菜单
Refreshes the production website from the repository's year-list Markdown, archive manifest, and year registry. Use when a finalized year list, preliminary *-ai collection, preserved reference, original listing, or generated website collection changes, or when the archive UI appears stale.
默认使用会先检查来源的 Prompt；你也可以切换为直接命令，或下载本地副本。
决定是否安装前，请先阅读 SKILL.md，以及 SkillsMP 当前展示的配套文件。
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
直接命令不会经过审查 Prompt；运行前请先检查来源。
npx skills add https://github.com/irsdl/webhacklist --skill webseclist-refresh-web-apps命令会保持在同一行。复制前请横向滚动并检查完整内容。
想先保存到本地？可下载 SkillsMP 当前能够提供的文件。
Builds or refreshes the Markdown-plus-PDF archive of resources cited by finalized Top 10 Web Hacking Techniques lists and bounded YYYY-ai.md preliminary collections, under archived-references/md/COLLECTION/ and archived-references/pdf/COLLECTION/. Use when a finalized or AI-generated list changes, a cited source needs preservation or repair, preliminary citations must be promoted or pruned when the real list arrives, or a review/validation queue needs work. This workflow reads source lists and never edits them.
Reviews and repairs references already published in the Top 10 Web Hacking Techniques Markdown-and-PDF archive. Use for one article, one collection such as 2019 or YYYY-ai, or a bounded period when asked to audit, validate, verify, QA, sanity-check or proofread archived references; investigate wrong-page captures, gibberish, damaged PDF text, bad titles, missing or wrong figures, missing document-derived bylines, broken or stale PDFs, missing or orphaned files, stale metadata, Markdown that renders wrong such as an unrecognised or unclosed code fence, a mangled code listing or a broken table, or a website footer, comments, related posts, subscribe pitch or other publisher tail left after the article. Also use before a release or website rebuild. Do not use for new or never-archived citations (webseclist-archive-references), removal (webseclist-remove-reference), a credit supplied by the user (webseclist-credit-author), research-value judgement (webseclist-judge-reference), or announcement snapshots (webseclis
Evaluates a candidate web-security research reference for genuine novelty at the time it first became public and for lasting usefulness, independently re-verifies every result, then decides whether to preserve it in the archive as a core technique, a supporting reference, or not at all. Produces a critical but fair, evidence-based scorecard across six weighted categories plus a verdict. Use whenever someone asks whether a blog post, paper, talk, advisory, tool, or writeup is NEW, ORIGINAL, WORTH KEEPING, ALREADY KNOWN, a DUPLICATE, or "just a rediscovery"; when triaging a nominee or a newly cited source for archived-references/; when comparing a finding against prior art; or when asked to score, rank, grade, or judge the research value of a web/API/HTTP security technique. Do NOT use it to fetch or convert sources into the archive (that is webseclist-archive-references) or to snapshot announcement pages (that is webseclist-archive-listings) - this skill only judges research value and never edits a year list.
基于 SOC 职业分类
正在显示 SKILL.md
| name | webseclist-refresh-web-apps |
| description | Refreshes the production website from the repository's year-list Markdown, archive manifest, and year registry. Use when a finalized year list, preliminary *-ai collection, preserved reference, original listing, or generated website collection changes, or when the archive UI appears stale. |
Read ../../../.claude/skills/webseclist-refresh-web-apps/SKILL.md completely,
then follow it as the canonical workflow for this skill.
Resolve every relative path mentioned by that file from
.claude/skills/webseclist-refresh-web-apps/, including paths under
references/, scripts/, and assets/.
Keep the workflow and its supporting resources in .claude/skills/; this
adapter exists only to make the same skill discoverable by Codex.
