version: 1
metadata:
  key: "automation-testing"
interface:
  display_name: "Automation Testing (English)"
  short_description: "Use this skill when you need to design automation testing approaches using patterns like POM, data-driven testing, or BDD; triggers include automation testing…"
  default_prompt: "Use the automation-testing skill to complete this testing task with structured outputs and practical next steps."
policy:
  allow_implicit_invocation: true

schema_version: v1alpha1

environment:
  type: none

skills:
  - source: local_path
    path: .

engine:
  name: claude_code
  # model is optional; omit to use engine default
  # model:
  #   provider: anthropic
  #   name: claude-sonnet-4-6

cases:
  files:
    - evals/cases/basic-success.yaml
    - evals/cases/edge-incomplete-input.yaml
    - evals/cases/edge-domain-boundary.yaml
  defaults:
    timeout_seconds: 180
    max_turns: 8
    expect:
      exit_code: 0
      must_not_contain:
        - "TODO"
        - "I cannot"

report:
  formats: [json]

{
  "meta": {
    "skill": "",
    "scope": "",
    "environment": "",
    "priority": ""
  },
  "inputs": {
    "requirement": "",
    "constraints": [],
    "risks": []
  },
  "execution": [
    { "step": 1, "action": "", "expected": "" }
  ],
  "results": {
    "status": "",
    "evidence": [],
    "defects": []
  },
  "next_actions": [
    { "owner": "", "eta": "", "action": "" }
  ]
}

# QA Output Template

## Summary
- Skill:
- Scope:
- Environment:
- Priority:

## Inputs
- Requirement:
- Constraints:
- Risks:

## Execution
1. Step 1
2. Step 2
3. Step 3

## Results
- Status:
- Evidence:
- Defects:

## Next Actions
- Owner:
- ETA:

QA Report
=========

1. Basic Information
- Skill:
- Scope:
- Environment:
- Priority:

2. Requirement and Constraints
- Requirement:
- Constraints:
- Risks:

3. Test/Review Process
- Step 1:
- Step 2:
- Step 3:

4. Outcome
- Status:
- Evidence:
- Defects:

5. Follow-up Plan
- Owner:
- ETA:
- Action:

# QA Output Mindmap

- QA Output
  - Meta
    - Skill
    - Scope
    - Environment
    - Priority
  - Inputs
    - Requirement
    - Constraints
    - Risks
  - Execution
    - Step 1
    - Step 2
    - Step 3
  - Results
    - Status
    - Evidence
    - Defects
  - Next Actions
    - Owner
    - ETA
    - Action

# Automation Testing Prompt

Design or refine an automation testing approach that is worth building, maintainable, and focused on the right risks.

## Role

- Act as a senior QA and automation testing expert who balances coverage value, stability, and maintenance cost.


## Input

- product scope, user flows, APIs, or current test suite information
- existing framework, language, CI setup, and team constraints
- manual pain points, flaky areas, release expectations, and risk hotspots

## What to do

1. Decide what should be automated first and what should stay manual for now.
2. Optimize for value, stability, and maintenance cost instead of raw script count.
3. Produce an execution-ready automation plan or recommendation.

## Execution Rules

- Prioritize stable, high-value, repeatable checks.
- Flag areas with poor automation ROI such as unstable UI or one-off flows.
- Respect the current stack when possible instead of proposing a full rewrite.

## Minimum Coverage Checklist

Unless the user explicitly narrows the scope, make sure the result addresses these items:
- scope and objective
- automation candidates
- manual-only areas
- priority by risk and ROI
- framework alignment
- data and environment needs
- flaky-test risks
- CI or execution strategy
- maintenance concerns
- missing information and assumptions

## Output

Return the result in this order:

### 1. Task Understanding
### 2. What to Automate First
### 3. What Not to Automate Yet
### 4. Recommended Approach
### 5. Execution Plan
### 6. Risks and Guardrails

## Quality Bar

- Explain why each automation recommendation is worth it.
- Do not recommend automating everything.
- Keep the result practical for the existing team.

## Troubleshooting

### Common Issues

#### 1. Element Not Found (NoSuchElementException)

**Problem:** Cannot find page element during test execution

**Solution:**
```python
# Use explicit wait
from selenium.webdriver.support.ui import WebDriverWait
from selenium.webdriver.support import expected_conditions as EC

wait = WebDriverWait(driver, 20)
element = wait.until(EC.presence_of_element_located((By.ID, "element")))

# Or increase implicit wait time
driver.implicitly_wait(10)
```

#### 2. Element Not Clickable (ElementClickInterceptedException)

**Problem:** Element is obscured by other elements

**Solution:**
```python
# Wait for element to be clickable
wait.until(EC.element_to_be_clickable((By.ID, "button"))).click()

# Or use JavaScript click
driver.execute_script("arguments[0].click();", element)

# Or scroll to element
driver.execute_script("arguments[0].scrollIntoView(true);", element)
```

#### 3. StaleElementReferenceException

**Problem:** Element reference becomes stale after page refresh

**Solution:**
```python
# Re-find the element
def safe_click(locator):
    for _ in range(3):
        try:
            element = driver.find_element(*locator)
            element.click()
            break
        except StaleElementReferenceException:
            time.sleep(0.5)
```

#### 4. Browser Driver Version Mismatch

**Problem:** `SessionNotCreatedException: session not created`

**Solution:**
```bash
# Use webdriver-manager to auto-manage drivers
pip install webdriver-manager

# Use in code
from webdriver_manager.chrome import ChromeDriverManager
driver = webdriver.Chrome(service=Service(ChromeDriverManager().install()))
```

#### 5. Slow Test Execution

**Problem:** Tests take too long to execute

**Solution:**
- Use headless mode: `options.add_argument("--headless")`
- Run tests in parallel: `pytest -n 4`
- Reduce unnecessary wait times
- Optimize locators (prioritize ID, Name)

#### 6. Flaky Tests

**Problem:** Tests sometimes pass, sometimes fail

**Solution:**
- Increase wait times
- Use explicit waits instead of implicit waits
- Check test data dependencies
- Ensure test independence
- Add retry mechanism: `@pytest.mark.flaky(reruns=3)`

#### 7. Screenshot Functionality Not Working

**Problem:** No screenshots generated when tests fail

**Solution:**
```python
# Add hook in conftest.py
@pytest.hookimpl(tryfirst=True, hookwrapper=True)
def pytest_runtest_makereport(item, call):
    outcome = yield
    rep = outcome.get_result()
    if rep.when == "call" and rep.failed:
        driver = item.funcargs.get("driver")
        if driver:
            driver.save_screenshot(f"screenshots/{item.name}.png")
```

#!/usr/bin/env python3
import argparse
import subprocess
import sys
from pathlib import Path


def detect_from(file: Path) -> str:
    ext = file.suffix.lower()
    if file.name.endswith('.word.md'):
        return 'markdown'
    return {
        '.md': 'markdown',
        '.markdown': 'markdown',
        '.json': 'json',
        '.csv': 'csv',
        '.tsv': 'excel',
        '.docx': 'word',
        '.xlsx': 'excel',
        '.xmind': 'xmind',
    }.get(ext, 'markdown')


def run_convert(convert_script: Path, src: Path, to_fmt: str, out: Path) -> int:
    cmd = [sys.executable, str(convert_script), str(src), '--from', detect_from(src), '--to', to_fmt, '--output', str(out)]
    return subprocess.call(cmd)


def main() -> None:
    parser = argparse.ArgumentParser(description='Batch convert all template files into target formats.')
    parser.add_argument('--templates-dir', type=Path, default=Path('output-templates'))
    parser.add_argument('--artifacts-dir', type=Path, default=Path('artifacts'))
    parser.add_argument('--targets', default='word,excel,xmind,json,csv,markdown', help='comma-separated target formats')
    parser.add_argument('--skip-same', action='store_true', help='skip conversion when source format equals target format')
    args = parser.parse_args()

    cwd = Path.cwd()
    templates_dir = (cwd / args.templates_dir).resolve()
    artifacts_dir = (cwd / args.artifacts_dir).resolve()
    artifacts_dir.mkdir(parents=True, exist_ok=True)

    local_convert = (Path(__file__).resolve().parent / 'convert_formats.py').resolve()
    targets = [t.strip() for t in args.targets.split(',') if t.strip()]

    if not templates_dir.exists():
        raise SystemExit(f'templates directory not found: {templates_dir}')

    files = [p for p in sorted(templates_dir.iterdir()) if p.is_file()]
    total = 0
    failed = 0

    for src in files:
        src_fmt = detect_from(src)
        for to_fmt in targets:
            if args.skip_same and src_fmt == to_fmt:
                continue
            out_ext = {
                'json': '.json',
                'csv': '.csv',
                'excel': '.tsv',
                'markdown': '.md',
                'word': '.word.md',
                'xmind': '.xmind.md',
            }[to_fmt]
            out = artifacts_dir / f"{src.stem}.to-{to_fmt}{out_ext}"
            total += 1
            rc = run_convert(local_convert, src, to_fmt, out)
            if rc != 0:
                failed += 1
                print(f'[FAILED] {src.name} -> {to_fmt}')
            else:
                print(f'[OK] {src.name} -> {out.name}')

    print(f'\nDone. total={total}, failed={failed}, artifacts={artifacts_dir}')
    if failed:
        raise SystemExit(1)


if __name__ == '__main__':
    main()

#!/usr/bin/env python3
import argparse
import csv
import json
import re
import zipfile
from pathlib import Path
from typing import Any
from xml.etree import ElementTree as ET


# ---- parsing ----
def parse_markdown(path: Path) -> dict[str, Any]:
    text = path.read_text(encoding="utf-8", errors="ignore")
    lines = text.splitlines()
    headings: list[dict[str, Any]] = []
    for line in lines:
        m = re.match(r"^(#{1,6})\s+(.*)$", line.strip())
        if m:
            headings.append({"level": len(m.group(1)), "title": m.group(2).strip()})
    return {"title": headings[0]["title"] if headings else path.stem, "headings": headings, "text": text}


def parse_json(path: Path) -> dict[str, Any]:
    data = json.loads(path.read_text(encoding="utf-8", errors="ignore"))
    return {"title": path.stem, "data": data}


def parse_csv_file(path: Path) -> dict[str, Any]:
    with path.open("r", encoding="utf-8", errors="ignore", newline="") as f:
        reader = csv.DictReader(f)
        rows = list(reader)
    return {"title": path.stem, "columns": reader.fieldnames or [], "rows": rows}


def parse_docx(path: Path) -> dict[str, Any]:
    paragraphs: list[str] = []
    with zipfile.ZipFile(path) as zf:
        with zf.open("word/document.xml") as f:
            root = ET.fromstring(f.read())
    ns = {"w": "http://schemas.openxmlformats.org/wordprocessingml/2006/main"}
    for p in root.findall(".//w:p", ns):
        texts = [t.text for t in p.findall(".//w:t", ns) if t.text]
        s = "".join(texts).strip()
        if s:
            paragraphs.append(s)
    return {"title": path.stem, "paragraphs": paragraphs}


def _shared_strings(zf: zipfile.ZipFile) -> list[str]:
    out: list[str] = []
    try:
        with zf.open("xl/sharedStrings.xml") as f:
            root = ET.fromstring(f.read())
        ns = {"a": "http://schemas.openxmlformats.org/spreadsheetml/2006/main"}
        for si in root.findall(".//a:si", ns):
            out.append("".join((t.text or "") for t in si.findall(".//a:t", ns)))
    except KeyError:
        pass
    return out


def parse_xlsx(path: Path) -> dict[str, Any]:
    rows: list[list[str]] = []
    with zipfile.ZipFile(path) as zf:
        shared = _shared_strings(zf)
        with zf.open("xl/worksheets/sheet1.xml") as f:
            root = ET.fromstring(f.read())
    ns = {"a": "http://schemas.openxmlformats.org/spreadsheetml/2006/main"}
    for row in root.findall(".//a:sheetData/a:row", ns):
        vals = []
        for c in row.findall("a:c", ns):
            t = c.attrib.get("t")
            v = c.find("a:v", ns)
            if v is None or v.text is None:
                vals.append("")
            elif t == "s":
                idx = int(v.text)
                vals.append(shared[idx] if 0 <= idx < len(shared) else "")
            else:
                vals.append(v.text)
        rows.append(vals)
    return {"title": path.stem, "rows": rows}


def parse_xmind(path: Path) -> dict[str, Any]:
    with zipfile.ZipFile(path) as zf:
        names = set(zf.namelist())
        topics: list[str] = []
        if "content.json" in names:
            data = json.loads(zf.read("content.json").decode("utf-8", errors="ignore"))

            def walk(node: Any):
                if isinstance(node, dict):
                    t = node.get("title")
                    if isinstance(t, str) and t.strip():
                        topics.append(t.strip())
                    for k in ("children", "topics", "rootTopic", "attached"):
                        walk(node.get(k))
                elif isinstance(node, list):
                    for i in node:
                        walk(i)

            walk(data)
        elif "content.xml" in names:
            root = ET.fromstring(zf.read("content.xml"))
            topics = [e.text.strip() for e in root.findall(".//title") if e.text and e.text.strip()]
        else:
            raise ValueError("Unsupported XMind package structure")
    return {"title": topics[0] if topics else path.stem, "topics": topics}


def detect_in_format(path: Path, forced: str | None) -> str:
    if forced and forced != "auto":
        return forced
    return {
        ".md": "markdown",
        ".markdown": "markdown",
        ".json": "json",
        ".csv": "csv",
        ".docx": "word",
        ".xlsx": "excel",
        ".xmind": "xmind",
        ".tsv": "excel",
    }.get(path.suffix.lower(), "markdown")


def normalize(parsed: dict[str, Any]) -> dict[str, Any]:
    title = parsed.get("title") or "QA Output"
    sections: list[dict[str, Any]] = []

    if "text" in parsed:
        sections.append({"name": "content", "items": [{"key": "text", "value": parsed["text"]}]})
    if "headings" in parsed:
        sections.append({"name": "headings", "items": [{"key": "heading", "value": h.get("title", "")} for h in parsed["headings"]]})
    if "data" in parsed:
        data = parsed["data"]
        if isinstance(data, dict):
            items = [{"key": k, "value": v} for k, v in list(data.items())[:100]]
            sections.append({"name": "json_object", "items": items})
        elif isinstance(data, list):
            sections.append({"name": "json_array", "items": [{"key": "row", "value": v} for v in data[:200]]})
        else:
            sections.append({"name": "json_value", "items": [{"key": "value", "value": data}]})
    if "rows" in parsed:
        rows = parsed["rows"]
        sections.append({"name": "rows", "items": [{"key": f"row_{i+1}", "value": r} for i, r in enumerate(rows[:200])]})
    if "columns" in parsed:
        sections.append({"name": "columns", "items": [{"key": "column", "value": c} for c in parsed["columns"]]})
    if "paragraphs" in parsed:
        sections.append({"name": "paragraphs", "items": [{"key": f"p{i+1}", "value": p} for i, p in enumerate(parsed["paragraphs"][:200])]})
    if "topics" in parsed:
        sections.append({"name": "topics", "items": [{"key": "topic", "value": t} for t in parsed["topics"][:300]]})

    return {"title": title, "sections": sections}


# ---- writers ----
def write_json(model: dict[str, Any], output: Path) -> None:
    output.write_text(json.dumps(model, ensure_ascii=False, indent=2), encoding="utf-8")


def _scalar(v: Any) -> str:
    if isinstance(v, (dict, list)):
        return json.dumps(v, ensure_ascii=False)
    return str(v)


def write_csv(model: dict[str, Any], output: Path) -> None:
    with output.open("w", encoding="utf-8", newline="") as f:
        writer = csv.writer(f)
        writer.writerow(["section", "key", "value"])
        for s in model.get("sections", []):
            for item in s.get("items", []):
                writer.writerow([s.get("name", ""), item.get("key", ""), _scalar(item.get("value", ""))])


def write_excel_tsv(model: dict[str, Any], output: Path) -> None:
    lines = ["Section\tKey\tValue"]
    for s in model.get("sections", []):
        for item in s.get("items", []):
            lines.append(f"{s.get('name','')}\t{item.get('key','')}\t{_scalar(item.get('value','')).replace(chr(9), ' ')}")
    output.write_text("\n".join(lines) + "\n", encoding="utf-8")


def write_markdown(model: dict[str, Any], output: Path) -> None:
    lines = [f"# {model.get('title', 'QA Output')}", ""]
    for s in model.get("sections", []):
        lines.append(f"## {s.get('name', 'section')}")
        for item in s.get("items", []):
            lines.append(f"- **{item.get('key','key')}**: {_scalar(item.get('value',''))}")
        lines.append("")
    output.write_text("\n".join(lines).rstrip() + "\n", encoding="utf-8")


def write_word_md(model: dict[str, Any], output: Path) -> None:
    lines = [model.get("title", "QA Output"), "=" * len(model.get("title", "QA Output")), ""]
    idx = 1
    for s in model.get("sections", []):
        lines.append(f"{idx}. {s.get('name', 'section').replace('_', ' ').title()}")
        for item in s.get("items", []):
            lines.append(f"- {item.get('key','key')}: {_scalar(item.get('value',''))}")
        lines.append("")
        idx += 1
    output.write_text("\n".join(lines).rstrip() + "\n", encoding="utf-8")


def write_xmind_md(model: dict[str, Any], output: Path) -> None:
    lines = [f"# {model.get('title', 'QA Output')}", "", f"- {model.get('title', 'QA Output')}"]
    for s in model.get("sections", []):
        lines.append(f"  - {s.get('name', 'section')}")
        for item in s.get("items", []):
            lines.append(f"    - {item.get('key','key')}: {_scalar(item.get('value',''))}")
    output.write_text("\n".join(lines).rstrip() + "\n", encoding="utf-8")


def default_output(input_path: Path, to_fmt: str) -> Path:
    ext = {
        "json": ".json",
        "csv": ".csv",
        "excel": ".tsv",
        "markdown": ".md",
        "word": ".word.md",
        "xmind": ".xmind.md",
    }[to_fmt]
    return input_path.with_name(input_path.stem + ".converted" + ext)


def main() -> None:
    parser = argparse.ArgumentParser(description="Convert QA output files between common formats")
    parser.add_argument("input", type=Path, help="Input file path")
    parser.add_argument("--from", dest="from_fmt", default="auto", choices=["auto", "word", "excel", "xmind", "json", "csv", "markdown"])
    parser.add_argument("--to", required=True, choices=["word", "excel", "xmind", "json", "csv", "markdown"])
    parser.add_argument("--output", type=Path, help="Output file path")
    args = parser.parse_args()

    in_fmt = detect_in_format(args.input, args.from_fmt)
    if in_fmt == "word":
        parsed = parse_docx(args.input)
    elif in_fmt == "excel":
        if args.input.suffix.lower() == ".tsv":
            rows = [line.rstrip("\n").split("\t") for line in args.input.read_text(encoding="utf-8", errors="ignore").splitlines() if line]
            parsed = {"title": args.input.stem, "rows": rows}
        else:
            parsed = parse_xlsx(args.input)
    elif in_fmt == "xmind":
        parsed = parse_xmind(args.input)
    elif in_fmt == "json":
        parsed = parse_json(args.input)
    elif in_fmt == "csv":
        parsed = parse_csv_file(args.input)
    else:
        parsed = parse_markdown(args.input)

    model = normalize(parsed)
    output = args.output or default_output(args.input, args.to)

    if args.to == "json":
        write_json(model, output)
    elif args.to == "csv":
        write_csv(model, output)
    elif args.to == "excel":
        write_excel_tsv(model, output)
    elif args.to == "markdown":
        write_markdown(model, output)
    elif args.to == "word":
        write_word_md(model, output)
    else:
        write_xmind_md(model, output)

    print(str(output))


if __name__ == "__main__":
    main()

#!/usr/bin/env python3
import os
import subprocess
import sys
LOCAL = os.path.normpath(os.path.join(os.path.dirname(__file__), 'convert_formats.py'))
if __name__ == '__main__':
    raise SystemExit(subprocess.call([sys.executable, LOCAL] + sys.argv[1:]))

#!/usr/bin/env python3
import os
import subprocess
import sys
LOCAL = os.path.normpath(os.path.join(os.path.dirname(__file__), 'convert_formats.py'))
if __name__ == '__main__':
    raise SystemExit(subprocess.call([sys.executable, LOCAL, '--to', 'csv'] + sys.argv[1:]))

#!/usr/bin/env python3
import os
import subprocess
import sys
LOCAL = os.path.normpath(os.path.join(os.path.dirname(__file__), 'convert_formats.py'))
if __name__ == '__main__':
    raise SystemExit(subprocess.call([sys.executable, LOCAL, '--to', 'excel'] + sys.argv[1:]))

#!/usr/bin/env python3
import os
import subprocess
import sys
LOCAL = os.path.normpath(os.path.join(os.path.dirname(__file__), 'convert_formats.py'))
if __name__ == '__main__':
    raise SystemExit(subprocess.call([sys.executable, LOCAL, '--to', 'json'] + sys.argv[1:]))

#!/usr/bin/env python3
import os
import subprocess
import sys
LOCAL = os.path.normpath(os.path.join(os.path.dirname(__file__), 'convert_formats.py'))
if __name__ == '__main__':
    raise SystemExit(subprocess.call([sys.executable, LOCAL, '--to', 'markdown'] + sys.argv[1:]))

#!/usr/bin/env python3
import os
import subprocess
import sys
LOCAL = os.path.normpath(os.path.join(os.path.dirname(__file__), 'convert_formats.py'))
if __name__ == '__main__':
    raise SystemExit(subprocess.call([sys.executable, LOCAL, '--to', 'word'] + sys.argv[1:]))

#!/usr/bin/env python3
import os
import subprocess
import sys
LOCAL = os.path.normpath(os.path.join(os.path.dirname(__file__), 'convert_formats.py'))
if __name__ == '__main__':
    raise SystemExit(subprocess.call([sys.executable, LOCAL, '--to', 'xmind'] + sys.argv[1:]))

#!/usr/bin/env python3
import os
import subprocess
import sys
LOCAL = os.path.normpath(os.path.join(os.path.dirname(__file__), 'parse_formats.py'))
if __name__ == '__main__':
    raise SystemExit(subprocess.call([sys.executable, LOCAL, '--format', 'csv'] + sys.argv[1:]))

#!/usr/bin/env python3
import os
import subprocess
import sys
LOCAL = os.path.normpath(os.path.join(os.path.dirname(__file__), 'parse_formats.py'))
if __name__ == '__main__':
    raise SystemExit(subprocess.call([sys.executable, LOCAL, '--format', 'excel'] + sys.argv[1:]))

#!/usr/bin/env python3
import argparse
import csv
import json
import re
import zipfile
from pathlib import Path
from typing import Any
from xml.etree import ElementTree as ET


def parse_markdown(path: Path) -> dict[str, Any]:
    text = path.read_text(encoding="utf-8", errors="ignore")
    headings = []
    for line in text.splitlines():
        m = re.match(r"^(#{1,6})\s+(.*)$", line.strip())
        if m:
            headings.append({"level": len(m.group(1)), "title": m.group(2).strip()})
    return {"format": "markdown", "headings": headings, "preview": text[:500]}


def parse_json(path: Path) -> dict[str, Any]:
    data = json.loads(path.read_text(encoding="utf-8", errors="ignore"))
    if isinstance(data, dict):
        shape = {"type": "object", "keys": list(data.keys())[:50]}
    elif isinstance(data, list):
        shape = {"type": "array", "size": len(data)}
    else:
        shape = {"type": type(data).__name__}
    return {"format": "json", "shape": shape, "data": data}


def parse_csv_file(path: Path) -> dict[str, Any]:
    with path.open("r", encoding="utf-8", errors="ignore", newline="") as f:
        reader = csv.DictReader(f)
        rows = list(reader)
    return {
        "format": "csv",
        "columns": reader.fieldnames or [],
        "row_count": len(rows),
        "sample_rows": rows[:10],
    }


def parse_docx(path: Path) -> dict[str, Any]:
    paragraphs = []
    with zipfile.ZipFile(path) as zf:
        with zf.open("word/document.xml") as f:
            root = ET.fromstring(f.read())
    ns = {"w": "http://schemas.openxmlformats.org/wordprocessingml/2006/main"}
    for p in root.findall(".//w:p", ns):
        texts = [t.text for t in p.findall(".//w:t", ns) if t.text]
        joined = "".join(texts).strip()
        if joined:
            paragraphs.append(joined)
    return {"format": "word", "paragraph_count": len(paragraphs), "paragraphs": paragraphs[:100]}


def _read_shared_strings(zf: zipfile.ZipFile) -> list[str]:
    strings = []
    try:
        with zf.open("xl/sharedStrings.xml") as f:
            root = ET.fromstring(f.read())
        ns = {"a": "http://schemas.openxmlformats.org/spreadsheetml/2006/main"}
        for si in root.findall(".//a:si", ns):
            parts = [t.text or "" for t in si.findall(".//a:t", ns)]
            strings.append("".join(parts))
    except KeyError:
        pass
    return strings


def parse_xlsx(path: Path) -> dict[str, Any]:
    rows_out: list[list[str]] = []
    with zipfile.ZipFile(path) as zf:
        shared = _read_shared_strings(zf)
        with zf.open("xl/worksheets/sheet1.xml") as f:
            root = ET.fromstring(f.read())
    ns = {"a": "http://schemas.openxmlformats.org/spreadsheetml/2006/main"}
    for row in root.findall(".//a:sheetData/a:row", ns):
        vals = []
        for c in row.findall("a:c", ns):
            cell_type = c.attrib.get("t")
            v = c.find("a:v", ns)
            if v is None or v.text is None:
                vals.append("")
                continue
            if cell_type == "s":
                idx = int(v.text)
                vals.append(shared[idx] if 0 <= idx < len(shared) else "")
            else:
                vals.append(v.text)
        rows_out.append(vals)
    return {"format": "excel", "row_count": len(rows_out), "sample_rows": rows_out[:20]}


def parse_xmind(path: Path) -> dict[str, Any]:
    with zipfile.ZipFile(path) as zf:
        names = set(zf.namelist())
        if "content.json" in names:
            data = json.loads(zf.read("content.json").decode("utf-8", errors="ignore"))
            titles: list[str] = []

            def walk(node: Any):
                if isinstance(node, dict):
                    title = node.get("title")
                    if isinstance(title, str) and title.strip():
                        titles.append(title.strip())
                    for k in ("children", "topics", "rootTopic", "attached"):
                        walk(node.get(k))
                elif isinstance(node, list):
                    for i in node:
                        walk(i)

            walk(data)
            return {"format": "xmind", "topic_count": len(titles), "topics": titles[:200]}
        if "content.xml" in names:
            root = ET.fromstring(zf.read("content.xml"))
            titles = [el.text.strip() for el in root.findall(".//title") if el.text and el.text.strip()]
            return {"format": "xmind", "topic_count": len(titles), "topics": titles[:200]}
    raise ValueError("Unsupported XMind package structure")


def detect_format(path: Path, forced: str | None) -> str:
    if forced and forced != "auto":
        return forced
    ext = path.suffix.lower()
    return {
        ".md": "markdown",
        ".markdown": "markdown",
        ".json": "json",
        ".csv": "csv",
        ".docx": "word",
        ".xlsx": "excel",
        ".xmind": "xmind",
    }.get(ext, "markdown")


def main() -> None:
    parser = argparse.ArgumentParser(description="Parse common QA output formats into normalized JSON")
    parser.add_argument("input", type=Path, help="Input file path")
    parser.add_argument("--format", default="auto", choices=["auto", "word", "excel", "xmind", "json", "csv", "markdown"])
    parser.add_argument("--output", type=Path, help="Output JSON path (default: stdout)")
    args = parser.parse_args()

    fmt = detect_format(args.input, args.format)
    if fmt == "word":
        result = parse_docx(args.input)
    elif fmt == "excel":
        result = parse_xlsx(args.input)
    elif fmt == "xmind":
        result = parse_xmind(args.input)
    elif fmt == "json":
        result = parse_json(args.input)
    elif fmt == "csv":
        result = parse_csv_file(args.input)
    else:
        result = parse_markdown(args.input)

    result["source"] = str(args.input)
    out = json.dumps(result, ensure_ascii=False, indent=2)
    if args.output:
        args.output.write_text(out, encoding="utf-8")
    else:
        print(out)


if __name__ == "__main__":
    main()

#!/usr/bin/env python3
import os
import subprocess
import sys
LOCAL = os.path.normpath(os.path.join(os.path.dirname(__file__), 'parse_formats.py'))
if __name__ == '__main__':
    raise SystemExit(subprocess.call([sys.executable, LOCAL, '--format', 'json'] + sys.argv[1:]))

#!/usr/bin/env python3
import os
import subprocess
import sys
LOCAL = os.path.normpath(os.path.join(os.path.dirname(__file__), 'parse_formats.py'))
if __name__ == '__main__':
    raise SystemExit(subprocess.call([sys.executable, LOCAL, '--format', 'markdown'] + sys.argv[1:]))

#!/usr/bin/env python3
import os
import subprocess
import sys
LOCAL = os.path.normpath(os.path.join(os.path.dirname(__file__), 'parse_formats.py'))
if __name__ == '__main__':
    raise SystemExit(subprocess.call([sys.executable, LOCAL] + sys.argv[1:]))

#!/usr/bin/env python3
import os
import subprocess
import sys
LOCAL = os.path.normpath(os.path.join(os.path.dirname(__file__), 'parse_formats.py'))
if __name__ == '__main__':
    raise SystemExit(subprocess.call([sys.executable, LOCAL, '--format', 'word'] + sys.argv[1:]))

#!/usr/bin/env python3
import os
import subprocess
import sys
LOCAL = os.path.normpath(os.path.join(os.path.dirname(__file__), 'parse_formats.py'))
if __name__ == '__main__':
    raise SystemExit(subprocess.call([sys.executable, LOCAL, '--format', 'xmind'] + sys.argv[1:]))