 내용\n")
+    body = body_plain
+    if not body and body_html:
+        body = strip_html(body_html)
+    out.append(body.strip() if body else "_(본문 없음)_")
+    out.append("")
+
+    # ── 본문 삽입 이미지
+    if all_inline:
+        out.append("## 본문 삽입 이미지\n")
+        out.append("| # | 파일명 | 크기 | 저장 경로 |")
+        out.append("|---|--------|------|-----------|")
+        for i, img in enumerate(all_inline, 1):
+            out.append(f"| {i} | {img['filename']} | {fmt_size(img['size'])} | `{img['saved_path']}` |")
+        out.append("")
+
+    # ── 첨부파일
+    if saved_attachments:
+        out.append("## 첨부파일\n")
+        out.append("| # | 파일명 | 크기 | 저장 경로 |")
+        out.append("|---|--------|------|-----------|")
+        for i, a in enumerate(saved_attachments, 1):
+            out.append(f"| {i} | {a['filename']} | {fmt_size(a['size'])} | `{a['saved_path']}` |")
+        out.append("")
+
+    return "\n".join(out)
+
+
+# ── Main ────────────────────────────────────────────────────────────
+
+if __name__ == "__main__":
+    if len(sys.argv) < 2:
+        print("Usage: python email-analyzer.py <eml_or_msg_file>", file=sys.stderr)
+        sys.exit(1)
+
+    path = sys.argv[1]
+    if not os.path.isfile(path):
+        print(f"파일을 찾을 수 없습니다: {path}", file=sys.stderr)
+        sys.exit(1)
+
+    ext = Path(path).suffix.lower()
+    if ext not in (".eml", ".msg"):
+        print(f"지원하지 않는 형식: {ext} (.eml 또는 .msg만 지원)", file=sys.stderr)
+        sys.exit(1)
+
+    print(build_report(path))

package/claude/skills/sd-explore/SKILL.md

@@ -1,6 +1,7 @@
 ---
 name: sd-explore
-description: Deeply analyze a codebase path by tracing execution paths, mapping architecture layers, understanding patterns, and documenting dependencies
+description: Deep codebase analysis - execution paths, architecture, dependencies
+disable-model-invocation: true
 model: sonnet
 context: fork
 allowed-tools: Read, Glob, Grep

package/claude/skills/sd-plan/SKILL.md

@@ -1,6 +1,7 @@
 ---
 name: sd-plan
-description: "NEVER invoke directly from user requests. This skill is ONLY called as a follow-up step after sd-brainstorm has completed. If the user asks to plan, design, or implement something, use sd-brainstorm first."
+description: Implementation plan creation from brainstorm designs
+disable-model-invocation: true
 model: opus
 ---
 

package/claude/skills/sd-plan-dev/SKILL.md

@@ -1,6 +1,7 @@
 ---
 name: sd-plan-dev
-description: Use when executing implementation plans with independent tasks in the current session
+description: Parallel execution of implementation plan tasks
+disable-model-invocation: true
 model: opus
 ---
 

package/claude/skills/sd-readme/SKILL.md

@@ -1,6 +1,7 @@
 ---
 name: sd-readme
-description: Use when updating a package README.md to reflect recent code changes, or when asked to sync README with current implementation, or when creating a new package README from scratch
+description: Package README.md sync with current source code exports
+disable-model-invocation: true
 argument-hint: "<package-name or path> (optional - omit to update all)"
 model: sonnet
 ---