Evidence-Grounded Context Refresh

Interview

by danielmiessler · MIT license · ★ 19,269 on GitHub · v1.1.13

Interview cover

Evidence-grounded context refresh: reads constitutional files, TELOS, and CURRENT_STATE/IDEAL_STATE dimension files via TelosFreshness, pulls observed data (Oura sleep/HRV, Conduit app-time, work registry, git, expenses via…

---
name: Interview
version: 1.1.13
description: "Evidence-grounded context refresh: reads constitutional files, TELOS, and CURRENT_STATE/IDEAL_STATE dimension files via TelosFreshness, pulls observed data (Oura sleep/HRV, Conduit app-time, work registry, git, expenses via StateEvidence), and drives a peer conversation that opens with claim-vs-evidence contradictions, drafts corrections for ratification, and closes with a ComputeGap-grounded ideal-state review. Routes to ContextCheckin; Phase0Setup on fresh install. USE WHEN /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, quarterly context refresh, fresh LifeOS install, configure DA name. NOT FOR single edits (Telos), bulk intake (Migrate), identity-only."
disable-model-invocation: true
---

# Interview — constitutional-context peer conversation

## What It Does

Interview reads your constitutional files — TELOS, identity, projects, system prompt, architecture — plus the CURRENT_STATE and IDEAL_STATE dimension files, checks their freshness, and confronts stale claims with observed data: Oura sleep/HRV/RHR, Conduit creation-vs-consumption time, the work registry, git cadence, and the expense ledger. The conversation opens with the sharpest claim-vs-evidence contradiction, drafts corrections you ratify, offers to populate the files the machinery can write, and closes with an ideal-state review grounded in the measured gap. On a fresh install it falls back to first-time setup. The 🎤 statusline chip (fed by `InterviewDue.ts`, daily launchd refresh) says when one is due; wrapping with `--mark-done` clears the cadence reason, and the skew/staleness reasons clear as their files are actually reviewed.

## The Problem

The files that define who you are and what you're working toward drift out of date the moment you stop looking at them. A goal you set in January may be done, dead, or still right — but nobody re-reads the whole TELOS to find out, so the context the system runs on slowly rots. The usual fix is a blank "what's your mission?" prompt, which ignores everything already on file and makes you repeat yourself. This skill reads what's there first, flags only what's gone stale, and asks "still right?" instead of starting from zero.

## How It Works

Overview

Interview reads your constitutional files — TELOS, identity, projects, system prompt, architecture — plus the CURRENT_STATE and IDEAL_STATE dimension files, checks their freshness, and confronts stale claims with observed data: Oura sleep/HRV/RHR, Conduit creation-vs-consumption time, the work registry, git cadence, and the expense ledger. The conversation opens with the sharpest claim-vs-evidence contradiction, drafts corrections you ratify, offers to populate the files the machinery can write, and closes with an ideal-state review grounded in the measured gap. On a fresh install it falls back to first-time setup. The 🎤 statusline chip (fed by InterviewDue.ts, daily launchd refresh)…

Manual install (npx, ZIP)
Claude Codenpx skills add danielmiessler/LifeOS --skill Interview -g -a claude-code
Claude Code (degit)npx degit danielmiessler/LifeOS/LifeOS/install/skills/Interview#main ~/.claude/skills/interview-danielmiessler
Claude.ai / desktopZip the folder and upload it under Settings → Capabilities → Skills.
Codex, Cursor, other agentsPoint them at SKILL.md. The other files are plain text.

Connects with Agent Alley MCP · agentalley.io/mcp

Files included

  • SKILL.md7.3 KB
Read SKILL.md here
danielmiessler/main1 file shown
SKILL.md
Show the full text72 lines

Interview — constitutional-context peer conversation

What It Does

Interview reads your constitutional files — TELOS, identity, projects, system prompt, architecture — plus the CURRENT_STATE and IDEAL_STATE dimension files, checks their freshness, and confronts stale claims with observed data: Oura sleep/HRV/RHR, Conduit creation-vs-consumption time, the work registry, git cadence, and the expense ledger. The conversation opens with the sharpest claim-vs-evidence contradiction, drafts corrections you ratify, offers to populate the files the machinery can write, and closes with an ideal-state review grounded in the measured gap. On a fresh install it falls back to first-time setup. The 🎤 statusline chip (fed by InterviewDue.ts, daily launchd refresh) says when one is due; wrapping with --mark-done clears the cadence reason, and the skew/staleness reasons clear as their files are actually reviewed.

The Problem

The files that define who you are and what you're working toward drift out of date the moment you stop looking at them. A goal you set in January may be done, dead, or still right — but nobody re-reads the whole TELOS to find out, so the context the system runs on slowly rots. The usual fix is a blank "what's your mission?" prompt, which ignores everything already on file and makes you repeat yourself. This skill reads what's there first, flags only what's gone stale, and asks "still right?" instead of starting from zero.

How It Works

The skill reads the constitutional files via the freshness tooling, scores each section's staleness, and routes to the right workflow — a check-in on a populated system, or first-time setup on a fresh one. Staleness is a priority signal, not a failure flag.

Workflow Routing

Workflow 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" Workflows/ContextCheckin.md
Phase0Setup fresh install; DA name still reads "LifeOS"; PRINCIPAL_IDENTITY still reads "User"; PROJECTS sample-row only; .env missing required keys Workflows/Phase0Setup.md
TelosCheckin (deprecated stub) back-compat for explicit "telos checkin" routing Workflows/TelosCheckin.md (redirects to ContextCheckin)

Routing decision (run before either workflow):

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.

Quick Reference

  • The TELOS is on file. Read it before asking. Generic "what's your mission?" prompts are forbidden when TELOS is populated.
  • Staleness is information, not failure — a 95-day-old Goals section might still be right; the prompt is "still right?", not "you're behind."
  • Per-entry on typed-ID sections (G3, M0, P2…), section-level on prose (Current State, Sparks).
  • Bump on every approved edit: bun ~/.claude/LIFEOS/TOOLS/TelosFreshness.ts --bump <slug>. Without this the staleness signal degrades to noise.
  • Stop signals are sacred. "Enough" / "stop" / "later" exits gracefully. State persists in the file itself.
  • ID-stability rule: G3 stays G3 even when edited or dropped; new entries get the next sequential ID.

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.
  • Migration must run once before TelosCheckin works. A TELOS without YAML frontmatter (no last_updated:) returns fileUpdated: null and every section reads as stale. Run bun ~/.claude/LIFEOS/TOOLS/MigrateTelosFreshness.ts once; idempotent and content-preserving (verifies sha256 of stripped content).
  • 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. Send /reload (POST) to invalidate the cache 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 "LifeOS", 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 workflow).
1---
2name: Interview
3version: 1.1.13
4description: "Evidence-grounded context refresh: reads constitutional files, TELOS, and CURRENT_STATE/IDEAL_STATE dimension files via TelosFreshness, pulls observed data (Oura sleep/HRV, Conduit app-time, work registry, git, expenses via StateEvidence), and drives a peer conversation that opens with claim-vs-evidence contradictions, drafts corrections for ratification, and closes with a ComputeGap-grounded ideal-state review. Routes to ContextCheckin; Phase0Setup on fresh install. USE WHEN /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, quarterly context refresh, fresh LifeOS install, configure DA name. NOT FOR single edits (Telos), bulk intake (Migrate), identity-only."
5disable-model-invocation: true
6---
7 
8# Interview — constitutional-context peer conversation
9 
10## What It Does
11 
12Interview reads your constitutional files — TELOS, identity, projects, system prompt, architecture — plus the CURRENT_STATE and IDEAL_STATE dimension files, checks their freshness, and confronts stale claims with observed data: Oura sleep/HRV/RHR, Conduit creation-vs-consumption time, the work registry, git cadence, and the expense ledger. The conversation opens with the sharpest claim-vs-evidence contradiction, drafts corrections you ratify, offers to populate the files the machinery can write, and closes with an ideal-state review grounded in the measured gap. On a fresh install it falls back to first-time setup. The 🎤 statusline chip (fed by `InterviewDue.ts`, daily launchd refresh) says when one is due; wrapping with `--mark-done` clears the cadence reason, and the skew/staleness reasons clear as their files are actually reviewed.
13 
14## The Problem
15 
16The files that define who you are and what you're working toward drift out of date the moment you stop looking at them. A goal you set in January may be done, dead, or still right — but nobody re-reads the whole TELOS to find out, so the context the system runs on slowly rots. The usual fix is a blank "what's your mission?" prompt, which ignores everything already on file and makes you repeat yourself. This skill reads what's there first, flags only what's gone stale, and asks "still right?" instead of starting from zero.
17 
18## How It Works
19 
20The skill reads the constitutional files via the freshness tooling, scores each section's staleness, and routes to the right workflow — a check-in on a populated system, or first-time setup on a fresh one. Staleness is a priority signal, not a failure flag.
21 
22## Workflow Routing
23 
24| Workflow | Trigger | File |
25|----------|---------|------|
26| **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" | `Workflows/ContextCheckin.md` |
27| **Phase0Setup** | fresh install; DA name still reads "LifeOS"; PRINCIPAL_IDENTITY still reads "User"; PROJECTS sample-row only; `.env` missing required keys | `Workflows/Phase0Setup.md` |
28| **TelosCheckin** *(deprecated stub)* | back-compat for explicit "telos checkin" routing | `Workflows/TelosCheckin.md` (redirects to ContextCheckin) |
29 
30**Routing decision (run before either workflow):**
31 
32```bash
33bun ~/.claude/LIFEOS/TOOLS/InterviewScan.ts --json | jq '[.targets[] | select(.phase == 0 and .completeness_score < 80)] | length'
34```
35 
36- `> 0` → run **Phase0Setup** first, then ContextCheckin.
37- `0` → run **ContextCheckin** directly.
38 
39## Quick Reference
40 
41- The TELOS is on file. **Read it before asking.** Generic "what's your mission?" prompts are forbidden when TELOS is populated.
42- Staleness is **information, not failure** — a 95-day-old Goals section might still be right; the prompt is "still right?", not "you're behind."
43- **Per-entry on typed-ID sections** (G3, M0, P2…), **section-level on prose** (Current State, Sparks).
44- **Bump on every approved edit:** `bun ~/.claude/LIFEOS/TOOLS/TelosFreshness.ts --bump <slug>`. Without this the staleness signal degrades to noise.
45- **Stop signals are sacred.** "Enough" / "stop" / "later" exits gracefully. State persists in the file itself.
46- **ID-stability rule:** G3 stays G3 even when edited or dropped; new entries get the next sequential ID.
47 
48## Gotchas
49 
50- **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.
51- **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.
52- **`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.
53- **Migration must run once before TelosCheckin works.** A TELOS without YAML frontmatter (no `last_updated:`) returns `fileUpdated: null` and every section reads as stale. Run `bun ~/.claude/LIFEOS/TOOLS/MigrateTelosFreshness.ts` once; idempotent and content-preserving (verifies sha256 of stripped content).
54- **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`.
55- **Pulse caches freshness for 60s.** After bumping, the next `/api/telos/freshness/summary` call returns the cached value until invalidation. Send `/reload` (POST) to invalidate the cache immediately, or wait 60s.
56- **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.
57- **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.
58- **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.
59 
60## Examples
61 
62- "/interview" on a populated system → routing probe via `InterviewScan.ts`, then ContextCheckin walking the stalest sections first ("G2 is 95 days old — still right?").
63- "what's stale?" → freshness summary from TelosFreshness, prioritized list, no edits unless approved.
64- Fresh install (DA name still "LifeOS", PROJECTS sample-row only) → Phase0Setup first, then ContextCheckin.
65 
66## Related
67 
68- `/Telos` — edit a single TELOS section directly (without the conversational walk).
69- `/Migrate` — intake content from other sources (one-shot classification, not an interview).
70- an identity-profile skill — manage PRINCIPAL_IDENTITY directly.
71- `Skill("ISA")` — interview an ISA (different artifact, different workflow).
72 
View all files on GitHub →

Details

Version
1.1.13
License
MIT
Stars on the repo
★ 19,269
Checked
Source
danielmiessler/LifeOS ↗
Creator
danielmiessler · 63 listings
View creator

Similar skills

See all →
Skill360 Feedback Surveymohitagw15856/pm-claude-skills · by mohitagw15856Design a 360-degree feedback survey or write a structured 360 feedback report. Use when asked to build a 360 feedback process, write 360 feedback for a colleague, design a feedback survey, or produce a feedback report. Produces either a complete survey instrument with rating scales and open-ended questions, or a structured narrative feedback report with themes, strengths, and development areas.★ 1.4k GitHub starsSkillExpert Knowledge Extractorinhouseseo/superseo-skills · by inhouseseoUse when extracting first-party expertise from a subject-matter expert before writing content. Produces a knowledge document of contrarian takes, specific examples, and surprising outcomes that AI can't fabricate.★ 353 GitHub starsSkillCreator Persona ResearcherTheMattBerman/scrollclaw · by TheMattBermanStart of the UGC pipeline for persona research, creator profiles, format selection, and scriptwriting. Use when the user is clearly asking for messaging work rather than broad full-pipeline orchestration.★ 71 GitHub starsSkillQuestionnaire Generatormattpocock/skills · by mattpocockTell us who you need answers from and what you're missing; get back a clean form you send them to fill in.★ 267k GitHub starsSkillIntent Interview Assistantaddyosmani/agent-skills · by addyosmaniExtracts what the user actually wants instead of what they think they should want. Achieves this through one-question-at-a-time interview until ~95% confidence about the underlying intent. Use when an ask is underspecified ("build me X" without "for whom" or "why now"), when the user explicitly invokes ("interview me", "grill me", "are we sure?", "stress-test my thinking"), or when you catch yourself silently filling in ambiguous requirements before any plan, spec, or code exists.★ 98.7k GitHub starsSkillBehavioral Science for Marketingcoreyhaines31/marketingskills · by coreyhaines31When the user wants to apply psychological principles, mental models, or behavioral science to marketing. Also use when the user mentions 'psychology,' 'mental models,' 'cognitive bias,' 'persuasion,' 'behavioral science,' 'why people buy,' 'decision-making,' 'consumer behavior,' 'anchoring,' 'social proof,' 'scarcity,' 'loss aversion,' 'framing,' or 'nudge.' Use this whenever someone wants to understand or leverage how people think and make decisions in a marketing context. For applying psychology to specific pages, see cro; for pricing tactics, see pricing; for copy framing, see copywriting.★ 51.1k GitHub stars

More from danielmiessler

SkillScope Oscillation Analyzerdanielmiessler/LifeOS · by danielmiessler3-pass scope oscillation that holds a question constant while shifting zoom — narrow/tactical, wide/strategic, then synthesis — to surface design tensions, scope recommendations, and coherence assessments invisible at any single zoom level. USE WHEN aperture oscillation, oscillate scope, zoom in and out, tactical vs strategic, scope framing, design tension, system coherence check, local vs global design, wrong scope, scope negotiation. NOT FOR lens rotation across angles (use IterativeDepth).★ 19.3k GitHub starsSkillAphorism Library Managerdanielmiessler/LifeOS · by danielmiesslerCurated aphorism collection with CRUD — content-based matching, themed search, thinker research, DB maintenance. Quotes organized by author/theme/context/usage to prevent repetition. Four workflows: FindAphorism, AddAphorism, ResearchThinker, SearchAphorisms. Themes: Stoicism, Wisdom, Truth-seeking, Excellence, Resilience, Curiosity. USE WHEN aphorism, quote, find a quote, research thinker, add aphorism, quote for newsletter, what did X say about, quote bank. NOT FOR creative writing or social posts.★ 19.3k GitHub starsSkillSocial Platform Scraperdanielmiessler/LifeOS · by danielmiesslerScrapes social platforms, business data, and e-commerce via Apify actors — Instagram, LinkedIn, TikTok, YouTube, Facebook, Google Maps, Amazon, and web crawls — filtering in code. USE WHEN scrape Instagram, scrape LinkedIn, scrape TikTok, scrape YouTube, scrape Facebook, Google Maps leads, Amazon reviews, business intelligence, multi-platform social listening, competitive analysis, lead generation, social monitoring, Apify actors, web crawl, extract contacts. NOT FOR X/Twitter account operations like posting, threads, or bookmarks (those need a dedicated X API client), 4-tier progressive scraping with proxy escalation (use BrightData), or real-Chrome bot bypass and computer use (use Interceptor).★ 19.3k GitHub starsSkillVisual Content Generatordanielmiessler/LifeOS · by danielmiesslerStatic visual content across 20+ formats — diagrams, mermaid, infographics, D3 dashboards, comics, icons, wallpaper — via Nano Banana Pro (default), Nano Banana, and Flux. USE WHEN art, illustration, diagram, flowchart, infographic, header image, blog social thumbnail, visualize, generate image, mermaid, architecture diagram, comic, icon, blog art, framework diagram, D3 chart, remove background, wallpaper. NOT FOR locked house-style YouTube/channel/video thumbnails, video or animation (use Remotion), or web UI design and integrated frontend layout (use Webdesign).★ 19.3k GitHub starsSkillArXiv Paper Finderdanielmiessler/LifeOS · by danielmiesslerSearch and retrieve arXiv academic papers by topic, category, or paper ID — with AlphaXiv-enriched AI-generated overviews. Uses arXiv Atom API across cs.AI/cs.LG/cs.CL/cs.CR/cs.MA/cs.SE/cs.IR. Three workflows: Latest, Search, Paper. USE WHEN arxiv, papers, latest papers, research papers, recent ML papers, paper lookup, summarize paper, latest LLM papers, AI safety papers, cs.AI latest. NOT FOR general research (Research), URL parsing, or annual reports.★ 19.3k GitHub starsSkillFiller Removal Audio Editordanielmiessler/LifeOS · by danielmiesslerAI audio editing pipeline: Whisper word-level transcription → Claude segment classification (KEEP/CUT_FILLER/CUT_FALSE_START/CUT_STUTTER/CUT_DEAD_AIR) → ffmpeg with 40ms qsin crossfades and room-tone fill → optional Cleanvoice cloud polish; plus GateScan/GateRepair for noise-gate ticking artifacts. Modes: --preview, --aggressive, --polish. Workflow: Clean. USE WHEN clean audio, edit audio, remove filler words, clean podcast, remove ums, cut dead air, polish audio, trim recording, cut stutters, ticking audio, clicking audio, audio clicks, gate artifacts, popping audio. NOT FOR video composition (use Remotion).★ 19.3k GitHub stars