summarize · serhiikorniienko — Claude Code skill: what it does, how to install
Turns a video, article, thread, or PDF into a structured summary with key points, location markers, quotes, and guidance on who should read or watch the full source.
npx skills add SerhiiKorniienko/bullshit-detector --skill summarize -a claude-codeWhat summarize does
The skill retrieves text from a link or file, reads it through, then builds a summary with a central takeaway, key points linked to timestamps or page numbers, notable quotes, and a note on who benefits from the full source. If fetch-content is installed, it uses that skill’s script for URLs; otherwise the agent can use a web-fetch tool or ask you to paste the text.
The length follows the source: a short thread gets a few lines, while a long podcast calls for a fuller account. It retains every item in a list-shaped source and carries over names, figures, and claims without rounding. If the agent cannot retrieve the linked text, it will need you to provide it.
What it helps with
- condense a video into points with timestamps
- pull an article’s main claims and notable quotes
- summarize a PDF with page references
- decide who needs the full version
Example prompts for the agent
- Summarize this video: [link]
- Summarize
report.pdfwith its main point and page references - Give me the key points from this thread and say who should read the full version
How to install summarize
1Skills CLI (Vercel)
npx skills add SerhiiKorniienko/bullshit-detector --skill summarize -a claude-code2Manually: put the files in place
~/.claude/skills/summarize/SKILL.mdCopy the whole skill folder; for one project use .claude/skills/summarize/
1Skills CLI (Vercel)
npx skills add SerhiiKorniienko/bullshit-detector --skill summarize -a codex2Manually: put the files in place
.agents/skills/summarize/SKILL.mdFor all projects use ~/.agents/skills/
1Skills CLI (Vercel)
npx skills add SerhiiKorniienko/bullshit-detector --skill summarize -a cursor2Manually: put the files in place
.cursor/skills/summarize/SKILL.mdCursor also reads .agents/skills/ and .claude/skills/
1GitHub CLI
gh skill install SerhiiKorniienko/bullshit-detector summarize2Manually: put the files in place
.github/skills/summarize/SKILL.md1Skills CLI (Vercel)
npx skills add SerhiiKorniienko/bullshit-detector --skill summarize -a gemini-cli2Platform CLI
gemini skills install https://github.com/SerhiiKorniienko/bullshit-detector --path skills/analysis/summarizeManually: put the files in place
.devin/skills/summarize/SKILL.mdThe legacy .windsurf/skills/ path still works
Skills CLI (Vercel)
npx skills add SerhiiKorniienko/bullshit-detector --skill summarize -a opencodeClaude.ai
Zip the folder and upload it in Settings → Capabilities → Skills
Step by step, with commands for each platform: How to install skills in Claude Code: five ways
Questions about summarize
How do I install summarize in Claude Code?
Run npx skills add SerhiiKorniienko/bullshit-detector --skill summarize -a claude-code. The skill file is at ~/.claude/skills/summarize/SKILL.md.
What does summarize do?
It creates a structured account of a video, article, thread, or PDF, with a central takeaway, linked key points, quotes, and guidance on who should read or watch the original.
How does summarize retrieve text from a URL?
When fetch-content is installed, the skill uses its script. Otherwise, the agent can use a web-fetch tool or ask you to paste the text.
Source text
SKILL.md · MIT
--- name: summarize description: Produce a structured summary of a video, article, tweet thread, or PDF — TLDR, key points with timestamps/locations, notable quotes, and who should read/watch it. Use when the user asks to summarize a link or file, wants a TLDR, or asks "what does this video/article say" / "is this worth watching". --- # summarize Give someone the content without the runtime. ## Workflow 1. **Get the text.** If the input is a URL and the `fetch-content` skill is installed, use its script; otherwise use your web fetch tool or ask for a paste. Keep the metadata. 2. **Read fully**, then write: ```markdown # <title> **<author> · <platform> · <date> · <duration/length> · <views if notable>** **TLDR:** one paragraph, ≤3 sentences — the actual thesis, not the topic. ## Key points Bulleted. Each point = one idea, with [timestamp] or [p.N] so the reader can jump to it. Preserve the content's own structure (if it promises "14 ways", list all 14 — compressed, not truncated). ## Notable quotes 1–3 verbatim quotes that carry the content's voice, with locations. ## Worth your time? One honest sentence per audience: who gains from the full version, who is fine with this summary. ``` ## Rules - Summarize what the content says, not what you think of it (that's the `bullshit-detector` skill — mention it if the content smells hyped, don't perform its job here). - Numbers, names, and claims must come from the content verbatim — no rounding, no "improving". - If the content is listicle-shaped, the summary must contain the complete list. Never "...and 9 more ways". - Scale length to source: a tweet gets 3 lines, a 3-hour podcast gets a full page.
© SerhiiKorniienko · MIT · SerhiiKorniienko/bullshit-detector
Similar skills
SKILL.md skills catalog →summarize by other authors comes first.