Skip to content

Interview: Context Refresh

Walks you through stale life-context and TELOS files, checking claims against your own data before proposing edits.

Stars
19,682
Licence
MIT
Files
6 files

What it does

This skill makes an AI agent act as a reflective interviewer over your personal LifeOS files (goals, identity, projects, current and ideal state). It checks how old each claim is, compares claims against observed data such as sleep, git activity, and expenses when those sources are connected, and opens with the sharpest contradiction it finds. It drafts corrections, but only changes a file after you approve that specific edit.

Great for

  • People running the LifeOS personal AI system who want periodic context check-ins
  • Users doing a quarterly refresh of their goals and current situation
  • Anyone setting up a fresh LifeOS install who needs guided configuration

Skip it if

  • Simple one-off edits to a single file, which the skill says belong to the separate Telos skill
  • Users without a LifeOS setup, since the skill depends on its specific files and scripts and would have little to work with
  • Sensitive personal data in shared or public sessions, because the interview draws on health, finance and journal-style records

Try asking

  • “/interview”
  • “what's stale in my TELOS?”
  • “telos check-in”
  • “update my current state”
Step-by-step guide: how to use Interview: Context RefreshInstall, first run, examples, tips and FAQs

Install in 3 steps

  1. 1

    Download the skill

    The ZIP contains the 6 original files, the MIT licence and an attribution note.

    Interview.zip
  2. 2

    Add it to your agent

    Claude Code (all projects)

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

    Claude Code / Agent SDK (this project only)

    mkdir -p .claude/skills && unzip Interview.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

  • Run the routing check or ask 'what's stale?' first to see the priority list before committing to a full interview
  • Review every proposed correction; the skill is designed to edit only after you ratify it
  • Make sure optional data sources are connected if you want evidence-based checks rather than questions alone

What's inside

  • Intents/ContextCheckin.md
  • Intents/Phase0Setup.md
  • Intents/TelosCheckin.md
  • References/ContextCheckinExamples.md
  • Setup.md
  • SKILL.md

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.