Skip to content
Get packs

LifeOS Upgrade Scout

Finds evidence-backed improvements for an AI system from Anthropic releases, practitioner techniques and news, filtering out ideas already adopted

Source Download skill
Repository
danielmiessler/LifeOS
Stars
19,682
Licence
MIT
Files
13 files

What it does

Once installed, the agent periodically checks Anthropic's blogs, changelogs, GitHub releases and docs, plus optional YouTube channels and GitHub trending repos, for new techniques that could improve a LifeOS setup. It compares each idea against the system's current files and past rejected decisions so it does not re-recommend work already done, and it ranks what remains with cited sources. It can also keep model references current, write a sourced AI news digest, and mine the system's own reflection logs for weaknesses.

Great for

  • Developers who maintain a LifeOS (or similar Claude Code personal AI infrastructure) and want a regular upgrade review
  • Teams that want a sourced digest of Anthropic changes and their impact on existing skills and hooks
  • Maintainers who want to check which model IDs in their configuration are outdated

Skip it if

  • Users who only want to mine a single article or video; the skill's own description routes that elsewhere (Harvest), so it is the wrong tool for one-off content extraction
  • Anyone expecting it to apply changes automatically; its output is recommendations that need human review, and its manual review step is required by the skill itself
  • Security news monitoring; the description says that belongs to a separate SecurityUpdates skill

Try asking

  • “Check Anthropic for new Claude features and tell me which ones matter for our LifeOS setup”
  • “Run an upgrade sweep and list tiered recommendations with sources”
  • “Are we on the latest Claude models? Check model freshness across our agents”
  • “Give me a sourced digest of what changed in AI this week and what it means for us”
Step-by-step guide: how to use LifeOS Upgrade ScoutInstall, first run, examples, tips and FAQs

Install in 3 steps

  1. 1

    Download the skill

    The ZIP contains the 13 original files, the MIT licence and an attribution note.

    Upgrade.zip
  2. 2

    Add it to your agent

    Claude Code (all projects)

    mkdir -p ~/.claude/skills && unzip Upgrade.zip -d ~/.claude/skills/

    Claude Code / Agent SDK (this project only)

    mkdir -p .claude/skills && unzip Upgrade.zip -d .claude/skills/

    Claude apps (web/desktop): Settings → Capabilities → Skills → Upload skill, and choose the ZIP.

  3. 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

  • Read the sweep report's Sources Processed section first; any skipped or timed-out source lowers coverage, so a short report does not mean nothing changed
  • Before adopting a recommendation, check the cited file:line evidence and run the backward-compatibility check it describes, since the skill itself asks for this
  • Configure optional sources (YouTube channels, GitHub trending queries, custom blogs) in your user customization folder so the lanes reflect your interests

What's inside

  • Intents/AlgorithmUpgrade.md
  • Intents/FindSources.md
  • Intents/MineReflections.md
  • Intents/Models.md
  • Intents/NewsDigest.md
  • Intents/ResearchUpgrade.md
  • Intents/Upgrade.md
  • References/ExampleReport.md
  • References/OutputFormat.md
  • Setup.md
  • SKILL.md
  • sources.json
  • Tools/Anthropic.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.