Jobo16/ielts-buddy / skills/ielts-reading-review
ielts-reading-review
Verified根据阅读题目、用户答案和原文证据解释错因、同义替换与干扰项,开展精读或整理阅读词块;也可读取已提交 IELTS Buddy 练习或模考科目。
| File | Kind | Size |
|---|---|---|
| SKILL.md | skill md | 1.3 KB |
| agents/openai.yaml | config | 257 B |
| manifest.json | config | 214 B |
| references/api-access.md | markdown | 1.1 KB |
| references/browser-routes.md | markdown | 587 B |
| references/intensive-reading/WORKFLOW.md | markdown | 2.5 KB |
| references/learning-data.md | markdown | 965 B |
| references/reading-lexicon/WORKFLOW.md | markdown | 6.0 KB |
| references/reading-review/WORKFLOW.md | markdown | 4.5 KB |
| references/review-records.md | markdown | 1.1 KB |
| references/skill-taxonomy.json | config | 1.5 KB |
| scripts/reading-lexicon/create_reading_lexicon_docx.py | script | 30.3 KB |
| scripts/reading-lexicon/extract_reading_docx.py | script | 3.5 KB |
| scripts/reading-lexicon/validate_reading_lexicon_docx.py | script | 6.4 KB |
| scripts/reading-review/create_reading_evidence_map_docx.py | script | 13.4 KB |
| scripts/reading-review/validate_reading_evidence_map_docx.py | script | 3.1 KB |
| scripts/simple_docx.py | script | 9.0 KB |
scripts/reading-review/validate_reading_evidence_map_docx.py
View on GitHub#!/usr/bin/env python3
"""Validate an IELTS Reading evidence-map DOCX."""
from __future__ import annotations
import argparse
import json
import re
from pathlib import Path
from xml.etree import ElementTree as ET
from zipfile import ZipFile
W_NS = "http://schemas.openxmlformats.org/wordprocessingml/2006/main"
W = f"{{{W_NS}}}"
FONT = "Times New Roman"
def qn(tag: str) -> str:
return f"{W}{tag}"
def text_of(el: ET.Element) -> str:
return "".join(t.text or "" for t in el.iter(qn("t")))
def normalize_spaces(text: str) -> str:
return " ".join(text.split())
def contains_text(haystack: str, needle: str) -> bool:
return normalize_spaces(needle).lower() in normalize_spaces(haystack).lower()
def main() -> None:
parser = argparse.ArgumentParser(description=__doc__)
parser.add_argument("docx", type=Path)
parser.add_argument("--plan-json", type=Path, default=None)
args = parser.parse_args()
with ZipFile(args.docx) as zf:
names = set(zf.namelist())
required = {"word/document.xml", "word/styles.xml", "[Content_Types].xml"}
missing = sorted(required - names)
if missing:
raise SystemExit(f"Missing required DOCX parts: {missing}")
doc_xml = zf.read("word/document.xml").decode("utf-8")
doc = ET.fromstring(doc_xml)
all_text = text_of(doc)
for marker in [
"雅思阅读证据图",
"答案证据图",
"逐题分析",
"证据",
"同义替换桥",
"陷阱/干扰项",
"错误类型",
]:
if marker not in all_text:
raise SystemExit(f"Missing required evidence-map text: {marker}")
tables = len(list(doc.iter(qn("tbl"))))
if tables < 1:
raise SystemExit("Expected at least one evidence-map table")
page_breaks = sum(1 for br in doc.iter(qn("br")) if br.get(qn("type")) == "page")
if page_breaks < 1:
raise SystemExit(f"Expected at least 1 page break, found {page_breaks}")
if FONT not in doc_xml:
raise SystemExit(f"{FONT} not found in document XML")
if args.plan_json:
plan = json.loads(args.plan_json.read_text(encoding="utf-8"))
items = [item for item in plan.get("items", []) if isinstance(item, dict)]
if not items:
raise SystemExit("Plan must contain at least one reading review item")
for item in items:
for key in ("correct_answer", "evidence", "paraphrase_bridge", "error_type"):
value = normalize_spaces(str(item.get(key, "")))
if value and not contains_text(all_text, value[:100]):
raise SystemExit(f"{key} missing from DOCX: {value[:100]}")
q = normalize_spaces(str(item.get("question_number", item.get("q", ""))))
if q and not contains_text(all_text, q):
raise SystemExit(f"Question number missing from DOCX: {q}")
paragraphs = len([p for p in doc.iter(qn("p")) if normalize_spaces(text_of(p))])
words = len(re.findall(r"[A-Za-z]+(?:[-'][A-Za-z]+)?|\d+", all_text))
print(f"OK: tables={tables}, page_breaks={page_breaks}, paragraphs={paragraphs}, words={words}")
if __name__ == "__main__":
main()
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| receiving-code-reviewobra/superpowersUse when receiving code review feedback, before implementing suggestions, especially if feedback seems unclear or technically questionable - requires technical rigor and verification, not performative agreement or blind implementation | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| requesting-code-reviewobra/superpowersUse when completing tasks, implementing major features, or before merging to verify work meets requirements | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| using-git-worktreesobra/superpowersUse when starting feature work that needs isolation from current workspace or before executing implementation plans - ensures an isolated workspace exists via native tools or git worktree fallback | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| verification-before-completionobra/superpowersUse when about to claim work is complete, fixed, or passing, before committing or creating PRs - requires running verification commands and confirming output before making any success claims; evidence before assertions always | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |