
Pareto Topic Sweep
Sweeps YouTube, GitHub and the web on a topic and reports past, current and frontier thinking with links.
- Repository
- danielmiessler/LifeOS
- Stars
- 19,682
- Licence
- MIT
- Files
- 9 files
What it does
When you ask about a topic, this skill makes the agent search YouTube, GitHub and the web, then filter the results down to the most relevant few by relevance, reach, recency and how unusual they are. It then writes a report covering how thinking on the topic used to be, what the mainstream thinks now, and where forward-thinking people seem to be heading, with links for each claim. Sources that fail or hit quota limits are noted rather than stopping the run.
Great for
- People who want a quick, linked overview of what is current and who to follow on a topic
- Researchers or analysts scanning a fast-moving field before a deeper dive
- Anyone who already has YouTube, GitHub and Perplexity access set up and wants repeatable sweeps
Skip it if
- Answering a specific factual question, where the Research skill is a better fit (the skill's own description says so)
- Analysing a single article or video in depth, which another skill covers; it also cannot judge content it has not collected
- Software-category searches without care: GitHub results can include cracked-software lure repos that look like malware bait, so review any linked repo before opening it
Try asking
- “Pareto agentic coding”
- “What's the zeitgeist on personal AI infrastructure?”
- “Where are the big thinkers going on local LLM inference?”
- “Who are the forward thinkers on 3D modeling software?”
Install in 3 steps
- 1
Download the skill
The ZIP contains the 9 original files, the MIT licence and an attribution note.
Pareto.zip - 2
Add it to your agent
Claude Code (all projects)
mkdir -p ~/.claude/skills && unzip Pareto.zip -d ~/.claude/skills/Claude Code / Agent SDK (this project only)
mkdir -p .claude/skills && unzip Pareto.zip -d .claude/skills/Claude apps (web/desktop): Settings → Capabilities → Skills → Upload skill, and choose the ZIP.
- 3
Ask for the task
No special command needed — the agent reads the skill's description and loads it when your request matches. Try one of the prompts above.
Get better results
- Phrase topics as a category (for example '3D modeling software') rather than a judgment like 'best 3D modeling system', because loose words match too much content.
- Run Setup.md first to confirm each source works with a small read-only sweep, and keep an eye on the YouTube daily quota (about 25 full runs per day).
- Check that a generated report's frontier section names people you recognise as genuinely ahead of the mainstream, and read any source marked as failed or unread.
What's inside
- Intents/Run.md
- Setup.md
- SKILL.md
- Tools/Check.help.md
- Tools/Check.ts
- Tools/Collect.help.md
- Tools/Collect.ts
- Tools/Rank.help.md
- Tools/Rank.ts
Redistributed unmodified from danielmiessler/LifeOS under the MIT licence. The assessment was drafted with AI from the skill's files on 2026-10-29. Skills can instruct your agent to run code — read SKILL.md and any scripts before installing.