메뉴
Fetch a URL or convert a local file (PDF/DOCX/HTML/etc.) into Markdown using `uvx markitdown`, optionally it can summarize
Codex 또는 Claude로 설치 이 Prompt를 복사해 Codex, Claude 또는 다른 어시스턴트에 붙여 넣으면 Skill 페이지를 검토하고 설치를 진행할 수 있습니다.
| name | summarize |
| description | Fetch a URL or convert a local file (PDF/DOCX/HTML/etc.) into Markdown using `uvx markitdown`, optionally it can summarize |
| disable-model-invocation | true |
Turn “things” (URLs, PDFs, Word docs, PowerPoints, HTML pages, text files, etc.) into Markdown so they can be inspected/quoted/processed like normal text.
markitdown can fetch URLs by itself; this skill mainly wraps it to make saving + summarizing convenient. For PDF inputs, use the markitdown[pdf] extra (or the wrapper below, which now does this automatically).
Use this skill when you need to:
Run from this skill folder (the agent should cd here first):
uvx --from 'markitdown[pdf]' markitdown <url-or-path>
To write Markdown to a temp file (prints the path) use the wrapper:
node to-markdown.mjs <url-or-path> --tmp
Tip: when summarizing, the script will always write the full converted Markdown to a temp .md file and will always print a final "Hint" line with the path (so you can open/inspect the full content).
Write Markdown to a specific file:
uvx --from 'markitdown[pdf]' markitdown <url-or-path> > /tmp/doc.md
Summaries are only useful when you provide what you want extracted and the audience/purpose.
node to-markdown.mjs <url-or-path> --summary --prompt "Summarize focusing on X, for audience Y. Extract Z."
Or:
node to-markdown.mjs <url-or-path> --summary --prompt "Focus on security implications and action items."
This will:
uvx --from 'markitdown[pdf]' markitdown.md file and print its path as a "Hint" linepi --model claude-haiku-4-5 (no-tools, no-session) to summarize using your extra promptSOC 직업 분류 기준
Know how Pi model selection is configured and changed: default model, thinking level, one-off model switches, Ctrl+P scoped model cycling, and prompt-editor modes for this repo.
Browser automation with persistent page state. Use when users ask to navigate websites, fill forms, take screenshots, extract web data, test web apps, or automate browser workflows. Trigger phrases include "go to [url]", "click on", "fill out the form", "take a screenshot", "scrape", "automate", "test the website", "log into", or any browser interaction request.
Interview the user relentlessly about a plan, decision, or idea by asking all independent questions in batches, round by round. Use when the user wants to stress-test their thinking, or uses any 'grill' trigger phrases.
Review a diff, branch, PR, commit, or work-in-progress change along two separate axes: Standards (repo conventions, maintainability, safety) and Spec (does the change implement the originating issue/PRD/request?). Runs focused sub-agents in parallel and reports prioritized, actionable findings side by side. Use when the user wants to review a branch, PR, WIP changes, or asks to "review since X".
Diagnosis loop for hard bugs and performance regressions. Use when the user says "diagnose"/"debug this/find bugs", or reports something broken/throwing/failing/slow.
Read this skill before making git commits
