refactor(linkedin)!: rename plugin linkedin-thought-leadership → linkedin-studio (v3.0.0)

BREAKING CHANGE: the marketplace slug, the agent namespace
(linkedin-studio:<agent>), and the runtime state-file path
(~/.claude/linkedin-studio.local.md) all change. Reinstall required;
existing state migrated in place (post metrics, streak, history preserved).
The /linkedin:* commands are unchanged — the command namespace is set
per-command in frontmatter and was always independent of the plugin slug.
Functionality is byte-identical to v2.4.0; this release is pure identity.

- dir + manifests: plugins/linkedin-studio + plugin.json + root marketplace.json
- agent namespace updated in commands/newsletter.md (only functional invoker)
- state path updated in 4 hook scripts + topic-rotation prompt + state template
- catch-all skill dir renamed skills/linkedin-studio (5 functional skills unchanged)
- docs + version bump to 3.0.0 across README badge, CHANGELOG, root README/CLAUDE.md
- historical records (CHANGELOG past entries, docs/ build artifacts,
  config-audit v5.0.0 snapshots) intentionally retain the old slug

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>

plugins/linkedin-studio/config/REMEMBER.template.md

@@ -0,0 +1,30 @@
+# LinkedIn Studio — Session State
+
+**Last updated:** [Auto-filled by session-start hook]
+
+## Last Session Summary
+<!-- Brief recap of what was done last session -->
+
+## Recent Posts
+<!-- Posts created in recent sessions -->
+<!-- Format: - [YYYY-MM-DD] "Hook text..." — topic -->
+
+## Active Content Plan
+<!-- Current week's plan and upcoming topics -->
+
+## Pending Tasks
+<!-- Actionable items for next session -->
+- [ ] Posts to publish
+- [ ] Analytics to import
+- [ ] Engagement tasks (5x5x5)
+
+## Current Strategy
+<!-- Phase and focus area -->
+**Phase:** [Foundation / Growth / Authority / Scale]
+**Focus:** [Current strategic priority]
+
+## Recommendations
+<!-- Top 3 actionable suggestions from last session -->
+
+## Notes
+<!-- Free-form session notes -->

plugins/linkedin-studio/config/content-history.template.md

@@ -0,0 +1,18 @@
+# Content History Log
+
+Tracks all LinkedIn posts created through the plugin. Append-only — never edit existing entries.
+
+Auto-initialized from `config/content-history.template.md` when the first post is logged.
+
+## Format
+
+| Date | Hook | Topic | Format | Words | Chars | Source |
+|------|------|-------|--------|-------|-------|--------|
+
+<!-- Entries are appended below by the Stop hook -->
+<!-- Format: | YYYY-MM-DD | "Hook text (60 chars max)..." | topic_area | post/quick/react/video | word_count | char_count | original/url/curated | -->
+
+## Content Log
+
+| Date | Hook | Topic | Format | Words | Chars | Source |
+|------|------|-------|--------|-------|-------|--------|

plugins/linkedin-studio/config/edition-config.template.json

@@ -0,0 +1,28 @@
+{
+  "_doc": {
+    "purpose": "Schema + starter for edition-config.json — the STATIC per-edition delivery metadata that render/build-linkedin.mjs reads (calendar, freshness, cover credit, captions). Complements edition-state.json (machine resumption state) and edition-delingstekst.md (distribution copy).",
+    "decision": "G — production lives in the series root, NOT in the plugin. Copy this template to <serie>/linkedin/edition-config.json and fill it in. This file is the schema-defining TEMPLATE only.",
+    "location": "<serie>/linkedin/edition-config.json  (read relative to cwd = series root; OUT_ROOT = <cwd>/linkedin)",
+    "graceful": "render/build-linkedin.mjs loadEditionConfig() falls back to empty defaults if this file is missing or malformed — every field below is optional. Provide it for a complete delivery page (calendar slot, freshness banner, cover credit, alt-text caption).",
+    "keys": "Article keys are zero-padded strings mirroring edition-state.json + the NN-prefix of each NN-utkast.md draft: \"01\", \"02\", ..., plus \"samle\" for the collected post.",
+    "fields": {
+      "calendar[NN]": "{ dag: human date label e.g. \"Mandag 02.06\", klokke: \"HH:MM\" } — the scheduled slot shown on POST.html. Default if absent: { dag: \"—\", klokke: \"08:00\" }.",
+      "freshness[NN]": "string — a freshness/recency note rendered in the amber banner (e.g. \"Tall fra Q1 2026; sjekk før publisering etter 01.07\"). Omit for no banner.",
+      "coverCredit": "string — global cover-image credit line (\"Add credit and caption\" field). One value for the whole edition.",
+      "captions[NN]": "string — per-article cover-image caption / alt text. Default if absent: \"—\".",
+      "carousel": "list of zero-padded NN strings (e.g. [\"03\",\"06\"]) — the editions that ship an optional carousel/document post. POST.html shows a carousel block only for these NN. Empty/absent → no carousel block. (S14/F6: replaces the old hardcoded Seres set.)"
+    }
+  },
+  "calendar": {
+    "01": { "dag": "<Ukedag DD.MM>", "klokke": "08:00" },
+    "samle": { "dag": "<Ukedag DD.MM>", "klokke": "08:00" }
+  },
+  "freshness": {
+    "01": "<optional freshness note shown in the banner — omit the key for no banner>"
+  },
+  "coverCredit": "<cover-image credit line, or empty string>",
+  "captions": {
+    "01": "<cover-image caption / alt text for article 01>"
+  },
+  "carousel": []
+}

plugins/linkedin-studio/config/edition-delingstekst.template.md

@@ -0,0 +1,55 @@
+<!--
+  TEMPLATE — edition-delingstekst.md  (distribution copy for a newsletter edition)
+
+  Purpose : the per-edition LinkedIn distribution text that render/build-linkedin.mjs
+            folds into each POST.html "all-in-one-place" deliverable. This is the
+            feed copy the reader sees BEFORE "…see more" — the hook that earns the
+            click (gated in /linkedin:newsletter Step 9).
+  Decision: G — production lives in the series root, NOT the plugin. Copy this to
+            <serie>/linkedin/edition-delingstekst.md and fill it in.
+  Location: <serie>/linkedin/edition-delingstekst.md  (cwd = series root).
+  Graceful: render/build-linkedin.mjs degrades if this file is missing (no
+            distribution copy is folded in; the article POST.html still builds).
+            Provide it for a complete delivery.
+
+  GRAMMAR (exactly what parseDelingstekst() recognizes — do not improvise):
+    - A section starts with a heading:  "## Del N — <title>"  (N = article number,
+      mapped to zero-padded key "0N")  OR  "## Samle <…>"  (the collected post,
+      key "samle").
+    - "## SYSTEM …" headings are ignored.
+    - Inside a section, until the next "## " heading or a "---" line:
+        * "**Første kommentar:** <text>"  → first-comment text (one line).
+        * a line beginning with "#" + non-space (e.g. "#KI #offentligsektor")
+          → the hashtag line.
+        * a "> …" blockquote line → ignored (use it for NB/notes to yourself).
+        * every other line → part of the share text (the hook + body shown in feed).
+  Keys MUST match the NN-prefix of the draft (NN-utkast.md) and edition-config.json.
+-->
+
+## Del 1 — <edition title>
+
+<First line = the krok/hook: the single line that must stop the scroll. Keep the
+strongest claim or tension here; this is what shows before "…see more".>
+
+<Then 2–4 short lines that pay off the hook and point at the article. Tighten,
+never pad — this is feed copy, not the article.>
+
+**Første kommentar:** <the first-comment text — e.g. a link, a question to seed
+discussion, or the "full edition here" pointer. LinkedIn suppresses links in the
+body, so the link belongs here.>
+
+#hashtag1 #hashtag2 #hashtag3
+
+> NB to self (ignored by the renderer): note any freshness caveat or A/B variant
+> you want to remember for this edition.
+
+---
+
+## Samle <collected-post title, if shipping a roundup of the series>
+
+<Hook for the collected/summary post. Same grammar. Omit this whole section if the
+edition has no samle post.>
+
+**Første kommentar:** <first comment for the samle post>
+
+#hashtag1 #hashtag2

plugins/linkedin-studio/config/edition-state.template.json

@@ -0,0 +1,65 @@
+{
+  "_doc": {
+    "purpose": "Schema for edition-state.json — deterministic resumption state for a newsletter edition in production. Holds the current phase + per-article status so /linkedin:newsletter (Step 0) can resume exactly where a prior session stopped.",
+    "decision": "G — production state lives in the serie-mappe (e.g. /Users/ktg/repos/maskinrommet/serier/<slug>/linkedin/edition-state.json), NOT in the plugin. This file is the schema-defining TEMPLATE only; copy + fill it in the serie-mappe when producing an edition.",
+    "complements": "edition-config.json (static: calendar, freshness, captions) and <serie>/STATE.md (human-readable narrative state, overwritten each phase per the ONE-system continuity rule — there is no edition-HANDOVER.md). edition-state.json is the machine-readable companion: deterministic resumption + the durable fact-check log, immutable rules, and persona verdicts that the old HANDOVER §4/§5 used to carry.",
+    "lifecycle": "/linkedin:newsletter reads this in Step 0 and rewrites it at every phase transition. Article keys mirror edition-config.json (zero-padded strings: \"01\", \"02\", ..., or \"samle\").",
+    "phases": [
+      "load-context — read <serie>/STATE.md, voice profile, persona library, series brief (Step 0)",
+      "brief-calibration — angle, voice, audience personas, key points, leader-takeaway (Step 1)",
+      "research — parallel scoped mandates → verified notes, triangulation (Step 2)",
+      "skeleton-pitch — five-line skeleton (premise/problem/recommendation/payoff/forward) + section pitches, operator gate + persona-skjelett-sweep BEFORE prose (Step 2.5)",
+      "spine-prose — one paragraph per section against the gated skeleton, operator gate BEFORE full expansion (Step 3a)",
+      "draft — full prose expansion against the gated spine; may span sessions (Step 3b)",
+      "consistency-quality — threads, premise→conclusion arc, AI-slop removal, formatting dose (Step 4)",
+      "factcheck-sweep — risk-sorted, guilty-until-disproven, verification log (Step 5)",
+      "editorial-review — editor's craft gate: prose-craft (em-dash density, verbatim repetition, postulated numbers, contradictions, versal-tic) + narrative-architecture (concrete instantiation, theory-anchored hypotheses, series-title symmetry, equal action per addressee, un-overloaded conclusion), ≤10 flags BLOCK/REWORK/NICE, operator-gated via SendUserFile BEFORE the persona sweep (Step 5.5)",
+      "persona-sweep-prelock — reader jury, primary wins, convergence to clean YES (Step 6)",
+      "annotation — optional annotatable review HTML for a manual pass (Step 7)",
+      "visual-assets — cover (+ optional inline figures) or carousel deck: brief → generate → operator-gate → approve, BEFORE lock so build-linkedin.mjs picks them up (Step 7.5)",
+      "lock-delivery — LOCK → POST.html all-in-one-place deliverable (Step 8)",
+      "hook-conversion-gate — persona gate on distribution text post-lock: would YOU click? (Step 9)",
+      "scheduling — register edition in plugin queue/state for native LinkedIn scheduling (Step 10)"
+    ],
+    "articleStatusValues": ["pending", "in-progress", "locked", "scheduled"],
+    "editorialReview": "Per-article editorial-review record written by Step 5.5 (editorial-review phase). Runs AFTER fact-check (Step 5) and BEFORE the persona sweep (Step 6): the editorial-reviewer agent judges CRAFT (prose-craft + narrative-architecture), not reader-response, mirroring the Maskinrommet skrivekontrakt §C2. The report (≤10 flags, each with kategori P1–P5/A1–A5, quote/line-ref, direction, severity BLOCK/REWORK/NICE) is surfaced to the operator via SendUserFile; the operator decides which flags fold in. Shape: { reportPath, flagCount, byAxis: { prosa, arkitektur }, bySeverity: { block, rework, nice }, foldedIn, waived, status }. status ladder: pending → reviewed → folded. null until Step 5.5 runs. This is the craft companion to factcheckLog (truth) and personaSweep (response).",
+    "visualAssets": "Per-article visual-asset record written by Step 7.5 (visual-assets phase). Runs BEFORE lock because render/build-linkedin.mjs picks up linkedin/NN/cover.png + the edition-config credit/caption when it builds POST.html — generating images after lock would force a re-render. Shape: { format: \"standard\" | \"carousel\"; cover: { brief, route, candidates[], approved, status }; figures: [ { id, brief, placement, status } ]; carousel: null | { source, pdf, status } }. format \"standard\" = cover + optional inline figures (cover.png is mandatory per the KTG cover-directive); format \"carousel\" = typografisk deck via render/build-carousel.mjs instead of cover+inline (cover/figures stay empty). route: \"mcp-image\" (default, via mcp__mcp-image__generate_image) | \"external\" (DALL·E / Midjourney / photographer → linkedin/NN/cover-raw.png). status ladder: pending → briefed → generated → approved. candidates[] holds the cover-v<N>-kandidat.png attempts; approved is the fixed approved name (\"cover.png\") once the operator-gate passes. figures[].id = \"fig1\"..; placement = section reference in NN-utkast.md (figures are referenced in the draft via ![alt](linkedin/NN/figN.png) and uploaded manually in the LinkedIn editor — build-linkedin.mjs does NOT embed them). Naming convention: cover.png (approved, fixed — what build-linkedin.mjs reads) | cover-v<N>-kandidat.png (attempts) | cover-raw.png (optional external pre-edit source) | fig<N>.png (inline). credit + caption are recorded in <serie>/linkedin/image-credit-caption.md and flow into edition-config.json coverCredit + captions[NN]."
+  },
+  "schemaVersion": 1,
+  "series": {
+    "slug": "<series-slug>",
+    "title": "<Series title>"
+  },
+  "currentArticle": "01",
+  "currentPhase": "load-context",
+  "updatedAt": "<ISO-8601 timestamp>",
+  "articles": {
+    "01": {
+      "title": "<Article 1 title>",
+      "phase": "load-context",
+      "status": "pending",
+      "immutableRules": null,
+      "factcheckLog": null,
+      "editorialReview": null,
+      "personaSweep": {
+        "skeleton": null,
+        "resonance": null,
+        "conversion": null
+      },
+      "visualAssets": {
+        "format": "standard",
+        "cover": {
+          "brief": null,
+          "route": null,
+          "candidates": [],
+          "approved": null,
+          "status": "pending"
+        },
+        "figures": [],
+        "carousel": null
+      },
+      "locked": false,
+      "scheduled": null
+    }
+  }
+}

plugins/linkedin-studio/config/image-credit-caption.template.md

@@ -0,0 +1,63 @@
+# Bilde-credit + caption — cover per edition
+
+> **TEMPLATE.** Copy this to `<serie>/linkedin/image-credit-caption.md` and fill it
+> in per series. `/linkedin:newsletter` Step 7.5 (visual-assets phase) reads it and
+> updates the row for the edition in production; the values flow into
+> `<serie>/linkedin/edition-config.json` → `coverCredit` + `captions[NN]`, which
+> `render/build-linkedin.mjs` reads when it builds `POST.html` (Step 8). This file
+> is the human-readable source of truth for *motif + credit + caption*; the JSON is
+> the machine copy the renderer consumes.
+
+LinkedIn-editoren har et **«Add credit and caption»**-felt under hvert bilde. Fyll
+inn per cover. Caption = én kort linje som koder artikkelens signal (det leseren
+skal sitte igjen med), ikke en bildebeskrivelse.
+
+> Format i editoren: ofte ett felt. Lim «Caption — Credit» eller bruk feltene hver
+> for seg om de finnes.
+
+## Verifiseringsplikt — credit skal være ærlig
+
+Er coveret **KI-generert** (Nano Banana Pro / Gemini / DALL·E / Midjourney) →
+credit MÅ si det. Aldri la et AI-bilde framstå som foto eller egenprodusert
+illustrasjon. Eksempel-credit for AI-cover:
+
+**Felles credit (alle editions):** `Illustrasjon generert med <verktøy>` — f.eks.
+`Illustrasjon generert med Google Gemini (Nano Banana Pro)`.
+
+Er coveret et ekte foto eller en håndlaget figur → bytt til den ærlige creditten
+(`Foto: <fotograf>`, `Egenprodusert figur`). Avvik fra felles-creditten føres under.
+
+**Per-edition credit-avvik:** _(list any edition whose credit differs from the
+felles-credit, with the reason — e.g. «Del 3: Egenprodusert figur (kodet SVG)».
+None by default.)_
+
+## Motiv + caption per edition
+
+| Del | Cover (motiv) | Caption |
+|-----|---------------|---------|
+| 01  | _<one-line motif — what the cover depicts>_ | _<one-line caption — the article's signal>_ |
+| 02  | _…_ | _…_ |
+| samle | _<optional samle-post badge/motif>_ | _<optional>_ |
+
+## Naming-konvensjon (cover-filer)
+
+- `cover.png` — **godkjent, fast navn**. Det eneste filnavnet `build-linkedin.mjs`
+  leser. Operator-gaten i Step 7.5 kopierer den godkjente kandidaten hit.
+- `cover-v<N>-kandidat.png` — genererings-forsøk (mcp-image eller etterbehandlet).
+  Flere kan ligge side om side uten å overskrive den godkjente.
+- `cover-raw.png` — valgfri ekstern pre-edit-kilde (DALL·E / Midjourney / fotograf).
+- `fig<N>.png` — inline-figur (`fig1.png`, `fig2.png`, …), referert fra utkast-markdown
+  med `![alt](linkedin/NN/figN.png)` og **lastet opp manuelt** i editoren
+  (`build-linkedin.mjs` embedder ikke figurer).
+
+## Carousel-utgaver
+
+Carousel-editions (typografisk deck via `render/build-carousel.mjs`) har som regel
+**ingen foto-cover** → ingen bilde-credit nødvendig. Slide-kilden er
+`linkedin/NN/carousel.md`, rendret til `linkedin/NN/carousel.pdf`. En carousel-edition
+som *også* legger en feed-cover trenger likevel en rad over.
+
+## Samle-post
+
+Ev. Maskinrommet-/serie-badge (egen asset) → ingen credit. Lenken til serien ligger i
+første kommentar, ikke i bildet.

plugins/linkedin-studio/config/personas.template.md

@@ -0,0 +1,134 @@
+# Reader Persona Library
+
+Reusable reader profiles for the long-form pipeline (`/linkedin:newsletter`).
+A reader persona is **not** a target-audience demographic — it is a named
+reader who reads a finished draft *read-only* and judges whether it **lands**
+(not whether it is "correct"). Personas give direction; the editor holds the
+pen. Personas never write text.
+
+Copy this file to `personas.local.md` and adjust the active set per project:
+
+```bash
+cp config/personas.template.md config/personas.local.md
+```
+
+`personas.local.md` is gitignored (via `*.local.md`) so your active overrides
+stay local. The template ships the three Seres seed personas below; clone,
+trim, or extend them per series.
+
+---
+
+## How the library is used
+
+- **Per-project selection.** `/linkedin:newsletter` (Step 1) picks the relevant
+  personas from this library and marks the primary in the edition brief.
+- **«primær trumfer».** Exactly one persona is the **primær** reader. On
+  conflict between personas, the primær weighs highest. A *secondary* NO caused
+  by role mismatch or an expertise ceiling («this I already know cold») is a
+  SIGNAL that the gate works — accept it, do not distort the text to chase it.
+  A *primær* NO is **not** accepted: the text is revised until the primær
+  reaches a clean YES.
+- **Two sweep modes** (same `persona-reviewer` agent): resonance mode (Step 6,
+  BEFORE lock — «does the point land for this reader?») and conversion mode
+  (Step 9, after lock — binary «would YOU click?» on the hook only).
+
+### The click-gate is blocking (bar = primær ekte JA)
+
+The persona sweep is not advisory — it returns a **blocking verdict**
+(PASS / REWORK / BLOCK), and the bar is the **primær reader's genuine, unqualified
+JA**. The three Seres seed personas are the canonical set: **A = IT-divisjonsdirektør**
+(sekundær), **B = KI-seksjonsleder** (sekundær), **C = Linjeleder** (PRIMÆR — trumfer).
+
+- **Bar = C ekte JA.** A clean, unqualified yes from the primær. **«JA med store
+  forbehold» = NEI.**
+- ⛔ **Hard fail (= omskriv, ikke annotér):** the verdict is BLOCK, regardless of
+  the other axes, when the primær —
+  - «mistet meg» (disengaged before the takeaway), or
+  - does not own the action (the takeaway is someone else's job), or
+  - hits a **sjargong-mur** (a wall of technical vocabulary their `sjargong`
+    rejects), or
+  - hits a **modell-/navne-katalog** (product/model/benchmark names listed for
+    completeness).
+- These are **rewrite triggers**, not annotations the editor can wave through. A
+  *sekundær* NO from a role/expertise ceiling stays a SIGNAL the gate works —
+  never distort the text to chase it.
+
+Each persona documents five fields. Keep the lowercase field keys exactly — the
+pipeline and the structural check key off them:
+
+- **rolle** — who they are and what they own.
+- **avkobler** — what disconnects them / makes them stop reading.
+- **overbeviser** — what convinces them / earns their trust.
+- **ekspertise** — expertise level, including any ceiling that makes basics fall flat.
+- **sjargong** — jargon tolerance (which vocabulary lands, which repels).
+
+---
+
+## Seed personas (Seres series, public-sector AI adoption)
+
+### Persona 1 — IT-divisjonsdirektør (sekundær)
+
+- **rolle** — Leder IT-divisjonen i en stor offentlig virksomhet; eier drift,
+  sikkerhet, arkitektur og leverandørforhold med budsjett- og risikoansvar.
+- **avkobler** — Hype uten driftskonsekvenser; «AI løser alt»; manglende kobling
+  til sikkerhet, forvaltningskrav og totalkostnad; abstrakt strategiprat uten et
+  klart hvem-eier-hva.
+- **overbeviser** — Konkret arkitektur og driftsmodell, etterlevelse/sikkerhet,
+  realistisk totalkostnad, referanser fra sammenlignbar virksomhet, og en tydelig
+  ansvarsdeling.
+- **ekspertise** — Høy teknisk og organisatorisk. Ekspertise-tak på grunnleggende
+  IT-forklaringer: en post som forklarer systemintegrasjon fra bunnen lander ikke
+  (sekundær-NEI her er et signal, ikke en svikt).
+- **sjargong** — Høy toleranse for IT-/arkitektur-sjargong; lav for AI-buzzwords
+  og konsulentspråk.
+
+### Persona 2 — KI-seksjonsleder (sekundær)
+
+- **rolle** — Leder en KI-seksjon; bygger AI-kapabilitet, rådgir ledelsen og
+  balanserer eksperimentering mot forvaltningskrav.
+- **avkobler** — Overforenkling av hva AI er; ignorering av governance, EU AI Act
+  og personvern; «bare kjør i gang»-holdning; manglende erkjennelse av at
+  dømmekraften ikke kan settes ut.
+- **overbeviser** — Nyansert forståelse av hva AI kan og ikke kan, konkret kobling
+  til forvaltningsverdier, erfaringsbasert framfor teoretisk, og ærlighet om
+  begrensninger.
+- **ekspertise** — Høy i AI-domenet. Ekspertise-tak: kjenner modellene og
+  teknikkene, så en «hva er en LLM»-post faller flatt. Verdien ligger i syntese
+  og dømmekraft, ikke grunnkurs.
+- **sjargong** — Høy toleranse for AI-/ML-sjargong; lav for vagt lederspråk og
+  overdreven popularisering.
+
+### Persona 3 — Linjeleder (primær)
+
+> **Dette er primær-personaen.** Ved konflikt mellom personaer vekter denne
+> høyest. En primær-NEI godtas ikke — teksten revideres til ren primær-JA.
+
+- **rolle** — Mellomleder med fag- og personalansvar i offentlig virksomhet; skal
+  beslutte om og hvordan AI tas i bruk i egen enhet, uten dyp teknisk bakgrunn.
+- **avkobler** — Teknisk dypdykk uten «hva betyr dette for meg og mine»;
+  frykt-retorikk; abstrakt policy; språk som forutsetter at hen kan koden.
+- **overbeviser** — Konkrete eksempler fra arbeidshverdagen, et klart ansvars- og
+  dømmekraftsbilde, trygghet på at hen kan ta gode beslutninger uten å være
+  tekniker, og en leder-takeaway hen kan handle på allerede i morgen.
+- **ekspertise** — Lav-til-middels teknisk; høy på ledelse og forvaltning. Trenger
+  oversettelse, ikke nedlatenhet.
+- **sjargong** — Lav toleranse for teknisk sjargong; setter pris på presise,
+  hverdagsnære formuleringer.
+
+---
+
+## Adding a persona
+
+Copy the block below into `personas.local.md` and fill every field. Mark at most
+one persona as `primær` per project; if you add a new primary, demote the old one
+to sekundær.
+
+```markdown
+### Persona N — [Title] ([primær | sekundær])
+
+- **rolle** — [Who they are and what they own.]
+- **avkobler** — [What makes them stop reading.]
+- **overbeviser** — [What earns their trust.]
+- **ekspertise** — [Expertise level + any ceiling that makes basics fall flat.]
+- **sjargong** — [Which vocabulary lands, which repels.]
+```

plugins/linkedin-studio/config/state-file.template.md

@@ -0,0 +1,61 @@
+---
+# LinkedIn Studio State
+# Auto-managed by the linkedin-studio plugin
+# Copy to ~/.claude/linkedin-studio.local.md
+
+# Posting metrics
+last_post_date: null
+first_post_date: null             # YYYY-MM-DD, set once on first post, never changed
+last_post_topic: ""              # Should match an expertise_areas value for pillar tracking
+posts_this_week: 0
+weekly_goal: 3
+current_streak: 0
+longest_streak: 0
+
+# Week tracking (ISO week)
+current_week: ""
+
+# Analytics tracking
+last_import_date: null
+last_import_week: ""
+
+# Milestone tracking
+follower_count: 0
+follower_target: 10000
+target_date: "2026-12-31"
+monthly_growth: []
+projected_10k_date: ""
+growth_rate_needed: 0
+
+# Planning
+next_planned_topic: ""
+pending_5x5x5: false
+content_series_active: ""
+
+# Profile
+expertise_areas:
+  - "general"
+  - ""
+  - ""
+  - ""
+  - ""
+---
+
+# LinkedIn Session State
+
+## Recent Posts
+
+<!-- Updated automatically by Stop hook -->
+<!-- Format: [YYYY-MM-DD] "Hook text..." (chars) - topic_area -->
+
+## Session Notes
+
+<!-- Free-form notes from sessions -->
+
+## Planned Content
+
+<!-- Upcoming posts and topics -->
+
+## Milestone Log
+
+<!-- Updated when follower_count changes. Format: [YYYY-MM] count (+delta) -->

plugins/linkedin-studio/config/user-profile.template.md

@@ -0,0 +1,126 @@
+# User Profile Configuration
+
+Copy this file to `user-profile.local.md` and customize for your needs.
+
+```bash
+cp config/user-profile.template.md config/user-profile.local.md
+```
+
+---
+
+## PERSONALIZATION SETTINGS
+
+### User Profile Context
+
+**Name:** [Your Name]
+**Current Role:** [Your Role] (posting as private individual, not representing employer)
+**Organization:** [Not disclosed / Your Company]
+**Industry/Domain:** [Your Industry]
+
+**Important Disclaimer:** All articles and posts are written as a private individual. Views expressed are personal and do not represent any employer.
+
+**Core Expertise Areas (5 topics):**
+1. [Topic 1]
+2. [Topic 2]
+3. [Topic 3]
+4. [Topic 4]
+5. [Topic 5]
+
+**Target Audience:**
+- **Primary:** [Who are you primarily writing for?]
+- **Secondary:** [Secondary audience]
+- **Geographic focus:** [Region/Country]
+
+**LinkedIn Goals (ranked by priority):**
+1. [ ] Build thought leadership & authority
+2. [ ] Attract speaking opportunities
+3. [ ] Network with peers/influencers
+4. [ ] Generate qualified leads
+5. [ ] Monetization (consulting/courses)
+6. [ ] Recruit talent
+
+---
+
+### Voice & Style Profile
+
+**Tone Preferences (select what applies):**
+- [ ] Professional & authoritative
+- [ ] Conversational & approachable
+- [ ] Storytelling-focused
+- [ ] Data-driven & analytical
+- [ ] Empathetic & supportive
+- [ ] Provocative & contrarian
+
+**Content Style Mix:**
+- Story-based posts
+- Framework/how-to posts
+- Data/research posts
+- Opinion/commentary posts
+- Case study posts
+- Personal reflection posts
+
+**Signature Elements:**
+- **Key frameworks you've developed:** [Your frameworks, or "None yet"]
+- **Recurring themes/angles:** [Your themes]
+- **Phrases you commonly use:** [Your phrases]
+- **Topics to AVOID:** [Topics you never discuss]
+
+**Writing Quirks & Preferences:**
+- **Preferred post length:** [Short 150-500 / Medium 1,200-1,800 / Long 2,000+]
+- **Emoji usage:** [None / Minimal 1-2 / Moderate 3-5]
+- **Question style CTAs:** [Always / Sometimes / Never]
+- **Use of personal anecdotes:** [Always / Sometimes / Rarely]
+- **Technical depth:** [Beginner / Intermediate / Advanced / Adaptive]
+
+---
+
+### Voice Profile Summary
+
+**[Your Name] writes with:**
+
+1. **[Quality 1]:** [Description]
+2. **[Quality 2]:** [Description]
+3. **[Quality 3]:** [Description]
+4. **[Quality 4]:** [Description]
+5. **[Quality 5]:** [Description]
+
+**DO:**
+- [What you always do in your writing]
+- [Another thing you do]
+
+**DON'T:**
+- [What you never do]
+- [Another thing to avoid]
+
+**Universal anti-patterns (keep these — they hold for every author):**
+- **Modell-/navne-katalog.** Do not reel off product names, model names, or
+  benchmarks for completeness. Pick ONE concrete, verifiable (preferably local)
+  case over a list — a name-dump is a jargon wall to a non-technical reader.
+- **Fullstendighet over leser-handling.** Serve what the primary reader can DO
+  from their chair, not everything the author knows. Completeness is not a virtue.
+- **Selvrefererende overhead-åpning.** No meta-commentary about what the text will
+  or will not do, no warm-ups. Start on the reader's problem.
+- **«ikke bare X, men Y», reflex rule-of-three, tacked-on summaries, hedging.**
+
+**Language:** [English / Norwegian / Other]
+
+---
+
+### Strategic Context
+
+**Current LinkedIn Status:**
+- **Follower count:** [Your current count]
+- **90-day growth goal:** [Your goal]
+- **Posting frequency:** [Daily / 3x week / 2x week]
+- **Optimal posting times:** [Your best times, or "To be determined"]
+
+---
+
+### Asset Utilization Preferences
+
+**When creating content, Claude should:**
+- [ ] Check `/assets/examples/` for past post patterns
+- [ ] Reference frameworks from `/assets/frameworks/`
+- [ ] Pull case studies from `/assets/case-studies/`
+- [ ] Incorporate voice samples from `/assets/voice-samples/`
+- [ ] Use research/data from `/assets/research/`