agentsclimarketplace

Wp http article audit

Skill bokuwalily/claude-code-skills/skills/wp-http-article-audit

WordPressサイトのURLリストを並列HTTPで一括取得し、記事上部エリア(article~最初のh2間)の特定CTAの設置状況を分類・CSV出力するときに使うFrom its SKILL.md

Install
npx -y skills add bokuwalily/claude-code-skills --skill wp-http-article-audit

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

One thing to look at

  • 0 stars0 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.

SKILL.md

3.4 KB, 939 tokens by cl100k_base, as published. Nobody here has run it

Procedure

  1. 対象URLリストを取得

    • Excelや管理画面から対象記事のURLを収集しCSVに保存
    • WP-CLIが使えるなら: wp post list --post_type=post --posts_per_page=-1 --fields=ID,post_name,guid
  2. 判定ロジックの設計

    • NG: ページ全体に検索ドメインが存在するかだけでは不正確(フッター・サイドバーで誤検知)
    • OK: <article> タグ開始〜最初の <h2> タグまでの範囲に絞って判定する
  3. 並列HTTPチェックスクリプト(Python例)

import asyncio, aiohttp, csv
from bs4 import BeautifulSoup

TARGET_DOMAIN = "lp.example.co.jp"
OTHER_DOMAIN  = "realme.jp"

async def check(session, url):
    try:
        async with session.get(url, timeout=aiohttp.ClientTimeout(total=10)) as r:
            html = await r.text()
    except Exception as e:
        return url, "ERROR", str(e)

    soup = BeautifulSoup(html, "html.parser")
    article = soup.find("article")
    if not article:
        return url, "NO_ARTICLE", ""

    # article 先頭〜最初の h2 までを切り出す
    segment = ""
    for tag in article.children:
        if getattr(tag, "name", None) == "h2":
            break
        segment += str(tag)

    if TARGET_DOMAIN in segment:
        status = "TARGET"
    elif OTHER_DOMAIN in segment:
        status = "OTHER_CTA"
    elif segment.strip():
        status = "NO_CTA"
    else:
        status = "EMPTY"
    return url, status, ""

async def main(urls):
    async with aiohttp.ClientSession() as session:
        tasks = [check(session, u) for u in urls]
        return await asyncio.gather(*tasks)

urls = [row[0] for row in csv.reader(open("target_urls.csv"))]
results = asyncio.run(main(urls))

with open("audit_result.csv", "w", newline="") as f:
    w = csv.writer(f)
    w.writerow(["url", "status", "note"])
    w.writerows(results)
  1. 結果の絞り込み
    • status != "TARGET" の行が対応必要記事
    • OTHER_CTA(他社CTAあり)と NO_CTA(なし)を別々に集計して優先度をつける

Pitfalls

  • フッター誤検知: ページ全体でドメイン検索すると、フッターやサイドバーのリンクも拾う。必ず記事上部エリアに限定する
  • article タグなし: LP や固定ページは <article> がない場合がある。フォールバック(main タグ等)を追加するか除外する
  • レート制限: 並列数を多くしすぎると503返す。asyncio.Semaphore(20) 等で同時接続数を制限する
  • エンコーディング: 日本語サイトは r.text() だと文字化けする場合あり。await r.read() して html.decode("utf-8", errors="replace") に切替える

Verification

# 出力CSVで件数確認
python3 -c "
import csv; rows=list(csv.DictReader(open('audit_result.csv')))
from collections import Counter; print(Counter(r['status'] for r in rows))
"
# → Counter({'TARGET': 215, 'OTHER_CTA': 517, 'NO_CTA': 86, ...}) のように分類されればOK

What ships with it

Read from the repository

Just SKILL.md. No reference files, no scripts.

Gives 0 of the 12 instructions most audit compliance skills give in 939 tokens

Counted across 937 of the 1,487 authors here whose files we hold, read 2026-08-07

  • Fetch latest guidelines before each reviewin 43 of 937, across 3 files
  • Group findings by severityin 43 of 937
  • Check files against all fetched rulesin 42 of 937, across 2 files
  • Output findings in terse file:line formatin 41 of 937, across 3 files
  • Ask user which files to review if none specifiedin 41 of 937, across 3 files
  • Read specified files or prompt user for filesin 39 of 937, across 1 file
  • Generate the audit reportin 33 of 937, across 30 files
  • Assign a severity to every findingin 25 of 937
  • Run automated accessibility scansin 23 of 937, across 13 files
  • Output a markdown audit reportin 22 of 937
  • Map findings to WCAG criteriain 20 of 937, across 10 files
  • Confirm audit scopein 19 of 937, across 9 files

Said here and by no other author read

  • Save target article URLs into a CSV file
  • Restrict evaluation to article top to first h2
  • Check URLs in parallel
  • Limit concurrent connections to avoid errors
  • Decode response bytes as UTF-8
  • Separate OTHER_CTA and NO_CTA when prioritizing

Grouped from the skills themselves: near-identical wordings counted once, and counted by distinct author, so one author publishing three of these counts once. Length counted with cl100k_base; the agent that loads this file may tokenize it differently.

Keep looking

Skills are one crate of 326,834. Ordering is by how many stacks a row turns up in, so the top of any crate is what has actually been picked rather than what has the most stars.