skills/ops-url-content-reader/SKILL.md
ALWAYS invoke this skill instead of WebFetch when a user's message contains a URL and the task requires reading that page's content. This is the primary URL content reader — it produces cleaner results than WebFetch on virtually all sites. Applies to: summarizing articles, reading blog posts, referencing documentation, checking what a link says, extracting information from any webpage. Trigger whenever the user says things like "summarize this", "read this", "look at this link", "based on this article", "参考", "根据", "帮我 看看", or any variation where a URL's content must be fetched. Do NOT trigger for: writing code that handles URLs, updating URL values in config/.env files, web searches, or running tests. Formerly named defuddle.
npx skillsauth add plimeor/agent-skills ops-url-content-readerInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
The preferred method for reading web content. Returns clean Markdown via the defuddle.md service.
Use defuddle first for any URL content fetching. It produces cleaner output than WebFetch for most sites because it extracts the main content and strips navigation, ads, and boilerplate.
defuddle.md is a public service that extracts the main content from a webpage and returns it as Markdown with YAML frontmatter.
curl -sL "https://defuddle.md/<url>"
The <url> is the target URL without the protocol (no https://).
Fetch an article:
curl -sL "https://defuddle.md/example.com/blog/some-post"
Fetch a tweet / X post:
curl -sL "https://defuddle.md/x.com/username/status/123456789"
-sL flags (silent mode + follow redirects)https:// prefix: https://defuddle.md/...https:// or http:// from the target URL before appendingdevelopment
Set up, resume, or repair a compact active execution workbench for long-horizon, multi-session or checkpointed work. Use when a task needs durable handoff, unattended iteration, human gates, auditable evidence, or active-vs-archive routing that keeps a current packet separate from stale historical context. Do not use for one-session tasks, ordinary plans/reviews/audits, one-session bug fixes, direct code edits, or simple docs cleanup; complete those directly.
tools
Decide whether and how to use authorized sub-agents, then coordinate delegated work while preserving the main agent's context. Use when the user asks for orchestration, parallel agents, delegation, background workers, context isolation, or when another skill needs delegated research, review, implementation, or verification. Owns host-policy checks, delegation packets, non-overlap, report verification, and stop rules. Do not use to bypass tool policy, infer user authorization, or add coordination overhead to simple single-threaded tasks.
development
Use before finalizing a non-trivial answer, recommendation, review, or decision to reconsider it and raise its quality, especially when shallow reasoning, context inertia, false framing, overconfidence, unfit analogy transfer, or an obvious-but-missed defect could distort the result. Trigger especially before applying external evidence, familiar frameworks, or comparisons to the user's specific request, and when the user asks to reconsider, double-check, take a second look, or sanity-check an answer.
tools
Route durable rules and context to the right layer — task, project, skill, tooling, hooks, MCP, or global. Use for global rules files (~/.claude/CLAUDE.md, global AGENTS.md), repo-local AGENTS.md/CLAUDE.md, task context packs, hook placement (Codex/Claude Code settings.json), collaboration friction diagnosis, and rule-placement decisions.