Other

Interview

Refreshes TELOS and current-state claims against observed evidence (Oura, Conduit, git, expenses) and drafts corrections for ratification

Workflows

Tools

Reference

Triggers

The Problem

A fresh AI session doesn't know your goals, your projects, or how your thinking has shifted since the last time you talked. You can paste in context manually every time, but it goes stale, and the model has no way to tell which parts are still true. After a few weeks, your TELOS file drifts from reality — sections you've moved past stay current, constraints you've resolved never get updated, and the DA keeps optimizing for a version of you from three months ago.

How This Skill Approaches It

Interview reads seven constitutional files (TELOS, DA_IDENTITY, PRINCIPAL_IDENTITY, PROJECTS, system prompt, PRINCIPAL_TELOS, ARCHITECTURE_SUMMARY) and checks them against staleness thresholds via TelosFreshness. A routing decision runs first: if the scan finds Phase 0 targets with completeness below 80 (DA name still 'LifeOS', identity still 'User', projects still sample rows), it runs Phase0Setup to get the system grounded before doing anything else. For populated installs, it runs ContextCheckin — surfacing the stalest sections by age and driving a focused peer conversation: one entry at a time, per typed ID on structured sections (G3, M0, P2), section-level on prose. Stop signals ('enough', 'later') exit cleanly; every approved edit bumps the freshness timestamp via TelosFreshness.ts so the staleness signal stays accurate. ContextAudit surfaces TBD markers left in files. The whole thing is a context debt payment, not a form fill.

Not for single edits (Telos), bulk intake (Migrate), identity-only

In Action

What you say to your DA, and what the Interview skill actually does.

You say "/interview"

Runs InterviewScan.ts to detect whether the system is freshly installed or populated, routes to Phase0Setup (if DA name/identity are still defaults) or ContextCheckin (if the system is live), then surfaces the stalest TELOS sections and drives a focused conversation to update them one at a time.
You say "what's stale in my context"

Runs ContextCheckin via TelosFreshness — reads all seven constitutional files, computes age per section, surfaces the ones past their staleness threshold, and opens a peer conversation about whether each item still holds rather than asking you to restate everything from scratch.

Inside the Skill

The thinking, frameworks, and architecture that distinguish this skill from a generic version of the same task.

Ideal State

Every prompt argues from what is already on file and from observed data: the files are read first, and a claim is checked against evidence or named as unchecked, never replaced by a blank "what's your mission?".
Staleness is treated as a priority signal, not a failure: the conversation leads with the sharpest contradiction or the stalest item and asks "still right?".
Nothing in a claims file changes without the principal ratifying that specific edit, and every reviewed item leaves its freshness marker bumped, so the 🎤 chip clears only when the agenda is actually done.
A fresh install is configured end to end (identity, voice, credentials, first project, work repo) before any check-in runs.

Intent Routing

Intent	Trigger	File
ContextCheckin	default `/interview` on a populated system; "context check-in", "telos check-in", "what's stale", "how are we doing on…", "still on…", "review context"	`Intents/ContextCheckin.md`
Phase0Setup	fresh install; `LIFEOS_CONFIG.toml` still holds the scaffold names (DA `Aria`, principal `Your Name`); PROJECTS sample-row only; `.env` missing required keys	`Intents/Phase0Setup.md`
TelosCheckin (deprecated stub)	back-compat for explicit "telos checkin" routing	`Intents/TelosCheckin.md` (redirects to ContextCheckin)

File	Read when
`ISA.md`	changing how the interview works: the skill's own ISA (evidence-grounded state freshness); `ISA.html` is its rendered page
`Setup.md`	first-time setup: the optional PREFERENCES.md key and a read-only proof
`References/ContextCheckinExamples.md`	shaping a ContextCheckin opening or per-entry prompt and wanting a worked run (stale system prompt, all-fresh with an audit finding, a Goals walk with its bump)

Routing decision (run before either intent):

bun ~/.claude/LIFEOS/TOOLS/InterviewScan.ts --json | jq '[.targets[] | select(.phase == 0 and .completeness_score < 80)] | length'

> 0 → run Phase0Setup first, then ContextCheckin.
0 → run ContextCheckin directly.

Data & Config

User customizations live at <configRoot>/LIFEOS/USER/CUSTOMIZATIONS/SKILLS/Interview/ (configRoot is $CLAUDE_CONFIG_DIR when set, else ~/.claude). PREFERENCES.md § State check-in priority names the journal dimension the wrap asks first (absent: equal weight). History.md, when present, holds this install's own interview history; it is reference, never read at run time. First-time setup and every key: Setup.md.

Gotchas

The current.json day-label trap. USER/HEALTH/current.json labels itself with today's day while its last_night block may carry the newest available sleep record, days older. Quote the evidence cache's latest_sleep_record_day, never the label.
Not every health source is live. The evidence panel (StateEvidence.ts) computes per-source liveness at run time — quote its live/dead map, never a remembered one. Claims whose only source is dead can be asked, not checked — say so instead of implying verification.
InterviewDue.ts --mark-done at wrap is what silences the 🎤 statusline chip. Skipping it leaves the chip nagging with the interview already done — the cadence clock reads MEMORY/STATE/interview.json, not file mtimes.
A file without the freshness frontmatter reads as stale. TELOS and the constitutional files each need a one-time migration first; the commands and the ask-first rule are in Intents/ContextCheckin.md § Safety gates.
The slug is normalized: "Current State" → current_state, "Wrong (Things I've been wrong about)" → wrong, "2036 — A Day in the Life…" → 2036. Always run heading text through sectionSlug() from TelosFreshness.ts.
Pulse caches freshness for 60s. After bumping, the next /api/telos/freshness/summary call returns the cached value until invalidation. POST /api/freshness/invalidate clears it immediately, or wait 60s.
TelosRenderer (GenerateTelosSummary.ts) preserves the markers. It splits by ^## headings; the per-section HTML comments live inside the section body and are not re-emitted in PRINCIPAL_TELOS.md. Safe to run after edits.
The scanner shares the freshness reader. InterviewScan.ts calls readTelosFreshness() once at startup and adds age_days, threshold_days, stale to every Phase 1+ target row. Stale sections get a +200 priority bump so they naturally rise in --next output.
Voice notifications are "only on actual writes." Don't voice-confirm every prompt — only after a real Edit lands. The voice channel is a low-frequency signal; preserving that is what makes it land when it matters.

Examples

"/interview" on a populated system → routing probe via InterviewScan.ts, then ContextCheckin walking the stalest sections first ("G2 is 95 days old — still right?").
"what's stale?" → freshness summary from TelosFreshness, prioritized list, no edits unless approved.
Fresh install (DA name still the scaffold Aria, PROJECTS sample-row only) → Phase0Setup first, then ContextCheckin.

/Telos — edit a single TELOS section directly (without the conversational walk).
/Migrate — intake content from other sources (one-shot classification, not an interview).
an identity-profile skill — manage PRINCIPAL_IDENTITY directly.
Skill("ISA") — interview an ISA (different artifact, different intent).

Workflows & Routing · 3

Each workflow is one job the skill runs. The trigger phrases route your request to the right one — this is the skill's routing table.

01

ContextCheckin Intents/ContextCheckin.md

default /interview on a populated system; context check-in, telos check-in, whats stale, how are we doing on…, still on…, review context
02

Phase0Setup Intents/Phase0Setup.md

fresh install; LIFEOS_CONFIG.toml still holds the scaffold names (DA Aria, principal Your Name); PROJECTS sample-row only; .env missing required keys
03

TelosCheckin *(deprecated stub)* Intents/TelosCheckin.md` (redirects to ContextCheckin)

back-compat for explicit telos checkin routing

How to Invoke

Say any of these to your DA and LifeOS activates the Interview skill automatically:

"/interview"
"resume interview"
"context check-in"
"telos check-in"
"what's stale"
"stale data"
"freshness check"
"update current state"
"update my current state"
"state sync"
"statusline says interview due"
"interview due"
"review TELOS"
"update ideal state"

Or invoke explicitly:

Skill("Interview")

References · 1

Auxiliary files the skill loads at runtime — frameworks, guides, configs.

Setup

Related Skills

Want LifeOS to do this for you?

Install LifeOS on your machine — your DA gets the Interview skill plus 96 others, all hooked into one Life OS.

Install LifeOS View on GitHub