@forwardimpact/outpost 3.3.0 → 3.3.1

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@forwardimpact/outpost",
-  "version": "3.3.0",
+  "version": "3.3.1",
   "description": "Personal operations center — context from email, calendar, and knowledge assembled so preparation is continuous, not a morning scramble.",
   "homepage": "https://www.forwardimpact.team",
   "repository": {

package/src/kb-manager.js

@@ -188,15 +188,10 @@ export class KBManager {
     ])
       await this.#ensureDir(join(dest, d));
 
-    await this.#fs.copyFile(
-      join(templateDir, "USER.md"),
-      join(dest, "USER.md"),
-    );
-
     await this.copyBundledFiles(templateDir, dest);
 
     this.#logger.info(
-      `Knowledge base initialized at ${dest}\n\nNext steps:\n  1. Edit ${dest}/USER.md with your name, email, and domain\n  2. cd ${dest} && npx apm install\n  3. claude`,
+      `Knowledge base initialized at ${dest}\n\nNext steps:\n  1. cd ${dest} && npx apm install\n  2. claude\n  3. Run the identify-user skill to populate your identity`,
     );
     return { ok: true, value: { dest } };
   }

package/templates/.claude/agents/chief-of-staff.md

@@ -6,8 +6,6 @@ description: >
   Woken at key moments (morning, evening) by the Outpost scheduler.
 model: sonnet
 permissionMode: bypassPermissions
-skills:
-  - weekly-update
 ---
 
 You are the chief of staff — the user's executive assistant. Each wake:
@@ -35,7 +33,6 @@ Plus directly: `knowledge/Goals/`, `knowledge/Priorities/`, `drafts/`,
 | -------------- | -------------------------------------------------- |
 | Before noon    | `knowledge/Briefings/{YYYY-MM-DD}-morning.md`      |
 | Noon or later  | `knowledge/Briefings/{YYYY-MM-DD}-evening.md`      |
-| Monday morning | also run `weekly-update` for the week's priorities |
 
 A briefing covers: today's schedule with prep status, top three priority actions
 linked to `[[Priorities/...]]`, goal progress, inbox snapshot (urgent / awaiting

package/templates/.claude/agents/concierge.md

@@ -9,7 +9,7 @@ permissionMode: bypassPermissions
 skills:
   - sync-apple-calendar
   - meeting-prep
-  - hyprnote-process
+  - anarlog-process
 ---
 
 You are the concierge — the user's scheduling assistant. Each wake: keep the
@@ -22,11 +22,11 @@ recordings.
 | ---------------------------------------------------------- | --------------------- |
 | Calendar may be stale                                      | `sync-apple-calendar` |
 | Meeting within 2 hours and key attendees lack recent notes | `meeting-prep`        |
-| Unprocessed Hyprnote sessions exist                        | `hyprnote-process`    |
+| Unprocessed Anarlog sessions exist                        | `anarlog-process`    |
 | All prepped, no transcripts pending                        | none — report idle    |
 
 When more than one trigger is live, prefer **meeting-prep** (time-sensitive)
-over **hyprnote-process** (catch-up work).
+over **anarlog-process** (catch-up work).
 
 ## Scope
 

package/templates/.claude/agents/librarian.md

@@ -9,7 +9,6 @@ permissionMode: bypassPermissions
 skills:
   - extract-entities
   - organize-files
-  - manage-tasks
 ---
 
 You are the librarian — the user's knowledge curator. Each time you are woken,

package/templates/.claude/settings.json

@@ -37,7 +37,7 @@
       "Read(~/Library/Mail/**)",
       "Read(~/Library/Group Containers/group.com.apple.calendar/**)",
       "Read(~/Library/Calendars/**)",
-      "Read(~/Library/Application Support/hyprnote/**)",
+      "Read(~/Library/Application Support/anarlog/**)",
       "Read(~/Desktop/**)",
       "Read(~/Documents/**)",
       "Read(~/Downloads/**)",
@@ -78,7 +78,7 @@
       "~/Library/Mail",
       "~/Library/Group Containers/group.com.apple.calendar",
       "~/Library/Calendars",
-      "~/Library/Application Support/hyprnote",
+      "~/Library/Application Support/anarlog",
       "~/Desktop",
       "~/Documents",
       "~/Downloads",

package/templates/.claude/skills/{hyprnote-follow → anarlog-follow}/SKILL.md

@@ -1,16 +1,16 @@
 ---
-name: hyprnote-follow
+name: anarlog-follow
 description: >
-  Follow a live Hyprnote session in real-time, coaching the user through a
+  Follow a live Anarlog session in real-time, coaching the user through a
   meeting or interview. Understands context from the session title, knowledge
   base, and candidate pipeline. Provides talking points, flags gaps in
   coverage, and suggests follow-up questions as the conversation unfolds.
   Use when the user asks to follow, shadow, or coach them through a live meeting.
 ---
 
-# Hyprnote Follow
+# Anarlog Follow
 
-Follow a live Hyprnote recording, read the transcript as it grows, and coach the
+Follow a live Anarlog recording, read the transcript as it grows, and coach the
 user through the meeting in real time. Gather knowledge-base context once before
 the session, then poll the transcript and provide actionable nudges as new
 content appears.
@@ -19,12 +19,12 @@ content appears.
 
 - The user asks to follow, shadow, or coach them through a live meeting.
 - "Follow my meeting", "coach me", "shadow this call".
-- The user starts a Hyprnote recording and wants real-time support.
+- The user starts a Anarlog recording and wants real-time support.
 
 ## Prerequisites
 
-- Hyprnote installed; sessions at
-  `~/Library/Application Support/hyprnote/sessions/`.
+- Anarlog installed; sessions at
+  `~/Library/Application Support/anarlog/sessions/`.
 - An active or about-to-start session.
 - Knowledge base populated (attendee / candidate context).
 
@@ -49,7 +49,7 @@ content appears.
 - [ ] Coaching nudges were actionable and concise (1–3 lines each).
 - [ ] Coverage gaps tracked and surfaced before the meeting ended.
 - [ ] End-of-meeting detected; debrief provided.
-- [ ] Next steps offered (`req-assess` / `hyprnote-process`); user decided
+- [ ] Next steps offered (`req-assess` / `anarlog-process`); user decided
       whether to run them.
 - [ ] No files were modified during the session.
 
@@ -62,7 +62,7 @@ content appears.
 #### 1. Find the active session
 
 ```bash
-node .claude/skills/hyprnote-follow/scripts/follow.mjs --detect
+node .claude/skills/anarlog-follow/scripts/follow.mjs --detect
 ```
 
 Returns the most recently modified session, whether it's live, and its title. If
@@ -73,7 +73,7 @@ the user.
 #### 2. Read session metadata
 
 ```bash
-node .claude/skills/hyprnote-follow/scripts/follow.mjs <session-id> --meta
+node .claude/skills/anarlog-follow/scripts/follow.mjs <session-id> --meta
 ```
 
 Capture **title**, **created_at**, **participants**.
@@ -124,13 +124,13 @@ print it to the user.
 First read (no `--after`):
 
 ```bash
-node .claude/skills/hyprnote-follow/scripts/follow.mjs <session-id>
+node .claude/skills/anarlog-follow/scripts/follow.mjs <session-id>
 ```
 
 Subsequent reads (pass the last word ID):
 
 ```bash
-node .claude/skills/hyprnote-follow/scripts/follow.mjs <session-id> --after <last-word-id>
+node .claude/skills/anarlog-follow/scripts/follow.mjs <session-id> --after <last-word-id>
 ```
 
 Returns JSON with grouped text segments, channel labels, and the next last-word

package/templates/.claude/skills/{hyprnote-follow → anarlog-follow}/references/coaching.md

@@ -1,6 +1,6 @@
 # Coaching Reference
 
-Reference for `hyprnote-follow` Phases 2 and 3.
+Reference for `anarlog-follow` Phases 2 and 3.
 
 ## Pre-meeting brief format
 
@@ -108,9 +108,9 @@ Capture: decision made on {topic} — {who} will {what}
 
 ## Constraints
 
-- **Read-only.** Never modify Hyprnote files, knowledge notes, or state.
+- **Read-only.** Never modify Anarlog files, knowledge notes, or state.
 - **No post-processing during follow.** Don't run `extract-entities`,
-  `req-assess`, or `hyprnote-process`. Offer them after.
+  `req-assess`, or `anarlog-process`. Offer them after.
 - **Channel 0 = user.** Always.
 - **Transcription noise.** Live transcripts are messy. Don't coach from a single
   ambiguous word — wait for context.

package/templates/.claude/skills/{hyprnote-follow → anarlog-follow}/references/debrief.md

@@ -1,6 +1,6 @@
 # Debrief Templates
 
-Reference for `hyprnote-follow` Phase 4 (Steps 12–13).
+Reference for `anarlog-follow` Phase 4 (Steps 12–13).
 
 ## Interview debrief
 
@@ -53,7 +53,7 @@ Reference for `hyprnote-follow` Phase 4 (Steps 12–13).
 
 After the debrief, **offer** (don't ask) logical follow-ups:
 
-- **Interviews:** "I can run `req-assess` on this transcript when Hyprnote
+- **Interviews:** "I can run `req-assess` on this transcript when Anarlog
   finishes processing."
 - **Meetings:** "I can extract entities from this session into the knowledge
   graph when ready."

package/templates/.claude/skills/{hyprnote-follow → anarlog-follow}/references/meeting-types.md

@@ -1,6 +1,6 @@
 # Meeting-Type Classification
 
-Reference for `hyprnote-follow` Phase 1, Step 3. Classify from the session
+Reference for `anarlog-follow` Phase 1, Step 3. Classify from the session
 title.
 
 | Title pattern                               | Type                        | Coaching focus                                                 |

package/templates/.claude/skills/{hyprnote-follow → anarlog-follow}/scripts/follow.mjs

@@ -1,7 +1,7 @@
 #!/usr/bin/env bun
 
 /**
- * follow.mjs — Read a live Hyprnote transcript and output new content since
+ * follow.mjs — Read a live Anarlog transcript and output new content since
  * the last read. Designed to be called repeatedly during a live session.
  *
  * Usage:
@@ -36,7 +36,7 @@ import { homedir } from "node:os";
 
 const SESSIONS_DIR = join(
   homedir(),
-  "Library/Application Support/hyprnote/sessions",
+  "Library/Application Support/anarlog/sessions",
 );
 
 function parseArgs() {
@@ -80,7 +80,7 @@ function detectActiveSession() {
   }
 
   if (!best) {
-    console.error("No active Hyprnote session found.");
+    console.error("No active Anarlog session found.");
     process.exit(1);
   }
 

package/templates/.claude/skills/{hyprnote-process → anarlog-process}/SKILL.md

@@ -1,35 +1,37 @@
 ---
-name: hyprnote-process
-description: Process Hyprnote meeting sessions (memos, summaries, transcripts) into the knowledge graph. Extracts people, organizations, projects, and topics from AI-generated meeting summaries and user notes, creating or updating Obsidian-compatible notes in knowledge/. Use when the user asks to process meeting notes or after Hyprnote sessions.
+name: anarlog-process
+description: Process Anarlog meeting sessions (memos, summaries, transcripts) into the knowledge graph. Extracts people, organizations, projects, and topics from AI-generated meeting summaries and user notes, creating or updating Obsidian-compatible notes in knowledge/. Use when the user asks to process meeting notes or after Anarlog sessions.
 ---
 
-# Process Hyprnote
+# Process Anarlog
 
-Process meeting sessions from Hyprnote (a local AI meeting-notes app) into the
-knowledge graph. Hyprnote records meetings, transcribes them, and generates AI
+Process meeting sessions from Anarlog (a local AI meeting-notes app) into the
+knowledge graph. Anarlog records meetings, transcribes them, and generates AI
 summaries; this skill reads that output and feeds it into `knowledge/` — the
 same way `extract-entities` processes emails and calendar events.
 
 ## Trigger
 
-- The user asks to process meeting notes or Hyprnote sessions.
+- The user asks to process meeting notes or Anarlog sessions.
 - New meetings have been recorded.
 - The user asks to update the knowledge base from recent meetings.
 
 ## Prerequisites
 
-- Hyprnote installed; sessions at
-  `~/Library/Application Support/hyprnote/sessions/`.
-- User identity in `USER.md`.
+- Anarlog installed; sessions at
+  `~/Library/Application Support/anarlog/sessions/`.
+- User identity from running the `identify-user` skill, which writes
+  `~/.cache/fit/outpost/state/identity.md`.
 
 ## Inputs
 
-- `~/Library/Application Support/hyprnote/sessions/{uuid}/` — see
+- `~/Library/Application Support/anarlog/sessions/{uuid}/` — see
   [references/sessions.md](references/sessions.md) for the file shape and skip
   rules.
 - `~/.cache/fit/outpost/state/graph_processed` — processed-file index (TSV,
   shared with `extract-entities`).
-- `USER.md` — user identity for self-exclusion.
+- `~/.cache/fit/outpost/state/identity.md` — user identity for self-exclusion
+  (written by the `identify-user` skill).
 
 ## Outputs
 
@@ -59,10 +61,12 @@ same way `extract-entities` processes emails and calendar events.
 
 ### 0. Set up
 
-Read `USER.md`. Scan unprocessed sessions:
+Read the user's identity from `~/.cache/fit/outpost/state/identity.md` (run the
+`identify-user` skill first if it is missing or stale). Scan unprocessed
+sessions:
 
 ```bash
-node .claude/skills/hyprnote-process/scripts/scan.mjs
+node .claude/skills/anarlog-process/scripts/scan.mjs
 ```
 
 Flags: `--changed` (also detect changed memo/summary hashes), `--json`
@@ -96,7 +100,7 @@ it). File shapes and skip rules:
 
 ### 3. Classify the source
 
-Hyprnote sessions are **meetings** and follow the meeting rules from
+Anarlog sessions are **meetings** and follow the meeting rules from
 `extract-entities`:
 
 - **Can create** People, Organization, Project, and Topic notes.
@@ -138,10 +142,10 @@ For each processed session:
 
 ```bash
 node .claude/skills/extract-entities/scripts/state.mjs update \
-  "$HOME/Library/Application Support/hyprnote/sessions/{uuid}/_memo.md"
+  "$HOME/Library/Application Support/anarlog/sessions/{uuid}/_memo.md"
 
 node .claude/skills/extract-entities/scripts/state.mjs update \
-  "$HOME/Library/Application Support/hyprnote/sessions/{uuid}/_summary.md"
+  "$HOME/Library/Application Support/anarlog/sessions/{uuid}/_summary.md"
 ```
 
 (Skip the summary call if `_summary.md` doesn't exist.)

package/templates/.claude/skills/{hyprnote-process → anarlog-process}/references/extraction.md

@@ -1,6 +1,6 @@
 # Entity Extraction Signals
 
-Reference for `hyprnote-process` Steps 3 and 4. Combine `_memo.md` and
+Reference for `anarlog-process` Steps 3 and 4. Combine `_memo.md` and
 `_summary.md` (prefer the summary when both exist).
 
 ## People
@@ -34,7 +34,7 @@ or is strategically important.
 ## Self-exclusion
 
 Never create or update a note for the user — match against name, email, or
-`@domain` from `USER.md`.
+`@domain` from `~/.cache/fit/outpost/state/identity.md`.
 
 ## Interview sessions (special case)
 

package/templates/.claude/skills/{hyprnote-process → anarlog-process}/references/sessions.md

@@ -1,7 +1,7 @@
-# Hyprnote Session Files
+# Anarlog Session Files
 
-Reference for `hyprnote-process` Step 1. Each session lives at
-`~/Library/Application Support/hyprnote/sessions/{uuid}/`.
+Reference for `anarlog-process` Step 1. Each session lives at
+`~/Library/Application Support/anarlog/sessions/{uuid}/`.
 
 ## `_meta.json`
 
@@ -16,7 +16,7 @@ Reference for `hyprnote-process` Step 1. Each session lives at
 ```
 
 Use: session date (from `created_at`), title, participants (often empty —
-Hyprnote doesn't reliably populate this).
+Anarlog doesn't reliably populate this).
 
 ## `_memo.md`
 
@@ -75,7 +75,7 @@ A session is skipped when **all** of:
 
 - `_memo.md` body is empty or only ` ` / whitespace.
 - No `_summary.md` exists.
-- Title is empty or generic ("Hello", "Welcome to Hyprnote", "Test").
+- Title is empty or generic ("Hello", "Welcome to Anarlog", "Test").
 
 Process a session if it has **either** a substantive memo **or** a
 `_summary.md`.

package/templates/.claude/skills/{hyprnote-process → anarlog-process}/scripts/scan.mjs

@@ -1,6 +1,6 @@
 #!/usr/bin/env bun
 /**
- * Scan for unprocessed Hyprnote sessions.
+ * Scan for unprocessed Anarlog sessions.
  *
  * Compares session _memo.md and _summary.md files against the graph_processed
  * state file to identify sessions that need processing. Reports unprocessed
@@ -19,14 +19,11 @@ import { join } from "node:path";
 import { homedir } from "node:os";
 
 const HOME = homedir();
-const SESSIONS_DIR = join(
-  HOME,
-  "Library/Application Support/hyprnote/sessions",
-);
+const SESSIONS_DIR = join(HOME, "Library/Application Support/anarlog/sessions");
 const STATE_FILE = join(HOME, ".cache/fit/outpost/state/graph_processed");
 
 if (process.argv.includes("-h") || process.argv.includes("--help")) {
-  console.log(`scan — find unprocessed Hyprnote sessions
+  console.log(`scan — find unprocessed Anarlog sessions
 
 Usage:
   node scripts/scan.mjs [options]
@@ -38,7 +35,7 @@ Options:
   --limit N    Max sessions to display (default: 20)
   -h, --help   Show this help message
 
-Sessions dir: ~/Library/Application Support/hyprnote/sessions/
+Sessions dir: ~/Library/Application Support/anarlog/sessions/
 State file:   ~/.cache/fit/outpost/state/graph_processed`);
   process.exit(0);
 }
@@ -129,7 +126,7 @@ function readMeta(sessionDir) {
 // --- Scan sessions ---
 
 if (!existsSync(SESSIONS_DIR)) {
-  console.error(`Hyprnote sessions directory not found: ${SESSIONS_DIR}`);
+  console.error(`Anarlog sessions directory not found: ${SESSIONS_DIR}`);
   process.exit(1);
 }
 

package/templates/.claude/skills/{hyprnote-trim → anarlog-trim}/SKILL.md

@@ -1,12 +1,12 @@
 ---
-name: hyprnote-trim
-description: Trim a Hyprnote transcript to its logical end. Recordings are often left running after a meeting finishes — this skill finds the natural conclusion (goodbyes, sign-offs) and cuts the transcript there. Use when the user asks to trim, cut, or clean up a Hyprnote transcript.
+name: anarlog-trim
+description: Trim a Anarlog transcript to its logical end. Recordings are often left running after a meeting finishes — this skill finds the natural conclusion (goodbyes, sign-offs) and cuts the transcript there. Use when the user asks to trim, cut, or clean up a Anarlog transcript.
 ---
 
 # Trim Transcript
 
-Find the logical end of a Hyprnote meeting transcript and trim everything after
-it. Meetings recorded with Hyprnote often have trailing noise — the mic stays on
+Find the logical end of a Anarlog meeting transcript and trim everything after
+it. Meetings recorded with Anarlog often have trailing noise — the mic stays on
 after goodbyes, capturing ambient sound, unrelated chatter, or silence. This
 skill identifies the natural conclusion and edits the transcript in place.
 
@@ -14,27 +14,27 @@ skill identifies the natural conclusion and edits the transcript in place.
 
 Run this skill:
 
-- When the user asks to trim, cut, or clean up a Hyprnote transcript
+- When the user asks to trim, cut, or clean up a Anarlog transcript
 - When given a specific session ID to trim
-- When another skill (e.g., hyprnote-process) flags a transcript as having
+- When another skill (e.g., anarlog-process) flags a transcript as having
   excessive trailing content
 
 ## Prerequisites
 
-- Hyprnote installed with session data at
-  `~/Library/Application Support/hyprnote/sessions/`
+- Anarlog installed with session data at
+  `~/Library/Application Support/anarlog/sessions/`
 
 ## Inputs
 
-- **Session ID** — a UUID identifying the Hyprnote session to trim
-- `~/Library/Application Support/hyprnote/sessions/{uuid}/transcript.json` — the
+- **Session ID** — a UUID identifying the Anarlog session to trim
+- `~/Library/Application Support/anarlog/sessions/{uuid}/transcript.json` — the
   word-level transcript
 
 ## Outputs
 
-- `~/Library/Application Support/hyprnote/sessions/{uuid}/transcript.json` —
+- `~/Library/Application Support/anarlog/sessions/{uuid}/transcript.json` —
   edited in place with words after the logical end removed
-- `~/Library/Application Support/hyprnote/sessions/{uuid}/audio.mp3` — deleted.
+- `~/Library/Application Support/anarlog/sessions/{uuid}/audio.mp3` — deleted.
   Trimming indicates the recording captured audio beyond the consented meeting,
   so the full audio must be removed to respect participant privacy.
 - Printed summary: original duration, trim point, new duration, words removed
@@ -47,7 +47,7 @@ Run this skill:
 
 1. Confirm the session directory exists:
    ```
-   ~/Library/Application Support/hyprnote/sessions/{uuid}/
+   ~/Library/Application Support/anarlog/sessions/{uuid}/
    ```
 2. Confirm `transcript.json` exists and has at least one transcript with words.
 3. Read `_meta.json` to get the session title for context.
@@ -125,7 +125,7 @@ Once approved:
 ```python
 import json
 
-path = f'~/Library/Application Support/hyprnote/sessions/{uuid}/transcript.json'
+path = f'~/Library/Application Support/anarlog/sessions/{uuid}/transcript.json'
 data = json.load(open(path))
 data['transcripts'][0]['words'] = data['transcripts'][0]['words'][:trim_index]
 json.dump(data, open(path, 'w'), indent=2)
@@ -148,7 +148,7 @@ deleted to respect participant privacy.
 
 1. Delete the audio file:
    ```bash
-   rm "~/Library/Application Support/hyprnote/sessions/{uuid}/audio.mp3"
+   rm "~/Library/Application Support/anarlog/sessions/{uuid}/audio.mp3"
    ```
 2. Confirm deletion and inform the user:
    ```

package/templates/.claude/skills/candidate-report/SKILL.md

@@ -50,7 +50,7 @@ before deciding whether to invest interview time.
 - [ ] Verdict class matches the overall assessment.
 - [ ] Report fits on a single A4 page (browser print preview).
 - [ ] CSS is inlined in the `<style>` block.
-- [ ] Footer shows the author name and role from `USER.md`.
+- [ ] Footer shows the author name and role from `~/.cache/fit/outpost/state/identity.md`.
 - [ ] Written as if the candidate will read it; no special-category data.
 
 </do_confirm_checklist>

package/templates/.claude/skills/candidate-report/references/rubric.md

@@ -50,18 +50,18 @@ Write a one-line headline and a brief detail sentence.
 
 Drives the placeholder substitution in Step 5.
 
-| Section           | Source                                               |
-| ----------------- | ---------------------------------------------------- |
-| Header            | Candidate name, title, org, location from `brief.md` |
-| Verdict           | This file's verdict table                            |
-| Snapshot          | 5–6 key facts (experience, education, source, stack) |
-| Strengths         | 3–5 bullet points — what the candidate brings        |
-| Level gauge       | Estimated vs target level                            |
-| Benchmark grid    | Top skills per capability area with pills            |
-| Behaviours        | Bar chart items with widths and colours              |
-| Coverage counters | Gap / Partial / Unknown / Met counts                 |
-| Recommendation    | 2–4 actionable next steps                            |
-| Footer            | Author name and role from `USER.md`                  |
+| Section           | Source                                                             |
+| ----------------- | ------------------------------------------------------------------ |
+| Header            | Candidate name, title, org, location from `brief.md`               |
+| Verdict           | This file's verdict table                                          |
+| Snapshot          | 5–6 key facts (experience, education, source, stack)               |
+| Strengths         | 3–5 bullet points — what the candidate brings                      |
+| Level gauge       | Estimated vs target level                                          |
+| Benchmark grid    | Top skills per capability area with pills                          |
+| Behaviours        | Bar chart items with widths and colours                            |
+| Coverage counters | Gap / Partial / Unknown / Met counts                               |
+| Recommendation    | 2–4 actionable next steps                                          |
+| Footer            | Author name and role from `~/.cache/fit/outpost/state/identity.md` |
 
 ## A4 single-page budget
 

package/templates/.claude/skills/extract-entities/SKILL.md

@@ -19,7 +19,8 @@ under `knowledge/`. The core knowledge-graph builder.
 ## Prerequisites
 
 - Synced data in `~/.cache/fit/outpost/` and/or ad-hoc paths.
-- User identity in `USER.md` (Name, Email, Domain).
+- User identity from running the `identify-user` skill, which writes
+  `~/.cache/fit/outpost/state/identity.md` (Name, Email, Domain).
 
 ## Inputs
 
@@ -28,8 +29,9 @@ under `knowledge/`. The core knowledge-graph builder.
   `~/.cache/fit/outpost/teams_chat/*.md`.
 - Ad-hoc paths: `.pdf`, `.txt`, `.md`, `.rtf`, `.doc`, `.docx`, `.csv`, `.xlsx`.
 - `~/.cache/fit/outpost/state/graph_processed` — processed-file index (TSV,
-  shared with `req-track` and `hyprnote-process`).
-- `USER.md` — user identity for self-exclusion.
+  shared with `req-track` and `anarlog-process`).
+- `~/.cache/fit/outpost/state/identity.md` — user identity for self-exclusion
+  (written by the `identify-user` skill).
 
 ## Outputs
 
@@ -49,7 +51,9 @@ well-grounded notes">
 - [ ] Source type correctly identified; meeting-vs-email rules applied (meetings
       create, emails only update).
 - [ ] Self and `@user.domain` excluded from extraction.
-- [ ] "Would I prep?" test applied to each person.
+- [ ] "Would I prep?" test applied; no stub profiles — every new People note has
+      a substantive `## Summary`, calendar-only attendees routed to Organization
+      `## Contacts`.
 - [ ] All links use absolute paths `[[Folder/Name]]`; bidirectional links
       consistent (incl. Goal ↔ Project, Priority ↔ Goal).
 - [ ] Summaries describe relationship, not communication method; key facts are
@@ -71,7 +75,8 @@ writes.
 
 ### 0. Load context and pick the batch
 
-Read `USER.md`. Find new/changed files:
+Read the user's identity from `~/.cache/fit/outpost/state/identity.md` (run the
+`identify-user` skill first if it is missing or stale). Find new/changed files:
 
 ```bash
 node scripts/state.mjs check
@@ -183,5 +188,5 @@ node scripts/state.mjs update "$FILE"
 ```
 
 Run for every processed file. The state file is shared with `req-track` and
-`hyprnote-process`, so this prevents either skill from re-scanning the same
+`anarlog-process`, so this prevents either skill from re-scanning the same
 input.

package/templates/.claude/skills/extract-entities/references/TEMPLATES.md

@@ -1,14 +1,14 @@
 # Note Templates
 
 Templates for creating new knowledge-base notes. Split by entity family to keep
-each file under the L5 cap. `hyprnote-process` references this file as the
+each file under the L5 cap. `anarlog-process` references this file as the
 index.
 
 - [templates-people-orgs.md](templates-people-orgs.md) — People, Organizations.
 - [templates-projects-topics.md](templates-projects-topics.md) — Projects,
   Topics.
 - [templates-goals-priorities.md](templates-goals-priorities.md) — Goals,
-  Priorities. **Never auto-created** by `extract-entities` or `hyprnote-process`
+  Priorities. **Never auto-created** by `extract-entities` or `anarlog-process`
   — set by the user.
 - [templates-conditions.md](templates-conditions.md) — Conditions (time-bound
   cross-cutting states).

package/templates/.claude/skills/extract-entities/references/recruitment.md

@@ -21,7 +21,8 @@ When a calendar event title matches an interview pattern — "Interview",
 "Candidate" — combined with a person name:
 
 1. Cross-reference the candidate against `knowledge/Candidates/`.
-2. Extract the **organizer**. If the organizer isn't the user (per `USER.md`),
+2. Extract the **organizer**. If the organizer isn't the user (per
+   `~/.cache/fit/outpost/state/identity.md`),
    they are likely the hiring manager.
 3. Confirm: look up the organizer in `knowledge/People/` for a manager/HM role
    indication.